| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 14505, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.4446146774934886e-05, | |
| "loss": 3.7196, | |
| "step": 2901 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.2220306396484375, | |
| "eval_runtime": 19.7102, | |
| "eval_samples_per_second": 49.822, | |
| "eval_steps_per_second": 0.406, | |
| "step": 2901 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.3334610081201164e-05, | |
| "loss": 3.082, | |
| "step": 5802 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.0640523433685303, | |
| "eval_runtime": 1.501, | |
| "eval_samples_per_second": 654.215, | |
| "eval_steps_per_second": 5.33, | |
| "step": 5802 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2223073387467443e-05, | |
| "loss": 2.8677, | |
| "step": 8703 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.9952707290649414, | |
| "eval_runtime": 1.4746, | |
| "eval_samples_per_second": 665.928, | |
| "eval_steps_per_second": 5.425, | |
| "step": 8703 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1111536693733721e-05, | |
| "loss": 2.7326, | |
| "step": 11604 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.962789535522461, | |
| "eval_runtime": 1.4981, | |
| "eval_samples_per_second": 655.5, | |
| "eval_steps_per_second": 5.34, | |
| "step": 11604 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.647, | |
| "step": 14505 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.953909158706665, | |
| "eval_runtime": 1.5027, | |
| "eval_samples_per_second": 653.503, | |
| "eval_steps_per_second": 5.324, | |
| "step": 14505 | |
| } | |
| ], | |
| "max_steps": 14505, | |
| "num_train_epochs": 5, | |
| "total_flos": 6.06254671872e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |