{ "best_metric": 0.7826666666666666, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0429/checkpoints/checkpoint-999", "epoch": 3.0, "eval_steps": 500, "global_step": 999, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 108.4359130859375, "learning_rate": 3e-05, "loss": 3.83, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.4288, "eval_loss": 3.639512538909912, "eval_runtime": 14.2625, "eval_samples_per_second": 262.928, "eval_steps_per_second": 4.137, "step": 333 }, { "epoch": 2.0, "grad_norm": 109.40319061279297, "learning_rate": 3e-05, "loss": 2.9112, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.6616, "eval_loss": 1.9469722509384155, "eval_runtime": 14.1683, "eval_samples_per_second": 264.674, "eval_steps_per_second": 4.164, "step": 666 }, { "epoch": 3.0, "grad_norm": 159.47296142578125, "learning_rate": 3e-05, "loss": 1.2967, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.7826666666666666, "eval_loss": 0.9053466320037842, "eval_runtime": 14.1805, "eval_samples_per_second": 264.448, "eval_steps_per_second": 4.161, "step": 999 } ], "logging_steps": 500, "max_steps": 999, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 2.4529287718656e+18, "train_batch_size": 64, "trial_name": null, "trial_params": null }