| { | |
| "best_metric": 0.44424504041671753, | |
| "best_model_checkpoint": "sci_intent_classify/checkpoint-1032", | |
| "epoch": 2.0, | |
| "global_step": 1032, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.0310077519379846e-05, | |
| "loss": 0.4199, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8460698689956332, | |
| "eval_loss": 0.4451884925365448, | |
| "eval_runtime": 41.7325, | |
| "eval_samples_per_second": 21.949, | |
| "eval_steps_per_second": 1.39, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 6.201550387596899e-07, | |
| "loss": 0.2676, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8460698689956332, | |
| "eval_loss": 0.44424504041671753, | |
| "eval_runtime": 41.3301, | |
| "eval_samples_per_second": 22.163, | |
| "eval_steps_per_second": 1.403, | |
| "step": 1032 | |
| } | |
| ], | |
| "max_steps": 1032, | |
| "num_train_epochs": 2, | |
| "total_flos": 972744180462054.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |