| { | |
| "best_metric": 2.8832545280456543, | |
| "best_model_checkpoint": "output/joji/checkpoint-24", | |
| "epoch": 1.0, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012302403914397873, | |
| "loss": 3.3079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.635498649403293e-05, | |
| "loss": 3.1823, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 3.0143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 2.9346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.8832545280456543, | |
| "eval_runtime": 0.6547, | |
| "eval_samples_per_second": 41.242, | |
| "eval_steps_per_second": 6.11, | |
| "step": 24 | |
| } | |
| ], | |
| "max_steps": 24, | |
| "num_train_epochs": 1, | |
| "total_flos": 24692097024000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |