| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4809, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 1.4582, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.1797, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.0162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.9622, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.9187, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.881, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.884, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.844, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.833, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.8299, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.8017, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.7802, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.8073, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.8148, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.7811, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 16, | |
| "total_flos": 18460240773120.0, | |
| "train_loss": 0.9545502178370953, | |
| "train_runtime": 315.4454, | |
| "train_samples_per_second": 6.34, | |
| "train_steps_per_second": 0.051 | |
| } | |
| ], | |
| "max_steps": 16, | |
| "num_train_epochs": 2, | |
| "total_flos": 18460240773120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |