{ "best_metric": 0.8696, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0760/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": 40.81962966918945, "learning_rate": 0.0005, "loss": 1.3626, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.8296, "eval_loss": 0.5708016753196716, "eval_runtime": 15.4649, "eval_samples_per_second": 242.485, "eval_steps_per_second": 3.815, "step": 333 }, { "epoch": 2.0, "grad_norm": 43.97241973876953, "learning_rate": 0.0005, "loss": 0.4488, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8589333333333333, "eval_loss": 0.4793437123298645, "eval_runtime": 15.409, "eval_samples_per_second": 243.364, "eval_steps_per_second": 3.829, "step": 666 }, { "epoch": 3.0, "grad_norm": 25.888343811035156, "learning_rate": 0.0005, "loss": 0.2804, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8669333333333333, "eval_loss": 0.4715974032878876, "eval_runtime": 15.5621, "eval_samples_per_second": 240.969, "eval_steps_per_second": 3.791, "step": 999 }, { "epoch": 4.0, "grad_norm": 24.508529663085938, "learning_rate": 0.0005, "loss": 0.2154, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.8696, "eval_loss": 0.49274325370788574, "eval_runtime": 15.4699, "eval_samples_per_second": 242.407, "eval_steps_per_second": 3.814, "step": 1332 } ], "logging_steps": 500, "max_steps": 1665, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.2705716958208e+18, "train_batch_size": 64, "trial_name": null, "trial_params": null }