| { | |
| "best_metric": 0.003647729055956006, | |
| "best_model_checkpoint": "vit-base-patch16-224-finetuned-barkley\\checkpoint-570", | |
| "epoch": 17.0, | |
| "eval_steps": 500, | |
| "global_step": 646, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "train_accuracy": 0.26398026315789475 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.455413341522217, | |
| "learning_rate": 2.0914608267470257e-06, | |
| "loss": 1.6093, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4148818501759678, | |
| "eval_error_rate": 0.5851181498240322, | |
| "eval_f1": 0.406583244487493, | |
| "eval_loss": 1.4340049028396606, | |
| "eval_precision": 0.47685010008788203, | |
| "eval_recall": 0.4342105263157895, | |
| "eval_runtime": 80.0768, | |
| "eval_samples_per_second": 1.898, | |
| "eval_steps_per_second": 0.237, | |
| "eval_top1_accuracy": 0.4342105263157895, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "train_accuracy": 0.5095029239766082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.083907127380371, | |
| "learning_rate": 2.365146216752351e-06, | |
| "loss": 1.2908, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6161337355455003, | |
| "eval_error_rate": 0.3838662644544997, | |
| "eval_f1": 0.615989993007031, | |
| "eval_loss": 1.1747227907180786, | |
| "eval_precision": 0.6587479462326463, | |
| "eval_recall": 0.6118421052631579, | |
| "eval_runtime": 62.2988, | |
| "eval_samples_per_second": 2.44, | |
| "eval_steps_per_second": 0.305, | |
| "eval_top1_accuracy": 0.6118421052631579, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "train_accuracy": 0.7017543859649122 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.073782444000244, | |
| "learning_rate": 2.8189702123460904e-06, | |
| "loss": 1.0409, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7424685771744596, | |
| "eval_error_rate": 0.2575314228255404, | |
| "eval_f1": 0.7293001164996891, | |
| "eval_loss": 0.9174113869667053, | |
| "eval_precision": 0.7381704260651629, | |
| "eval_recall": 0.7302631578947368, | |
| "eval_runtime": 63.0328, | |
| "eval_samples_per_second": 2.411, | |
| "eval_steps_per_second": 0.301, | |
| "eval_top1_accuracy": 0.7302631578947368, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "train_accuracy": 0.8172514619883041 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 4.503601551055908, | |
| "learning_rate": 3.449473887042014e-06, | |
| "loss": 0.781, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8650025138260432, | |
| "eval_error_rate": 0.1349974861739568, | |
| "eval_f1": 0.862176726467179, | |
| "eval_loss": 0.6527765989303589, | |
| "eval_precision": 0.8632378661708033, | |
| "eval_recall": 0.8618421052631579, | |
| "eval_runtime": 64.1793, | |
| "eval_samples_per_second": 2.368, | |
| "eval_steps_per_second": 0.296, | |
| "eval_top1_accuracy": 0.8618421052631579, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "train_accuracy": 0.9027777777777778 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 3.8262150287628174, | |
| "learning_rate": 4.251851708560589e-06, | |
| "loss": 0.5429, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9442885872297637, | |
| "eval_error_rate": 0.05571141277023628, | |
| "eval_f1": 0.9404774954713644, | |
| "eval_loss": 0.41116613149642944, | |
| "eval_precision": 0.9416901233513075, | |
| "eval_recall": 0.9407894736842105, | |
| "eval_runtime": 64.0989, | |
| "eval_samples_per_second": 2.371, | |
| "eval_steps_per_second": 0.296, | |
| "eval_top1_accuracy": 0.9407894736842105, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "train_accuracy": 0.9568713450292398 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 2.5020029544830322, | |
| "learning_rate": 5.219988165325166e-06, | |
| "loss": 0.328, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.981111111111111, | |
| "eval_error_rate": 0.018888888888888955, | |
| "eval_f1": 0.980233547031901, | |
| "eval_loss": 0.22286705672740936, | |
| "eval_precision": 0.9808624413887572, | |
| "eval_recall": 0.9802631578947368, | |
| "eval_runtime": 65.9742, | |
| "eval_samples_per_second": 2.304, | |
| "eval_steps_per_second": 0.288, | |
| "eval_top1_accuracy": 0.9802631578947368, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "train_accuracy": 0.9707602339181286 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 3.700869560241699, | |
| "learning_rate": 6.346504377274108e-06, | |
| "loss": 0.1837, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9877777777777779, | |
| "eval_error_rate": 0.012222222222222134, | |
| "eval_f1": 0.9868484170131115, | |
| "eval_loss": 0.11809363961219788, | |
| "eval_precision": 0.9870857699805068, | |
| "eval_recall": 0.9868421052631579, | |
| "eval_runtime": 64.4539, | |
| "eval_samples_per_second": 2.358, | |
| "eval_steps_per_second": 0.295, | |
| "eval_top1_accuracy": 0.9868421052631579, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "train_accuracy": 0.9766081871345029 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.4798824787139893, | |
| "learning_rate": 7.622814335733349e-06, | |
| "loss": 0.1131, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9944444444444445, | |
| "eval_error_rate": 0.005555555555555536, | |
| "eval_f1": 0.99343678755752, | |
| "eval_loss": 0.06803914159536362, | |
| "eval_precision": 0.9936647173489279, | |
| "eval_recall": 0.993421052631579, | |
| "eval_runtime": 66.8397, | |
| "eval_samples_per_second": 2.274, | |
| "eval_steps_per_second": 0.284, | |
| "eval_top1_accuracy": 0.993421052631579, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "train_accuracy": 0.9912280701754386 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.24450232088565826, | |
| "learning_rate": 9.039190343704055e-06, | |
| "loss": 0.0526, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9944444444444445, | |
| "eval_error_rate": 0.005555555555555536, | |
| "eval_f1": 0.99343678755752, | |
| "eval_loss": 0.0387217253446579, | |
| "eval_precision": 0.9936647173489279, | |
| "eval_recall": 0.993421052631579, | |
| "eval_runtime": 62.2983, | |
| "eval_samples_per_second": 2.44, | |
| "eval_steps_per_second": 0.305, | |
| "eval_top1_accuracy": 0.993421052631579, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "train_accuracy": 0.9948830409356725 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.18834975361824036, | |
| "learning_rate": 1.0584837157796744e-05, | |
| "loss": 0.0283, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9877777777777779, | |
| "eval_error_rate": 0.012222222222222134, | |
| "eval_f1": 0.9868641519390525, | |
| "eval_loss": 0.032834384590387344, | |
| "eval_precision": 0.9873294346978557, | |
| "eval_recall": 0.9868421052631579, | |
| "eval_runtime": 65.4882, | |
| "eval_samples_per_second": 2.321, | |
| "eval_steps_per_second": 0.29, | |
| "eval_top1_accuracy": 0.9868421052631579, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "train_accuracy": 0.9956140350877193 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 0.2787030041217804, | |
| "learning_rate": 1.2247974266721769e-05, | |
| "loss": 0.019, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_error_rate": 0.011111111111111072, | |
| "eval_f1": 0.9867701266776593, | |
| "eval_loss": 0.0223978441208601, | |
| "eval_precision": 0.9872979940891655, | |
| "eval_recall": 0.9868421052631579, | |
| "eval_runtime": 66.7371, | |
| "eval_samples_per_second": 2.278, | |
| "eval_steps_per_second": 0.285, | |
| "eval_top1_accuracy": 0.9868421052631579, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "train_accuracy": 0.9963450292397661 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.9764137268066406, | |
| "learning_rate": 1.401592567923113e-05, | |
| "loss": 0.0148, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9888888888888889, | |
| "eval_error_rate": 0.011111111111111072, | |
| "eval_f1": 0.9867701266776593, | |
| "eval_loss": 0.02013457380235195, | |
| "eval_precision": 0.9872979940891655, | |
| "eval_recall": 0.9868421052631579, | |
| "eval_runtime": 62.9372, | |
| "eval_samples_per_second": 2.415, | |
| "eval_steps_per_second": 0.302, | |
| "eval_top1_accuracy": 0.9868421052631579, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "train_accuracy": 0.9963450292397661 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 0.050672873854637146, | |
| "learning_rate": 1.5875216537171772e-05, | |
| "loss": 0.0095, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9877777777777779, | |
| "eval_error_rate": 0.012222222222222134, | |
| "eval_f1": 0.9868484170131115, | |
| "eval_loss": 0.03958281874656677, | |
| "eval_precision": 0.9870857699805068, | |
| "eval_recall": 0.9868421052631579, | |
| "eval_runtime": 63.5973, | |
| "eval_samples_per_second": 2.39, | |
| "eval_steps_per_second": 0.299, | |
| "eval_top1_accuracy": 0.9868421052631579, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "train_accuracy": 0.9978070175438597 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.06194866821169853, | |
| "learning_rate": 1.7811675817291163e-05, | |
| "loss": 0.007, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 1.0, | |
| "eval_error_rate": 0.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0047844694927334785, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 63.8972, | |
| "eval_samples_per_second": 2.379, | |
| "eval_steps_per_second": 0.297, | |
| "eval_top1_accuracy": 1.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "train_accuracy": 0.9956140350877193 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 0.3071841597557068, | |
| "learning_rate": 1.9810544339029155e-05, | |
| "loss": 0.011, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 1.0, | |
| "eval_error_rate": 0.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.003647729055956006, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 65.5965, | |
| "eval_samples_per_second": 2.317, | |
| "eval_steps_per_second": 0.29, | |
| "eval_top1_accuracy": 1.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "train_accuracy": 0.9978070175438597 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.05617503821849823, | |
| "learning_rate": 2.1856587255089357e-05, | |
| "loss": 0.0071, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9941176470588236, | |
| "eval_error_rate": 0.00588235294117645, | |
| "eval_f1": 0.9934170172927719, | |
| "eval_loss": 0.009170782752335072, | |
| "eval_precision": 0.9935988620199147, | |
| "eval_recall": 0.993421052631579, | |
| "eval_runtime": 66.4048, | |
| "eval_samples_per_second": 2.289, | |
| "eval_steps_per_second": 0.286, | |
| "eval_top1_accuracy": 0.993421052631579, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "train_accuracy": 0.9963450292397661 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 0.02715430036187172, | |
| "learning_rate": 2.393421016741653e-05, | |
| "loss": 0.0103, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9944444444444445, | |
| "eval_error_rate": 0.005555555555555536, | |
| "eval_f1": 0.9934286478144102, | |
| "eval_loss": 0.014811488799750805, | |
| "eval_precision": 0.9936332767402377, | |
| "eval_recall": 0.993421052631579, | |
| "eval_runtime": 64.9042, | |
| "eval_samples_per_second": 2.342, | |
| "eval_steps_per_second": 0.293, | |
| "eval_top1_accuracy": 0.993421052631579, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "step": 646, | |
| "total_flos": 1.601957481669329e+18, | |
| "train_loss": 0.3558414801263219, | |
| "train_runtime": 14288.2591, | |
| "train_samples_per_second": 2.553, | |
| "train_steps_per_second": 0.08 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 1.601957481669329e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |