{ "best_metric": 0.7477333333333334, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0332/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": 365.205810546875, "learning_rate": 3.7500000000000003e-05, "loss": 3.764, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.47146666666666665, "eval_loss": 3.383570909500122, "eval_runtime": 14.6367, "eval_samples_per_second": 256.206, "eval_steps_per_second": 4.031, "step": 333 }, { "epoch": 2.0, "grad_norm": 162.07933044433594, "learning_rate": 2.5e-05, "loss": 2.5716, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.6546666666666666, "eval_loss": 1.7165641784667969, "eval_runtime": 14.5952, "eval_samples_per_second": 256.934, "eval_steps_per_second": 4.042, "step": 666 }, { "epoch": 3.0, "grad_norm": 264.2698669433594, "learning_rate": 1.25e-05, "loss": 1.4218, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.7370666666666666, "eval_loss": 1.1565073728561401, "eval_runtime": 14.5238, "eval_samples_per_second": 258.197, "eval_steps_per_second": 4.062, "step": 999 }, { "epoch": 4.0, "grad_norm": 331.9979553222656, "learning_rate": 0.0, "loss": 1.1112, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.7477333333333334, "eval_loss": 1.0315948724746704, "eval_runtime": 14.5808, "eval_samples_per_second": 257.187, "eval_steps_per_second": 4.046, "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 }