{ "best_metric": 0.8978666666666667, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0990/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": 49.76169967651367, "learning_rate": 0.0002713525491562421, "loss": 1.6502, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.8256, "eval_loss": 0.5836127400398254, "eval_runtime": 8.4529, "eval_samples_per_second": 443.634, "eval_steps_per_second": 6.98, "step": 333 }, { "epoch": 2.0, "grad_norm": 82.36568450927734, "learning_rate": 0.0001963525491562421, "loss": 0.4765, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8602666666666666, "eval_loss": 0.44638821482658386, "eval_runtime": 8.4363, "eval_samples_per_second": 444.506, "eval_steps_per_second": 6.994, "step": 666 }, { "epoch": 3.0, "grad_norm": 37.204444885253906, "learning_rate": 0.0001036474508437579, "loss": 0.2889, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8866666666666667, "eval_loss": 0.36947357654571533, "eval_runtime": 8.4102, "eval_samples_per_second": 445.888, "eval_steps_per_second": 7.015, "step": 999 }, { "epoch": 4.0, "grad_norm": 38.398014068603516, "learning_rate": 2.8647450843757897e-05, "loss": 0.1797, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.8978666666666667, "eval_loss": 0.3559515178203583, "eval_runtime": 8.3912, "eval_samples_per_second": 446.898, "eval_steps_per_second": 7.031, "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 }