| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6806930693069307, | |
| "eval_steps": 500, | |
| "global_step": 1100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.948432343234324e-05, | |
| "loss": 3.3362, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.8968646864686466e-05, | |
| "loss": 1.728, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8452970297029704e-05, | |
| "loss": 1.6496, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.793729372937294e-05, | |
| "loss": 1.6284, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7421617161716174e-05, | |
| "loss": 1.6107, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6905940594059406e-05, | |
| "loss": 1.5895, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6390264026402644e-05, | |
| "loss": 1.5785, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.5874587458745876e-05, | |
| "loss": 1.5796, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5358910891089114e-05, | |
| "loss": 1.5762, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4843234323432346e-05, | |
| "loss": 1.5726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.432755775577558e-05, | |
| "loss": 1.571, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3811881188118816e-05, | |
| "loss": 1.5665, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.329620462046205e-05, | |
| "loss": 1.5658, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.278052805280528e-05, | |
| "loss": 1.5666, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.226485148514852e-05, | |
| "loss": 1.5502, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.174917491749175e-05, | |
| "loss": 1.5604, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.123349834983499e-05, | |
| "loss": 1.5564, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.071782178217822e-05, | |
| "loss": 1.5492, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.020214521452145e-05, | |
| "loss": 1.5514, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.968646864686469e-05, | |
| "loss": 1.5458, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.917079207920793e-05, | |
| "loss": 1.5398, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.865511551155115e-05, | |
| "loss": 1.5374, | |
| "step": 1100 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4848, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 4.609002406359859e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |