| { | |
| "best_metric": 3.1062893867492676, | |
| "best_model_checkpoint": "output/bladee/checkpoint-46", | |
| "epoch": 1.0, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001332390992573511, | |
| "loss": 2.6534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001218137945423232, | |
| "loss": 2.6882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00010424345897243074, | |
| "loss": 2.5786, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.255708249541069e-05, | |
| "loss": 2.6681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9258967871997494e-05, | |
| "loss": 2.6912, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.703953841164296e-05, | |
| "loss": 2.7339, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8464652850520685e-05, | |
| "loss": 2.6054, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.679304716725937e-06, | |
| "loss": 2.6629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5992243352900665e-07, | |
| "loss": 2.625, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.1062893867492676, | |
| "eval_runtime": 0.8504, | |
| "eval_samples_per_second": 76.437, | |
| "eval_steps_per_second": 10.584, | |
| "step": 46 | |
| } | |
| ], | |
| "max_steps": 5888, | |
| "num_train_epochs": 128, | |
| "total_flos": 47947087872000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |