| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 4585, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.5656, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7843137254901961, | |
| "eval_combined_score": 0.821189120809614, | |
| "eval_f1": 0.8580645161290321, | |
| "eval_loss": 0.699867844581604, | |
| "eval_runtime": 8.9164, | |
| "eval_samples_per_second": 45.758, | |
| "eval_steps_per_second": 5.72, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.3874, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_combined_score": 0.8389755230951441, | |
| "eval_f1": 0.8691275167785235, | |
| "eval_loss": 0.727956235408783, | |
| "eval_runtime": 8.877, | |
| "eval_samples_per_second": 45.961, | |
| "eval_steps_per_second": 5.745, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.1627, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8161764705882353, | |
| "eval_combined_score": 0.8471126255380201, | |
| "eval_f1": 0.878048780487805, | |
| "eval_loss": 1.127362847328186, | |
| "eval_runtime": 8.9375, | |
| "eval_samples_per_second": 45.65, | |
| "eval_steps_per_second": 5.706, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0751, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_combined_score": 0.8601882613510521, | |
| "eval_f1": 0.8870431893687708, | |
| "eval_loss": 1.0288920402526855, | |
| "eval_runtime": 8.9056, | |
| "eval_samples_per_second": 45.814, | |
| "eval_steps_per_second": 5.727, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0339, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8259803921568627, | |
| "eval_combined_score": 0.8529225141833383, | |
| "eval_f1": 0.8798646362098139, | |
| "eval_loss": 1.087214469909668, | |
| "eval_runtime": 8.9004, | |
| "eval_samples_per_second": 45.841, | |
| "eval_steps_per_second": 5.73, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 4585, | |
| "total_flos": 1.147379926167552e+16, | |
| "train_loss": 0.24493944382329544, | |
| "train_runtime": 1541.0719, | |
| "train_samples_per_second": 11.901, | |
| "train_steps_per_second": 2.975 | |
| } | |
| ], | |
| "max_steps": 4585, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.147379926167552e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |