| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021333333333333333, | |
| "eval_steps": 500, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.972326633975752e-05, | |
| "loss": 1.1857, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.765191054744305e-05, | |
| "loss": 0.8642, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.363468755735123e-05, | |
| "loss": 0.819, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.783564079088477e-05, | |
| "loss": 0.7933, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.049157449684723e-05, | |
| "loss": 0.7945, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.190238384283412e-05, | |
| "loss": 0.7813, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.241880868706075e-05, | |
| "loss": 0.8124, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.242811110572242e-05, | |
| "loss": 0.7499, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.2338261534486844e-05, | |
| "loss": 0.7848, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.2561279283505883e-05, | |
| "loss": 0.7363, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.349640771651611e-05, | |
| "loss": 0.7639, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5513811136094787e-05, | |
| "loss": 0.7834, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.939459113251408e-06, | |
| "loss": 0.7352, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.041815510209396e-06, | |
| "loss": 0.7608, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.0208757505326016e-06, | |
| "loss": 0.778, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.7577, | |
| "step": 1600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1600, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 6.53458201903104e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |