| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 1125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0008222222222222222, | |
| "loss": 0.2605, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0006444444444444444, | |
| "loss": 0.2056, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.2846032381057739, | |
| "eval_macro-f1": 0.3334545959979333, | |
| "eval_micro-f1": 0.47625951431678143, | |
| "eval_runtime": 15.3528, | |
| "eval_samples_per_second": 65.135, | |
| "eval_steps_per_second": 8.142, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00046666666666666666, | |
| "loss": 0.1915, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002888888888888889, | |
| "loss": 0.1815, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001111111111111111, | |
| "loss": 0.1698, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.24874328076839447, | |
| "eval_macro-f1": 0.40516740460648787, | |
| "eval_micro-f1": 0.5660096690219413, | |
| "eval_runtime": 15.0266, | |
| "eval_samples_per_second": 66.549, | |
| "eval_steps_per_second": 8.319, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1125, | |
| "total_flos": 358938279936000.0, | |
| "train_loss": 0.19838053215874565, | |
| "train_runtime": 189.1751, | |
| "train_samples_per_second": 47.575, | |
| "train_steps_per_second": 5.947 | |
| } | |
| ], | |
| "max_steps": 1125, | |
| "num_train_epochs": 1, | |
| "total_flos": 358938279936000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |