| { | |
| "best_metric": 2.7078893184661865, | |
| "best_model_checkpoint": "output/bryan-adams/checkpoint-57", | |
| "epoch": 1.0, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013461158482121457, | |
| "loss": 3.0903, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00012704167144630924, | |
| "loss": 3.0754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011506151581352585, | |
| "loss": 2.9778, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.957518838012702e-05, | |
| "loss": 2.6513, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.175134934996847e-05, | |
| "loss": 2.7331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.293505690059801e-05, | |
| "loss": 2.7073, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.4546263713777056e-05, | |
| "loss": 2.907, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.7972661667182378e-05, | |
| "loss": 2.6304, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4464961055407408e-05, | |
| "loss": 2.8435, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.042506989064599e-06, | |
| "loss": 2.692, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.1635553598866533e-07, | |
| "loss": 2.7442, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.7078893184661865, | |
| "eval_runtime": 4.1805, | |
| "eval_samples_per_second": 20.811, | |
| "eval_steps_per_second": 2.631, | |
| "step": 57 | |
| } | |
| ], | |
| "max_steps": 57, | |
| "num_train_epochs": 1, | |
| "total_flos": 59051999232000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |