| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 3116, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 31251.434, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5e-05, | |
| "loss": 31304.524, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5e-05, | |
| "loss": 31288.94, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 5e-05, | |
| "loss": 31300.232, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5e-05, | |
| "loss": 31299.28, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 5e-05, | |
| "loss": 31302.636, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 3116, | |
| "total_flos": 5.941153309497754e+16, | |
| "train_loss": 31291.547015404365, | |
| "train_runtime": 1788.4277, | |
| "train_samples_per_second": 13.937, | |
| "train_steps_per_second": 1.742 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3116, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 5.941153309497754e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |