| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.589622641509434, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7392, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5226, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4216, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3783, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7e-05, | |
| "loss": 0.389, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3473, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3238, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3164, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.691358024691359e-05, | |
| "loss": 0.3214, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.382716049382717e-05, | |
| "loss": 0.3176, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.074074074074075e-05, | |
| "loss": 0.3112, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.765432098765433e-05, | |
| "loss": 0.2775, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.456790123456791e-05, | |
| "loss": 0.2463, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 8.148148148148148e-05, | |
| "loss": 0.2837, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.839506172839507e-05, | |
| "loss": 0.2425, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.530864197530865e-05, | |
| "loss": 0.2824, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 0.2316, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.91358024691358e-05, | |
| "loss": 0.2329, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.60493827160494e-05, | |
| "loss": 0.2712, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.296296296296296e-05, | |
| "loss": 0.2609, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.987654320987654e-05, | |
| "loss": 0.2416, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.679012345679012e-05, | |
| "loss": 0.2109, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.370370370370371e-05, | |
| "loss": 0.2487, | |
| "step": 250 | |
| } | |
| ], | |
| "max_steps": 424, | |
| "num_train_epochs": 1, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |