{ "best_metric": 0.9982142857142857, "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-013/checkpoint-50", "epoch": 23.90909090909091, "eval_steps": 10, "global_step": 60, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.909090909090909, "grad_norm": 21.050426483154297, "learning_rate": 1.888888888888889e-05, "loss": 1.4584, "step": 10 }, { "epoch": 3.909090909090909, "eval_accuracy": 0.6803571428571429, "eval_loss": 1.0501041412353516, "eval_runtime": 7.8893, "eval_samples_per_second": 70.983, "eval_steps_per_second": 8.873, "step": 10 }, { "epoch": 7.909090909090909, "grad_norm": 18.589374542236328, "learning_rate": 1.5185185185185187e-05, "loss": 0.5812, "step": 20 }, { "epoch": 7.909090909090909, "eval_accuracy": 0.9339285714285714, "eval_loss": 0.41678062081336975, "eval_runtime": 8.3006, "eval_samples_per_second": 67.465, "eval_steps_per_second": 8.433, "step": 20 }, { "epoch": 11.909090909090908, "grad_norm": 13.205336570739746, "learning_rate": 1.1481481481481482e-05, "loss": 0.2353, "step": 30 }, { "epoch": 11.909090909090908, "eval_accuracy": 0.9214285714285714, "eval_loss": 0.2735881507396698, "eval_runtime": 7.4198, "eval_samples_per_second": 75.474, "eval_steps_per_second": 9.434, "step": 30 }, { "epoch": 15.909090909090908, "grad_norm": 15.005224227905273, "learning_rate": 7.77777777777778e-06, "loss": 0.1102, "step": 40 }, { "epoch": 15.909090909090908, "eval_accuracy": 0.9821428571428571, "eval_loss": 0.17276060581207275, "eval_runtime": 8.4889, "eval_samples_per_second": 65.969, "eval_steps_per_second": 8.246, "step": 40 }, { "epoch": 19.90909090909091, "grad_norm": 10.179276466369629, "learning_rate": 4.074074074074074e-06, "loss": 0.0623, "step": 50 }, { "epoch": 19.90909090909091, "eval_accuracy": 0.9982142857142857, "eval_loss": 0.10527712851762772, "eval_runtime": 8.7926, "eval_samples_per_second": 63.69, "eval_steps_per_second": 7.961, "step": 50 }, { "epoch": 23.90909090909091, "grad_norm": 2.0169765949249268, "learning_rate": 3.7037037037037036e-07, "loss": 0.0285, "step": 60 }, { "epoch": 23.90909090909091, "eval_accuracy": 0.9964285714285714, "eval_loss": 0.10176356136798859, "eval_runtime": 8.2541, "eval_samples_per_second": 67.845, "eval_steps_per_second": 8.481, "step": 60 }, { "epoch": 23.90909090909091, "step": 60, "total_flos": 5.259589576438579e+17, "train_loss": 0.41265740791956584, "train_runtime": 329.3655, "train_samples_per_second": 7.469, "train_steps_per_second": 0.182 } ], "logging_steps": 10, "max_steps": 60, "num_input_tokens_seen": 0, "num_train_epochs": 30, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.259589576438579e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }