{ "best_metric": 0.8669333333333333, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0769/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": 107.70264434814453, "learning_rate": 8.535533905932738e-05, "loss": 2.6604, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.7453333333333333, "eval_loss": 0.9006837010383606, "eval_runtime": 7.0199, "eval_samples_per_second": 534.196, "eval_steps_per_second": 8.405, "step": 333 }, { "epoch": 2.0, "grad_norm": 135.91204833984375, "learning_rate": 5e-05, "loss": 0.637, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8498666666666667, "eval_loss": 0.49153149127960205, "eval_runtime": 7.1159, "eval_samples_per_second": 526.991, "eval_steps_per_second": 8.291, "step": 666 }, { "epoch": 3.0, "grad_norm": 164.11947631835938, "learning_rate": 1.4644660940672627e-05, "loss": 0.3828, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.8669333333333333, "eval_loss": 0.4312443435192108, "eval_runtime": 7.1907, "eval_samples_per_second": 521.51, "eval_steps_per_second": 8.205, "step": 999 } ], "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": false }, "attributes": {} } }, "total_flos": 2.4529287718656e+18, "train_batch_size": 64, "trial_name": null, "trial_params": null }