| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 10378, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.759105800732319e-05, | |
| "loss": 19.9182, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.518211601464637e-05, | |
| "loss": 2.8554, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.2773174021969556e-05, | |
| "loss": 1.1633, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.0364232029292733e-05, | |
| "loss": 0.7392, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.795529003661592e-05, | |
| "loss": 0.5942, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.55463480439391e-05, | |
| "loss": 0.5252, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.313740605126229e-05, | |
| "loss": 0.5016, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.072846405858547e-05, | |
| "loss": 0.4575, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8319522065908656e-05, | |
| "loss": 0.4414, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.5910580073231837e-05, | |
| "loss": 0.4227, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.350163808055502e-05, | |
| "loss": 0.4023, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1092696087878206e-05, | |
| "loss": 0.3792, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.868375409520139e-05, | |
| "loss": 0.3566, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.627481210252457e-05, | |
| "loss": 0.3496, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3865870109847756e-05, | |
| "loss": 0.3438, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.145692811717094e-05, | |
| "loss": 0.3427, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.047986124494123e-06, | |
| "loss": 0.3259, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.639044131817306e-06, | |
| "loss": 0.328, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.2301021391404895e-06, | |
| "loss": 0.318, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.8211601464636733e-06, | |
| "loss": 0.325, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.235988587141037, | |
| "eval_runtime": 169.8494, | |
| "eval_samples_per_second": 65.758, | |
| "eval_steps_per_second": 8.225, | |
| "step": 10378 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10378, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 4.389574183747584e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |