| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9952087611225187, | |
| "global_step": 1641, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.4355751099937147e-05, | |
| "loss": 2.0603, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.070395977372723e-06, | |
| "loss": 1.3222, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.7850408548082967e-06, | |
| "loss": 0.6524, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1641, | |
| "total_flos": 123535515189248.0, | |
| "train_loss": 1.2714026414498114, | |
| "train_runtime": 44021.0599, | |
| "train_samples_per_second": 4.779, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "max_steps": 1641, | |
| "num_train_epochs": 3, | |
| "total_flos": 123535515189248.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |