| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0528, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.7376237623762376, | |
| "eval_loss": 0.1697508543729782, | |
| "eval_runtime": 11.9306, | |
| "eval_samples_per_second": 228.236, | |
| "eval_steps_per_second": 1.844, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.003, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_f1": 0.8160919540229885, | |
| "eval_loss": 0.16279307007789612, | |
| "eval_runtime": 11.9395, | |
| "eval_samples_per_second": 228.067, | |
| "eval_steps_per_second": 1.843, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 860, | |
| "total_flos": 2.86580561498112e+16, | |
| "train_loss": 0.02791861295700073, | |
| "train_runtime": 1253.6999, | |
| "train_samples_per_second": 86.879, | |
| "train_steps_per_second": 0.686 | |
| } | |
| ], | |
| "max_steps": 860, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.86580561498112e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |