| { | |
| "best_metric": 1.3811118602752686, | |
| "best_model_checkpoint": "output/the-king-and-the-jester/checkpoint-41", | |
| "epoch": 1.0, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001322266681456038, | |
| "loss": 1.4322, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011802778132101399, | |
| "loss": 1.3789, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.666210850995409e-05, | |
| "loss": 1.4705, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.12275675311363e-05, | |
| "loss": 1.3895, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.541204214117678e-05, | |
| "loss": 1.4426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.295865696864204e-05, | |
| "loss": 1.4315, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.123042792471563e-06, | |
| "loss": 1.3887, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.0128603879541336e-07, | |
| "loss": 1.4529, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3811118602752686, | |
| "eval_runtime": 2.6826, | |
| "eval_samples_per_second": 20.875, | |
| "eval_steps_per_second": 2.609, | |
| "step": 41 | |
| } | |
| ], | |
| "max_steps": 574, | |
| "num_train_epochs": 14, | |
| "total_flos": 42590601216000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |