{ "best_metric": 0.8866666666666667, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0975/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": 124.55803680419922, "learning_rate": 9e-05, "loss": 2.8198, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.7285333333333334, "eval_loss": 1.035683035850525, "eval_runtime": 8.8407, "eval_samples_per_second": 424.175, "eval_steps_per_second": 6.674, "step": 333 }, { "epoch": 2.0, "grad_norm": 107.2367172241211, "learning_rate": 9e-05, "loss": 0.6948, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8256, "eval_loss": 0.5680239796638489, "eval_runtime": 8.8964, "eval_samples_per_second": 421.517, "eval_steps_per_second": 6.632, "step": 666 }, { "epoch": 3.0, "grad_norm": 255.8367919921875, "learning_rate": 9e-05, "loss": 0.4339, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8744, "eval_loss": 0.4293777346611023, "eval_runtime": 8.8384, "eval_samples_per_second": 424.287, "eval_steps_per_second": 6.675, "step": 999 }, { "epoch": 4.0, "grad_norm": 56.477073669433594, "learning_rate": 9e-05, "loss": 0.3076, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.8866666666666667, "eval_loss": 0.3863438069820404, "eval_runtime": 8.7884, "eval_samples_per_second": 426.698, "eval_steps_per_second": 6.713, "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 }