{ "best_metric": 0.7821333333333333, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0729/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": 103.88338470458984, "learning_rate": 5.974873734152915e-05, "loss": 3.3837, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.5605333333333333, "eval_loss": 2.202631711959839, "eval_runtime": 15.0578, "eval_samples_per_second": 249.041, "eval_steps_per_second": 3.918, "step": 333 }, { "epoch": 2.0, "grad_norm": 132.1537628173828, "learning_rate": 3.5e-05, "loss": 1.3284, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.744, "eval_loss": 0.9008901119232178, "eval_runtime": 15.1564, "eval_samples_per_second": 247.42, "eval_steps_per_second": 3.893, "step": 666 }, { "epoch": 3.0, "grad_norm": 119.50969696044922, "learning_rate": 1.0251262658470837e-05, "loss": 0.8548, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.7746666666666666, "eval_loss": 0.7643803358078003, "eval_runtime": 14.9234, "eval_samples_per_second": 251.282, "eval_steps_per_second": 3.954, "step": 999 }, { "epoch": 4.0, "grad_norm": 99.21233367919922, "learning_rate": 0.0, "loss": 0.7616, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.7821333333333333, "eval_loss": 0.7301152348518372, "eval_runtime": 14.4051, "eval_samples_per_second": 260.325, "eval_steps_per_second": 4.096, "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 }