{ "best_metric": 0.11935162544250488, "best_model_checkpoint": "vit-fine-tuned-image-classification-beans\\checkpoint-100", "epoch": 3.0, "eval_steps": 100, "global_step": 195, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.15384615384615385, "grad_norm": 1.954852819442749, "learning_rate": 0.00018974358974358974, "loss": 0.8193, "step": 10 }, { "epoch": 0.3076923076923077, "grad_norm": 0.7795785069465637, "learning_rate": 0.0001794871794871795, "loss": 0.3169, "step": 20 }, { "epoch": 0.46153846153846156, "grad_norm": 0.6669347882270813, "learning_rate": 0.00016923076923076923, "loss": 0.2594, "step": 30 }, { "epoch": 0.6153846153846154, "grad_norm": 1.080024003982544, "learning_rate": 0.00015897435897435896, "loss": 0.2773, "step": 40 }, { "epoch": 0.7692307692307693, "grad_norm": 0.25586265325546265, "learning_rate": 0.00014871794871794872, "loss": 0.1443, "step": 50 }, { "epoch": 0.9230769230769231, "grad_norm": 1.5575575828552246, "learning_rate": 0.00013846153846153847, "loss": 0.2078, "step": 60 }, { "epoch": 1.0769230769230769, "grad_norm": 0.294820100069046, "learning_rate": 0.00012820512820512823, "loss": 0.1707, "step": 70 }, { "epoch": 1.2307692307692308, "grad_norm": 0.15214024484157562, "learning_rate": 0.00011794871794871796, "loss": 0.0791, "step": 80 }, { "epoch": 1.3846153846153846, "grad_norm": 2.057741165161133, "learning_rate": 0.0001076923076923077, "loss": 0.0404, "step": 90 }, { "epoch": 1.5384615384615383, "grad_norm": 4.684866428375244, "learning_rate": 9.743589743589744e-05, "loss": 0.1184, "step": 100 }, { "epoch": 1.5384615384615383, "eval_accuracy": 0.9624060150375939, "eval_loss": 0.11935162544250488, "eval_runtime": 30.276, "eval_samples_per_second": 4.393, "eval_steps_per_second": 0.562, "step": 100 }, { "epoch": 1.6923076923076923, "grad_norm": 0.13851244747638702, "learning_rate": 8.717948717948718e-05, "loss": 0.073, "step": 110 }, { "epoch": 1.8461538461538463, "grad_norm": 0.1308572143316269, "learning_rate": 7.692307692307693e-05, "loss": 0.086, "step": 120 }, { "epoch": 2.0, "grad_norm": 0.10320036113262177, "learning_rate": 6.666666666666667e-05, "loss": 0.0231, "step": 130 }, { "epoch": 2.1538461538461537, "grad_norm": 0.32273927330970764, "learning_rate": 5.6410256410256414e-05, "loss": 0.0209, "step": 140 }, { "epoch": 2.3076923076923075, "grad_norm": 0.26616284251213074, "learning_rate": 4.615384615384616e-05, "loss": 0.0183, "step": 150 }, { "epoch": 2.4615384615384617, "grad_norm": 0.09009333699941635, "learning_rate": 3.58974358974359e-05, "loss": 0.0517, "step": 160 }, { "epoch": 2.6153846153846154, "grad_norm": 0.08223859965801239, "learning_rate": 2.564102564102564e-05, "loss": 0.0353, "step": 170 }, { "epoch": 2.769230769230769, "grad_norm": 0.08049986511468887, "learning_rate": 1.5384615384615387e-05, "loss": 0.0435, "step": 180 }, { "epoch": 2.9230769230769234, "grad_norm": 0.14337565004825592, "learning_rate": 5.128205128205128e-06, "loss": 0.0161, "step": 190 }, { "epoch": 3.0, "step": 195, "total_flos": 2.4038230623573197e+17, "train_loss": 0.14413543897561537, "train_runtime": 2492.1418, "train_samples_per_second": 1.245, "train_steps_per_second": 0.078 } ], "logging_steps": 10, "max_steps": 195, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.4038230623573197e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }