| { | |
| "best_metric": 0.8746666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0539/checkpoints/checkpoint-1332", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1332, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 113.79971313476562, | |
| "learning_rate": 7e-05, | |
| "loss": 3.4037, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_loss": 2.08650803565979, | |
| "eval_runtime": 9.3394, | |
| "eval_samples_per_second": 401.524, | |
| "eval_steps_per_second": 6.317, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 48.82363510131836, | |
| "learning_rate": 7e-05, | |
| "loss": 1.1835, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8098666666666666, | |
| "eval_loss": 0.6989992260932922, | |
| "eval_runtime": 9.2225, | |
| "eval_samples_per_second": 406.614, | |
| "eval_steps_per_second": 6.397, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 63.07221603393555, | |
| "learning_rate": 7e-05, | |
| "loss": 0.6322, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8514666666666667, | |
| "eval_loss": 0.5104021430015564, | |
| "eval_runtime": 9.2757, | |
| "eval_samples_per_second": 404.283, | |
| "eval_steps_per_second": 6.361, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 66.16280364990234, | |
| "learning_rate": 7e-05, | |
| "loss": 0.4639, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8746666666666667, | |
| "eval_loss": 0.43885722756385803, | |
| "eval_runtime": 9.3881, | |
| "eval_samples_per_second": 399.44, | |
| "eval_steps_per_second": 6.285, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1332, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |