{ "best_metric": 0.84, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0116/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": 158.25697326660156, "learning_rate": 5.974873734152915e-05, "loss": 3.3342, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.6522666666666667, "eval_loss": 1.9411085844039917, "eval_runtime": 14.3331, "eval_samples_per_second": 261.632, "eval_steps_per_second": 4.116, "step": 333 }, { "epoch": 2.0, "grad_norm": 192.94464111328125, "learning_rate": 3.5e-05, "loss": 1.068, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8173333333333334, "eval_loss": 0.6742849349975586, "eval_runtime": 14.1281, "eval_samples_per_second": 265.428, "eval_steps_per_second": 4.176, "step": 666 }, { "epoch": 3.0, "grad_norm": 234.19351196289062, "learning_rate": 1.0251262658470837e-05, "loss": 0.6166, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8392, "eval_loss": 0.5606585741043091, "eval_runtime": 14.2657, "eval_samples_per_second": 262.868, "eval_steps_per_second": 4.136, "step": 999 }, { "epoch": 4.0, "grad_norm": 134.02249145507812, "learning_rate": 0.0, "loss": 0.5222, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.84, "eval_loss": 0.5490079522132874, "eval_runtime": 14.1805, "eval_samples_per_second": 264.448, "eval_steps_per_second": 4.161, "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 }