| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 10969, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9699759929498285e-05, | |
| "loss": 2.1315, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9396480991886225e-05, | |
| "loss": 1.298, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9092594280852098e-05, | |
| "loss": 1.1595, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8788707569817974e-05, | |
| "loss": 1.16, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8484820858783847e-05, | |
| "loss": 1.0615, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.818093414774972e-05, | |
| "loss": 1.0704, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.7877047436715592e-05, | |
| "loss": 1.029, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.7573768499103536e-05, | |
| "loss": 1.0325, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.726988178806941e-05, | |
| "loss": 1.0336, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.696599507703528e-05, | |
| "loss": 0.9839, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.6662108366001154e-05, | |
| "loss": 0.9754, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.635822165496703e-05, | |
| "loss": 1.0014, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.6054334943932903e-05, | |
| "loss": 0.9806, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.5751056006320843e-05, | |
| "loss": 0.9233, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.544716929528672e-05, | |
| "loss": 0.9523, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.514389035767466e-05, | |
| "loss": 0.9003, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4840003646640532e-05, | |
| "loss": 0.9033, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4536116935606408e-05, | |
| "loss": 0.9347, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.4232230224572281e-05, | |
| "loss": 0.9087, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.3928343513538154e-05, | |
| "loss": 0.8889, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3624456802504026e-05, | |
| "loss": 0.8578, | |
| "step": 10500 | |
| } | |
| ], | |
| "max_steps": 32907, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.292748391980032e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |