| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 4960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.994959677419355e-05, | |
| "loss": 10.8422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.4798387096774196e-05, | |
| "loss": 6.1187, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.991935483870968e-05, | |
| "loss": 5.3286, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.487903225806452e-05, | |
| "loss": 5.1872, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.9838709677419357e-05, | |
| "loss": 5.1382, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.4798387096774196e-05, | |
| "loss": 5.1171, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.975806451612903e-05, | |
| "loss": 5.0995, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.4717741935483872e-05, | |
| "loss": 5.0782, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 5.0796, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 4.637096774193548e-06, | |
| "loss": 5.0694, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 4960, | |
| "total_flos": 2.2795257419613e+16, | |
| "train_loss": 4.613737192461567, | |
| "train_runtime": 2303.2997, | |
| "train_samples_per_second": 34.433, | |
| "train_steps_per_second": 2.153 | |
| } | |
| ], | |
| "max_steps": 4960, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.2795257419613e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |