{ "best_metric": 0.8909333333333334, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0130/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": 37.760292053222656, "learning_rate": 0.00025606601717798207, "loss": 1.5893, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.8152, "eval_loss": 0.6142104268074036, "eval_runtime": 14.6753, "eval_samples_per_second": 255.532, "eval_steps_per_second": 4.02, "step": 333 }, { "epoch": 2.0, "grad_norm": 30.022668838500977, "learning_rate": 0.00015, "loss": 0.4568, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8648, "eval_loss": 0.4314861297607422, "eval_runtime": 14.8056, "eval_samples_per_second": 253.283, "eval_steps_per_second": 3.985, "step": 666 }, { "epoch": 3.0, "grad_norm": 33.27289581298828, "learning_rate": 4.3933982822017876e-05, "loss": 0.278, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8818666666666667, "eval_loss": 0.37829309701919556, "eval_runtime": 15.456, "eval_samples_per_second": 242.623, "eval_steps_per_second": 3.817, "step": 999 }, { "epoch": 4.0, "grad_norm": 27.2575740814209, "learning_rate": 0.0, "loss": 0.1959, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.8909333333333334, "eval_loss": 0.3674047589302063, "eval_runtime": 15.7134, "eval_samples_per_second": 238.65, "eval_steps_per_second": 3.755, "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 }