| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 1980, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.25, |
| "learning_rate": 8.314606741573035e-06, |
| "loss": 4.2194, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 5.50561797752809e-06, |
| "loss": 3.3918, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.51, |
| "eval_loss": 3.1021862030029297, |
| "eval_runtime": 23.3073, |
| "eval_samples_per_second": 42.519, |
| "eval_steps_per_second": 21.281, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 2.696629213483146e-06, |
| "loss": 3.2545, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 1980, |
| "total_flos": 306526787665920.0, |
| "train_loss": 3.5130721891769254, |
| "train_runtime": 755.7574, |
| "train_samples_per_second": 5.24, |
| "train_steps_per_second": 2.62 |
| } |
| ], |
| "max_steps": 1980, |
| "num_train_epochs": 1, |
| "total_flos": 306526787665920.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
