{ "best_metric": 0.8498666666666667, "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0738/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": 103.27342224121094, "learning_rate": 7.500000000000001e-05, "loss": 2.7924, "step": 333 }, { "epoch": 1.0, "eval_accuracy": 0.7170666666666666, "eval_loss": 1.0600813627243042, "eval_runtime": 7.2439, "eval_samples_per_second": 517.68, "eval_steps_per_second": 8.145, "step": 333 }, { "epoch": 2.0, "grad_norm": 69.00341033935547, "learning_rate": 5e-05, "loss": 0.7538, "step": 666 }, { "epoch": 2.0, "eval_accuracy": 0.8106666666666666, "eval_loss": 0.6125195026397705, "eval_runtime": 7.089, "eval_samples_per_second": 528.986, "eval_steps_per_second": 8.323, "step": 666 }, { "epoch": 3.0, "grad_norm": 184.40866088867188, "learning_rate": 2.5e-05, "loss": 0.487, "step": 999 }, { "epoch": 3.0, "eval_accuracy": 0.84, "eval_loss": 0.49762213230133057, "eval_runtime": 7.1478, "eval_samples_per_second": 524.634, "eval_steps_per_second": 8.254, "step": 999 }, { "epoch": 4.0, "grad_norm": 52.62934112548828, "learning_rate": 0.0, "loss": 0.37, "step": 1332 }, { "epoch": 4.0, "eval_accuracy": 0.8498666666666667, "eval_loss": 0.4809016287326813, "eval_runtime": 7.116, "eval_samples_per_second": 526.985, "eval_steps_per_second": 8.291, "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 }