{ "best_metric": 0.030909119173884392, "best_model_checkpoint": "vit-large-patch16-224-new-dungeon-geo-morphs-004/checkpoint-60", "epoch": 26.666666666666668, "eval_steps": 10, "global_step": 60, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 4.444444444444445, "grad_norm": 21.82240867614746, "learning_rate": 1.888888888888889e-05, "loss": 1.2665, "step": 10 }, { "epoch": 4.444444444444445, "eval_accuracy": 0.8936170212765957, "eval_loss": 0.5981470942497253, "eval_runtime": 0.6381, "eval_samples_per_second": 73.661, "eval_steps_per_second": 9.404, "step": 10 }, { "epoch": 8.88888888888889, "grad_norm": 31.40165138244629, "learning_rate": 1.5185185185185187e-05, "loss": 0.4646, "step": 20 }, { "epoch": 8.88888888888889, "eval_accuracy": 0.9787234042553191, "eval_loss": 0.1824849247932434, "eval_runtime": 0.6745, "eval_samples_per_second": 69.676, "eval_steps_per_second": 8.895, "step": 20 }, { "epoch": 13.333333333333334, "grad_norm": 6.628233909606934, "learning_rate": 1.1481481481481482e-05, "loss": 0.135, "step": 30 }, { "epoch": 13.333333333333334, "eval_accuracy": 0.9574468085106383, "eval_loss": 0.07716856896877289, "eval_runtime": 0.68, "eval_samples_per_second": 69.12, "eval_steps_per_second": 8.824, "step": 30 }, { "epoch": 17.77777777777778, "grad_norm": 1.2984089851379395, "learning_rate": 7.77777777777778e-06, "loss": 0.0486, "step": 40 }, { "epoch": 17.77777777777778, "eval_accuracy": 0.9574468085106383, "eval_loss": 0.06602360308170319, "eval_runtime": 0.6359, "eval_samples_per_second": 73.91, "eval_steps_per_second": 9.435, "step": 40 }, { "epoch": 22.22222222222222, "grad_norm": 9.370550155639648, "learning_rate": 4.074074074074074e-06, "loss": 0.0254, "step": 50 }, { "epoch": 22.22222222222222, "eval_accuracy": 0.9574468085106383, "eval_loss": 0.043419163674116135, "eval_runtime": 0.694, "eval_samples_per_second": 67.727, "eval_steps_per_second": 8.646, "step": 50 }, { "epoch": 26.666666666666668, "grad_norm": 1.1367130279541016, "learning_rate": 3.7037037037037036e-07, "loss": 0.0108, "step": 60 }, { "epoch": 26.666666666666668, "eval_accuracy": 1.0, "eval_loss": 0.030909119173884392, "eval_runtime": 0.6256, "eval_samples_per_second": 75.132, "eval_steps_per_second": 9.591, "step": 60 }, { "epoch": 26.666666666666668, "step": 60, "total_flos": 4.974678329479004e+17, "train_loss": 0.32515382394194603, "train_runtime": 485.8441, "train_samples_per_second": 4.199, "train_steps_per_second": 0.123 } ], "logging_steps": 10, "max_steps": 60, "num_input_tokens_seen": 0, "num_train_epochs": 30, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.01 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.974678329479004e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }