{ "best_metric": 0.8181818181818182, "best_model_checkpoint": "2024_08_15_swinv2-base-patch4-window8-256/checkpoint-174", "epoch": 2.0, "eval_steps": 500, "global_step": 174, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.11494252873563218, "grad_norm": 40.21982192993164, "learning_rate": 5.555555555555557e-06, "loss": 0.369, "step": 10 }, { "epoch": 0.22988505747126436, "grad_norm": 31.26569175720215, "learning_rate": 9.871794871794872e-06, "loss": 0.5608, "step": 20 }, { "epoch": 0.3448275862068966, "grad_norm": 24.969097137451172, "learning_rate": 9.230769230769232e-06, "loss": 0.8375, "step": 30 }, { "epoch": 0.45977011494252873, "grad_norm": 3.7851438522338867, "learning_rate": 8.58974358974359e-06, "loss": 0.4851, "step": 40 }, { "epoch": 0.5747126436781609, "grad_norm": 3.543433904647827, "learning_rate": 7.948717948717949e-06, "loss": 0.507, "step": 50 }, { "epoch": 0.6896551724137931, "grad_norm": 3.535554885864258, "learning_rate": 7.307692307692308e-06, "loss": 0.4749, "step": 60 }, { "epoch": 0.8045977011494253, "grad_norm": 3.087676763534546, "learning_rate": 6.666666666666667e-06, "loss": 0.2292, "step": 70 }, { "epoch": 0.9195402298850575, "grad_norm": 16.41364288330078, "learning_rate": 6.025641025641026e-06, "loss": 0.4908, "step": 80 }, { "epoch": 1.0, "eval_accuracy": 0.7954545454545454, "eval_loss": 0.48821794986724854, "eval_runtime": 28.1268, "eval_samples_per_second": 3.129, "eval_steps_per_second": 3.129, "step": 87 }, { "epoch": 1.0344827586206897, "grad_norm": 21.090808868408203, "learning_rate": 5.384615384615385e-06, "loss": 0.2291, "step": 90 }, { "epoch": 1.1494252873563218, "grad_norm": 48.51396179199219, "learning_rate": 4.743589743589744e-06, "loss": 0.5361, "step": 100 }, { "epoch": 1.264367816091954, "grad_norm": 1.5283576250076294, "learning_rate": 4.102564102564103e-06, "loss": 0.4894, "step": 110 }, { "epoch": 1.3793103448275863, "grad_norm": 2.1673336029052734, "learning_rate": 3.4615384615384617e-06, "loss": 0.444, "step": 120 }, { "epoch": 1.4942528735632183, "grad_norm": 1.3773008584976196, "learning_rate": 2.8205128205128207e-06, "loss": 0.2406, "step": 130 }, { "epoch": 1.6091954022988506, "grad_norm": 4.856438636779785, "learning_rate": 2.1794871794871797e-06, "loss": 0.4014, "step": 140 }, { "epoch": 1.7241379310344827, "grad_norm": 22.820289611816406, "learning_rate": 1.5384615384615387e-06, "loss": 0.8933, "step": 150 }, { "epoch": 1.839080459770115, "grad_norm": 47.16185760498047, "learning_rate": 8.974358974358975e-07, "loss": 0.319, "step": 160 }, { "epoch": 1.9540229885057472, "grad_norm": 4.938830375671387, "learning_rate": 2.564102564102564e-07, "loss": 1.0014, "step": 170 }, { "epoch": 2.0, "eval_accuracy": 0.8181818181818182, "eval_loss": 0.49721577763557434, "eval_runtime": 28.8569, "eval_samples_per_second": 3.05, "eval_steps_per_second": 3.05, "step": 174 }, { "epoch": 2.0, "step": 174, "total_flos": 7.134454803647693e+16, "train_loss": 0.4921485822776268, "train_runtime": 389.2579, "train_samples_per_second": 1.788, "train_steps_per_second": 0.447 } ], "logging_steps": 10, "max_steps": 174, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 7.134454803647693e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }