| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.716981132075472, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7283870967741936, | |
| "eval_loss": 3.1895267963409424, | |
| "eval_runtime": 2.407, | |
| "eval_samples_per_second": 1287.91, | |
| "eval_steps_per_second": 27.005, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.606918238993711e-05, | |
| "loss": 3.7135, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8558064516129033, | |
| "eval_loss": 1.6236796379089355, | |
| "eval_runtime": 2.447, | |
| "eval_samples_per_second": 1266.857, | |
| "eval_steps_per_second": 26.563, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9093548387096774, | |
| "eval_loss": 0.8421777486801147, | |
| "eval_runtime": 2.447, | |
| "eval_samples_per_second": 1266.858, | |
| "eval_steps_per_second": 26.563, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.2138364779874214e-05, | |
| "loss": 1.4042, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9312903225806451, | |
| "eval_loss": 0.5201095342636108, | |
| "eval_runtime": 2.462, | |
| "eval_samples_per_second": 1259.139, | |
| "eval_steps_per_second": 26.401, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 8.207547169811321e-06, | |
| "loss": 0.5087, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2544, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "total_flos": 448150785781692.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.5656189676317626, | |
| "num_train_epochs": 8, | |
| "temperature": 9 | |
| } | |
| } | |