| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 12756, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.804013797428661e-05, | |
| "loss": 2.1839, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.608027594857322e-05, | |
| "loss": 1.9717, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.412041392285983e-05, | |
| "loss": 1.8822, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.216055189714644e-05, | |
| "loss": 1.8259, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.020068987143305e-05, | |
| "loss": 1.7765, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.824082784571966e-05, | |
| "loss": 1.7298, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.628096582000627e-05, | |
| "loss": 1.7051, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.432110379429289e-05, | |
| "loss": 1.6743, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.236124176857949e-05, | |
| "loss": 1.6451, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.0401379742866105e-05, | |
| "loss": 1.6222, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8441517717152715e-05, | |
| "loss": 1.6055, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.648165569143932e-05, | |
| "loss": 1.593, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4521793665725935e-05, | |
| "loss": 1.5686, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.256193164001254e-05, | |
| "loss": 1.5539, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.0602069614299155e-05, | |
| "loss": 1.5416, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.8642207588585765e-05, | |
| "loss": 1.5314, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6682345562872375e-05, | |
| "loss": 1.5281, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.4722483537158985e-05, | |
| "loss": 1.5097, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.2762621511445595e-05, | |
| "loss": 1.4938, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0802759485732206e-05, | |
| "loss": 1.4836, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.842897460018814e-06, | |
| "loss": 1.481, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.883035434305425e-06, | |
| "loss": 1.473, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.923173408592035e-06, | |
| "loss": 1.4617, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.963311382878645e-06, | |
| "loss": 1.46, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.0034493571652555e-06, | |
| "loss": 1.459, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 12756, | |
| "total_flos": 8.064944553679258e+16, | |
| "train_loss": 1.6269652545171758, | |
| "train_runtime": 39015.8853, | |
| "train_samples_per_second": 7.847, | |
| "train_steps_per_second": 0.327 | |
| } | |
| ], | |
| "max_steps": 12756, | |
| "num_train_epochs": 3, | |
| "total_flos": 8.064944553679258e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |