--- tags: - generated_from_keras_callback model-index: - name: pretrained-m-bert-1 results: [] --- # pretrained-m-bert-1 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 3.3662 - Validation Loss: 14.3784 - Epoch: 99 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 10.2573 | 10.9396 | 0 | | 7.8912 | 10.9597 | 1 | | 6.8354 | 11.2198 | 2 | | 6.3659 | 11.5487 | 3 | | 6.0787 | 11.1321 | 4 | | 5.8528 | 11.1589 | 5 | | 5.7689 | 11.3702 | 6 | | 5.3858 | 11.8196 | 7 | | 5.1194 | 12.0623 | 8 | | 5.2013 | 11.8812 | 9 | | 5.0820 | 11.7143 | 10 | | 4.9735 | 12.6034 | 11 | | 5.0704 | 11.9522 | 12 | | 5.0098 | 12.1079 | 13 | | 5.0869 | 12.2301 | 14 | | 4.8156 | 12.2691 | 15 | | 4.8344 | 12.6859 | 16 | | 4.8416 | 12.5824 | 17 | | 4.5567 | 13.1279 | 18 | | 4.6677 | 12.5301 | 19 | | 4.7248 | 12.5819 | 20 | | 4.5435 | 12.5466 | 21 | | 4.6501 | 12.4965 | 22 | | 4.7348 | 12.7858 | 23 | | 4.4649 | 12.5727 | 24 | | 4.3665 | 12.2411 | 25 | | 4.6434 | 12.6519 | 26 | | 4.4239 | 13.6048 | 27 | | 4.3893 | 13.3377 | 28 | | 4.6514 | 12.3628 | 29 | | 4.4743 | 12.6613 | 30 | | 4.2777 | 12.3419 | 31 | | 4.5667 | 13.5223 | 32 | | 4.0886 | 13.2224 | 33 | | 4.3032 | 13.2787 | 34 | | 4.3670 | 13.1041 | 35 | | 4.1487 | 12.6903 | 36 | | 4.3331 | 13.4880 | 37 | | 4.2907 | 13.2240 | 38 | | 4.3252 | 12.6439 | 39 | | 4.1121 | 13.5487 | 40 | | 4.3273 | 14.4200 | 41 | | 4.2030 | 14.4691 | 42 | | 4.1795 | 13.1436 | 43 | | 4.0424 | 14.0504 | 44 | | 4.0158 | 12.5468 | 45 | | 4.0108 | 13.6426 | 46 | | 3.9515 | 13.4965 | 47 | | 3.9743 | 13.2319 | 48 | | 4.1075 | 13.2999 | 49 | | 4.0501 | 12.7201 | 50 | | 3.8606 | 13.1704 | 51 | | 3.8056 | 13.7504 | 52 | | 3.7682 | 13.5004 | 53 | | 4.0676 | 13.6444 | 54 | | 4.0957 | 13.4160 | 55 | | 4.9373 | 14.2742 | 56 | | 4.5111 | 13.9469 | 57 | | 4.1604 | 13.4773 | 58 | | 3.9956 | 12.9802 | 59 | | 4.1232 | 14.1715 | 60 | | 3.9857 | 12.2465 | 61 | | 4.1082 | 13.8947 | 62 | | 3.8659 | 13.6370 | 63 | | 3.8396 | 13.5898 | 64 | | 3.8220 | 13.2523 | 65 | | 3.6864 | 13.9323 | 66 | | 3.7541 | 13.6081 | 67 | | 3.8218 | 12.9945 | 68 | | 3.7251 | 13.7039 | 69 | | 3.5017 | 12.9811 | 70 | | 3.5342 | 12.5702 | 71 | | 3.9520 | 12.4899 | 72 | | 3.7465 | 13.2309 | 73 | | 3.6003 | 14.0988 | 74 | | 3.7954 | 13.0785 | 75 | | 3.5654 | 13.7277 | 76 | | 3.5591 | 13.7914 | 77 | | 3.5355 | 13.6749 | 78 | | 3.5903 | 13.6141 | 79 | | 3.5371 | 13.4166 | 80 | | 3.4502 | 12.6523 | 81 | | 3.3372 | 13.8609 | 82 | | 3.3071 | 14.3441 | 83 | | 3.6932 | 13.9718 | 84 | | 3.5619 | 13.3749 | 85 | | 3.5016 | 13.1467 | 86 | | 3.4279 | 14.0124 | 87 | | 3.3140 | 13.6681 | 88 | | 3.3575 | 12.9451 | 89 | | 3.2268 | 12.4299 | 90 | | 3.2001 | 14.5106 | 91 | | 3.1390 | 13.9366 | 92 | | 3.1230 | 13.6865 | 93 | | 3.2337 | 13.5835 | 94 | | 3.1397 | 13.8130 | 95 | | 3.2095 | 13.8431 | 96 | | 2.9553 | 14.5159 | 97 | | 3.3319 | 12.9168 | 98 | | 3.3662 | 14.3784 | 99 | ### Framework versions - Transformers 4.27.0.dev0 - TensorFlow 2.9.2 - Datasets 2.9.0 - Tokenizers 0.13.2