{ "best_metric": 0.8376, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0469/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": 62.07609939575195, "learning_rate": 3e-05, "loss": 3.8133, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.4696, "eval_loss": 3.6090831756591797, "eval_runtime": 14.1229, "eval_samples_per_second": 265.526, "eval_steps_per_second": 4.178, "step": 333 }, { "epoch": 2.0, "grad_norm": 124.3885269165039, "learning_rate": 3e-05, "loss": 2.8292, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.6666666666666666, "eval_loss": 1.855066180229187, "eval_runtime": 14.2193, "eval_samples_per_second": 263.725, "eval_steps_per_second": 4.149, "step": 666 }, { "epoch": 3.0, "grad_norm": 119.76927947998047, "learning_rate": 3e-05, "loss": 1.2073, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8045333333333333, "eval_loss": 0.8274251222610474, "eval_runtime": 14.1167, "eval_samples_per_second": 265.643, "eval_steps_per_second": 4.179, "step": 999 }, { "epoch": 4.0, "grad_norm": 152.52467346191406, "learning_rate": 3e-05, "loss": 0.6702, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.8376, "eval_loss": 0.5758199691772461, "eval_runtime": 13.8947, "eval_samples_per_second": 269.886, "eval_steps_per_second": 4.246, "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 }