| { | |
| "best_metric": 0.33705124258995056, | |
| "best_model_checkpoint": "test_training/checkpoint-1126", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1689, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5198342214328006e-05, | |
| "loss": 0.4813, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8415, | |
| "eval_loss": 0.3723330795764923, | |
| "eval_runtime": 4.6116, | |
| "eval_samples_per_second": 433.689, | |
| "eval_steps_per_second": 13.661, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.039668442865601e-05, | |
| "loss": 0.2779, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8705, | |
| "eval_loss": 0.33705124258995056, | |
| "eval_runtime": 4.608, | |
| "eval_samples_per_second": 434.032, | |
| "eval_steps_per_second": 13.672, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.595026642984015e-06, | |
| "loss": 0.1523, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.878, | |
| "eval_loss": 0.43207448720932007, | |
| "eval_runtime": 4.6165, | |
| "eval_samples_per_second": 433.227, | |
| "eval_steps_per_second": 13.647, | |
| "step": 1689 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1689, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4984396857213696.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |