| { | |
| "best_metric": 0.15817709267139435, | |
| "best_model_checkpoint": "portuguese_meals_image_detection/checkpoint-5070", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 5070, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7986627043090639, | |
| "eval_loss": 2.3052420616149902, | |
| "eval_runtime": 22.7197, | |
| "eval_samples_per_second": 59.244, | |
| "eval_steps_per_second": 7.438, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9049034175334324, | |
| "eval_loss": 1.5531599521636963, | |
| "eval_runtime": 22.3802, | |
| "eval_samples_per_second": 60.143, | |
| "eval_steps_per_second": 7.551, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 9.103585657370518e-06, | |
| "loss": 1.9788, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9420505200594353, | |
| "eval_loss": 1.1377794742584229, | |
| "eval_runtime": 22.8971, | |
| "eval_samples_per_second": 58.785, | |
| "eval_steps_per_second": 7.381, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9613670133729569, | |
| "eval_loss": 0.8949278593063354, | |
| "eval_runtime": 22.8451, | |
| "eval_samples_per_second": 58.919, | |
| "eval_steps_per_second": 7.398, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9710252600297177, | |
| "eval_loss": 0.7272208333015442, | |
| "eval_runtime": 22.5952, | |
| "eval_samples_per_second": 59.57, | |
| "eval_steps_per_second": 7.479, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 8.107569721115539e-06, | |
| "loss": 0.7727, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9769687964338781, | |
| "eval_loss": 0.6021968126296997, | |
| "eval_runtime": 22.9952, | |
| "eval_samples_per_second": 58.534, | |
| "eval_steps_per_second": 7.349, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9799405646359584, | |
| "eval_loss": 0.5113309621810913, | |
| "eval_runtime": 22.744, | |
| "eval_samples_per_second": 59.18, | |
| "eval_steps_per_second": 7.431, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9806835066864784, | |
| "eval_loss": 0.4436838626861572, | |
| "eval_runtime": 22.2626, | |
| "eval_samples_per_second": 60.46, | |
| "eval_steps_per_second": 7.591, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 7.111553784860559e-06, | |
| "loss": 0.4181, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9799405646359584, | |
| "eval_loss": 0.38924625515937805, | |
| "eval_runtime": 22.8549, | |
| "eval_samples_per_second": 58.893, | |
| "eval_steps_per_second": 7.394, | |
| "step": 1521 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9814264487369985, | |
| "eval_loss": 0.3481634855270386, | |
| "eval_runtime": 22.5124, | |
| "eval_samples_per_second": 59.789, | |
| "eval_steps_per_second": 7.507, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9814264487369985, | |
| "eval_loss": 0.3135211169719696, | |
| "eval_runtime": 22.4742, | |
| "eval_samples_per_second": 59.891, | |
| "eval_steps_per_second": 7.52, | |
| "step": 1859 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 6.115537848605578e-06, | |
| "loss": 0.266, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9821693907875185, | |
| "eval_loss": 0.28906822204589844, | |
| "eval_runtime": 22.7533, | |
| "eval_samples_per_second": 59.156, | |
| "eval_steps_per_second": 7.427, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9829123328380386, | |
| "eval_loss": 0.268048495054245, | |
| "eval_runtime": 22.694, | |
| "eval_samples_per_second": 59.311, | |
| "eval_steps_per_second": 7.447, | |
| "step": 2197 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9829123328380386, | |
| "eval_loss": 0.24836774170398712, | |
| "eval_runtime": 22.5694, | |
| "eval_samples_per_second": 59.638, | |
| "eval_steps_per_second": 7.488, | |
| "step": 2366 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 5.119521912350598e-06, | |
| "loss": 0.1903, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9829123328380386, | |
| "eval_loss": 0.23243731260299683, | |
| "eval_runtime": 22.7926, | |
| "eval_samples_per_second": 59.054, | |
| "eval_steps_per_second": 7.415, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9806835066864784, | |
| "eval_loss": 0.22185435891151428, | |
| "eval_runtime": 22.6881, | |
| "eval_samples_per_second": 59.326, | |
| "eval_steps_per_second": 7.449, | |
| "step": 2704 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9814264487369985, | |
| "eval_loss": 0.20966528356075287, | |
| "eval_runtime": 22.358, | |
| "eval_samples_per_second": 60.202, | |
| "eval_steps_per_second": 7.559, | |
| "step": 2873 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 4.123505976095618e-06, | |
| "loss": 0.1472, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9814264487369985, | |
| "eval_loss": 0.20012235641479492, | |
| "eval_runtime": 22.9511, | |
| "eval_samples_per_second": 58.646, | |
| "eval_steps_per_second": 7.363, | |
| "step": 3042 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9821693907875185, | |
| "eval_loss": 0.19222623109817505, | |
| "eval_runtime": 25.4756, | |
| "eval_samples_per_second": 52.835, | |
| "eval_steps_per_second": 6.634, | |
| "step": 3211 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9829123328380386, | |
| "eval_loss": 0.1853048950433731, | |
| "eval_runtime": 23.0714, | |
| "eval_samples_per_second": 58.341, | |
| "eval_steps_per_second": 7.325, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 3.1274900398406375e-06, | |
| "loss": 0.1212, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9814264487369985, | |
| "eval_loss": 0.18127979338169098, | |
| "eval_runtime": 22.5621, | |
| "eval_samples_per_second": 59.658, | |
| "eval_steps_per_second": 7.49, | |
| "step": 3549 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9814264487369985, | |
| "eval_loss": 0.1769726574420929, | |
| "eval_runtime": 22.898, | |
| "eval_samples_per_second": 58.782, | |
| "eval_steps_per_second": 7.381, | |
| "step": 3718 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9806835066864784, | |
| "eval_loss": 0.17226694524288177, | |
| "eval_runtime": 22.9554, | |
| "eval_samples_per_second": 58.635, | |
| "eval_steps_per_second": 7.362, | |
| "step": 3887 | |
| }, | |
| { | |
| "epoch": 23.67, | |
| "learning_rate": 2.1314741035856577e-06, | |
| "loss": 0.1041, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9821693907875185, | |
| "eval_loss": 0.16755062341690063, | |
| "eval_runtime": 22.569, | |
| "eval_samples_per_second": 59.639, | |
| "eval_steps_per_second": 7.488, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9821693907875185, | |
| "eval_loss": 0.16521112620830536, | |
| "eval_runtime": 23.0831, | |
| "eval_samples_per_second": 58.311, | |
| "eval_steps_per_second": 7.321, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9806835066864784, | |
| "eval_loss": 0.1628224402666092, | |
| "eval_runtime": 23.1794, | |
| "eval_samples_per_second": 58.069, | |
| "eval_steps_per_second": 7.291, | |
| "step": 4394 | |
| }, | |
| { | |
| "epoch": 26.63, | |
| "learning_rate": 1.1354581673306774e-06, | |
| "loss": 0.0941, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9806835066864784, | |
| "eval_loss": 0.1619950830936432, | |
| "eval_runtime": 22.8344, | |
| "eval_samples_per_second": 58.946, | |
| "eval_steps_per_second": 7.401, | |
| "step": 4563 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9821693907875185, | |
| "eval_loss": 0.1596996784210205, | |
| "eval_runtime": 23.0761, | |
| "eval_samples_per_second": 58.329, | |
| "eval_steps_per_second": 7.324, | |
| "step": 4732 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9829123328380386, | |
| "eval_loss": 0.15874390304088593, | |
| "eval_runtime": 22.9713, | |
| "eval_samples_per_second": 58.595, | |
| "eval_steps_per_second": 7.357, | |
| "step": 4901 | |
| }, | |
| { | |
| "epoch": 29.59, | |
| "learning_rate": 1.3944223107569722e-07, | |
| "loss": 0.089, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9829123328380386, | |
| "eval_loss": 0.15817709267139435, | |
| "eval_runtime": 22.2, | |
| "eval_samples_per_second": 60.631, | |
| "eval_steps_per_second": 7.613, | |
| "step": 5070 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5070, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.2509561184764314e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |