| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.8, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.4452, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.4168, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.3512, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.306, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.3201, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.2128, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.2058, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.1738, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.1371, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1345, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0901, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.087, | |
| "step": 6000 | |
| } | |
| ], | |
| "max_steps": 6250, | |
| "num_train_epochs": 5, | |
| "total_flos": 1047523211328192.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |