| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 3354, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.105545617173524e-06, | |
| "loss": 0.6881, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.211091234347049e-06, | |
| "loss": 0.4955, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8793565683646113, | |
| "eval_f1": 0.8793090346786706, | |
| "eval_loss": 0.3616451621055603, | |
| "eval_precision": 0.8805569789010309, | |
| "eval_recall": 0.8793565683646113, | |
| "eval_runtime": 59.9562, | |
| "eval_samples_per_second": 18.664, | |
| "eval_steps_per_second": 2.335, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 7.316636851520573e-06, | |
| "loss": 0.2764, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 6.422182468694097e-06, | |
| "loss": 0.2205, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8766756032171582, | |
| "eval_f1": 0.8764664011056418, | |
| "eval_loss": 0.4942081570625305, | |
| "eval_precision": 0.8772358831944725, | |
| "eval_recall": 0.8766756032171582, | |
| "eval_runtime": 59.8387, | |
| "eval_samples_per_second": 18.7, | |
| "eval_steps_per_second": 2.34, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.527728085867621e-06, | |
| "loss": 0.1486, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.633273703041145e-06, | |
| "loss": 0.0856, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 5590, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.561969933062336e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |