Training in progress, step 500
Browse files- README.md +316 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_task5_organization
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_task5_organization
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.5623
|
| 19 |
+
- Qwk: 0.6455
|
| 20 |
+
- Mse: 0.5623
|
| 21 |
+
- Rmse: 0.7499
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 100
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:------:|
|
| 52 |
+
| No log | 0.0211 | 2 | 3.9455 | -0.0257 | 3.9455 | 1.9863 |
|
| 53 |
+
| No log | 0.0421 | 4 | 2.1378 | 0.0628 | 2.1378 | 1.4621 |
|
| 54 |
+
| No log | 0.0632 | 6 | 1.4185 | 0.0 | 1.4185 | 1.1910 |
|
| 55 |
+
| No log | 0.0842 | 8 | 1.1640 | 0.1738 | 1.1640 | 1.0789 |
|
| 56 |
+
| No log | 0.1053 | 10 | 1.1887 | 0.0520 | 1.1887 | 1.0903 |
|
| 57 |
+
| No log | 0.1263 | 12 | 1.1105 | 0.1398 | 1.1105 | 1.0538 |
|
| 58 |
+
| No log | 0.1474 | 14 | 0.9870 | 0.2541 | 0.9870 | 0.9935 |
|
| 59 |
+
| No log | 0.1684 | 16 | 0.9019 | 0.3432 | 0.9019 | 0.9497 |
|
| 60 |
+
| No log | 0.1895 | 18 | 0.8888 | 0.3688 | 0.8888 | 0.9428 |
|
| 61 |
+
| No log | 0.2105 | 20 | 0.9008 | 0.3332 | 0.9008 | 0.9491 |
|
| 62 |
+
| No log | 0.2316 | 22 | 0.8553 | 0.4547 | 0.8553 | 0.9248 |
|
| 63 |
+
| No log | 0.2526 | 24 | 0.7936 | 0.3604 | 0.7936 | 0.8909 |
|
| 64 |
+
| No log | 0.2737 | 26 | 0.7916 | 0.3529 | 0.7916 | 0.8897 |
|
| 65 |
+
| No log | 0.2947 | 28 | 0.7595 | 0.5419 | 0.7595 | 0.8715 |
|
| 66 |
+
| No log | 0.3158 | 30 | 0.7590 | 0.5399 | 0.7590 | 0.8712 |
|
| 67 |
+
| No log | 0.3368 | 32 | 0.7530 | 0.5060 | 0.7530 | 0.8678 |
|
| 68 |
+
| No log | 0.3579 | 34 | 0.7966 | 0.5467 | 0.7966 | 0.8925 |
|
| 69 |
+
| No log | 0.3789 | 36 | 1.0234 | 0.4705 | 1.0234 | 1.0116 |
|
| 70 |
+
| No log | 0.4 | 38 | 1.0615 | 0.4917 | 1.0615 | 1.0303 |
|
| 71 |
+
| No log | 0.4211 | 40 | 0.7440 | 0.6203 | 0.7440 | 0.8626 |
|
| 72 |
+
| No log | 0.4421 | 42 | 0.6880 | 0.6714 | 0.6880 | 0.8295 |
|
| 73 |
+
| No log | 0.4632 | 44 | 0.6583 | 0.6473 | 0.6583 | 0.8113 |
|
| 74 |
+
| No log | 0.4842 | 46 | 0.8834 | 0.5996 | 0.8834 | 0.9399 |
|
| 75 |
+
| No log | 0.5053 | 48 | 1.1907 | 0.4699 | 1.1907 | 1.0912 |
|
| 76 |
+
| No log | 0.5263 | 50 | 0.9862 | 0.5455 | 0.9862 | 0.9931 |
|
| 77 |
+
| No log | 0.5474 | 52 | 0.6400 | 0.6015 | 0.6400 | 0.8000 |
|
| 78 |
+
| No log | 0.5684 | 54 | 0.6104 | 0.5977 | 0.6104 | 0.7813 |
|
| 79 |
+
| No log | 0.5895 | 56 | 0.6289 | 0.6410 | 0.6289 | 0.7930 |
|
| 80 |
+
| No log | 0.6105 | 58 | 0.6570 | 0.6586 | 0.6570 | 0.8105 |
|
| 81 |
+
| No log | 0.6316 | 60 | 0.6538 | 0.6225 | 0.6538 | 0.8086 |
|
| 82 |
+
| No log | 0.6526 | 62 | 0.6393 | 0.6005 | 0.6393 | 0.7996 |
|
| 83 |
+
| No log | 0.6737 | 64 | 0.6340 | 0.5902 | 0.6340 | 0.7962 |
|
| 84 |
+
| No log | 0.6947 | 66 | 0.6228 | 0.5828 | 0.6228 | 0.7892 |
|
| 85 |
+
| No log | 0.7158 | 68 | 0.6892 | 0.6559 | 0.6892 | 0.8302 |
|
| 86 |
+
| No log | 0.7368 | 70 | 0.7561 | 0.6838 | 0.7561 | 0.8695 |
|
| 87 |
+
| No log | 0.7579 | 72 | 0.6538 | 0.5884 | 0.6538 | 0.8086 |
|
| 88 |
+
| No log | 0.7789 | 74 | 0.6807 | 0.5477 | 0.6807 | 0.8251 |
|
| 89 |
+
| No log | 0.8 | 76 | 0.8085 | 0.5643 | 0.8085 | 0.8992 |
|
| 90 |
+
| No log | 0.8211 | 78 | 0.6686 | 0.5944 | 0.6686 | 0.8177 |
|
| 91 |
+
| No log | 0.8421 | 80 | 0.5923 | 0.6491 | 0.5923 | 0.7696 |
|
| 92 |
+
| No log | 0.8632 | 82 | 0.6195 | 0.6176 | 0.6195 | 0.7871 |
|
| 93 |
+
| No log | 0.8842 | 84 | 0.5842 | 0.6983 | 0.5842 | 0.7643 |
|
| 94 |
+
| No log | 0.9053 | 86 | 0.5840 | 0.7027 | 0.5840 | 0.7642 |
|
| 95 |
+
| No log | 0.9263 | 88 | 0.5883 | 0.6927 | 0.5883 | 0.7670 |
|
| 96 |
+
| No log | 0.9474 | 90 | 0.5764 | 0.6775 | 0.5764 | 0.7592 |
|
| 97 |
+
| No log | 0.9684 | 92 | 0.5649 | 0.6751 | 0.5649 | 0.7516 |
|
| 98 |
+
| No log | 0.9895 | 94 | 0.5649 | 0.6377 | 0.5649 | 0.7516 |
|
| 99 |
+
| No log | 1.0105 | 96 | 0.6798 | 0.6887 | 0.6798 | 0.8245 |
|
| 100 |
+
| No log | 1.0316 | 98 | 0.6996 | 0.6697 | 0.6996 | 0.8364 |
|
| 101 |
+
| No log | 1.0526 | 100 | 0.6053 | 0.7348 | 0.6053 | 0.7780 |
|
| 102 |
+
| No log | 1.0737 | 102 | 0.6351 | 0.6932 | 0.6351 | 0.7969 |
|
| 103 |
+
| No log | 1.0947 | 104 | 0.6131 | 0.6314 | 0.6131 | 0.7830 |
|
| 104 |
+
| No log | 1.1158 | 106 | 0.6060 | 0.6370 | 0.6060 | 0.7785 |
|
| 105 |
+
| No log | 1.1368 | 108 | 0.6164 | 0.6593 | 0.6164 | 0.7851 |
|
| 106 |
+
| No log | 1.1579 | 110 | 0.6589 | 0.6550 | 0.6589 | 0.8117 |
|
| 107 |
+
| No log | 1.1789 | 112 | 0.6931 | 0.6774 | 0.6931 | 0.8325 |
|
| 108 |
+
| No log | 1.2 | 114 | 0.6570 | 0.6205 | 0.6570 | 0.8105 |
|
| 109 |
+
| No log | 1.2211 | 116 | 0.6556 | 0.6562 | 0.6556 | 0.8097 |
|
| 110 |
+
| No log | 1.2421 | 118 | 0.6513 | 0.6164 | 0.6513 | 0.8070 |
|
| 111 |
+
| No log | 1.2632 | 120 | 0.7564 | 0.5061 | 0.7564 | 0.8697 |
|
| 112 |
+
| No log | 1.2842 | 122 | 0.7879 | 0.5175 | 0.7879 | 0.8877 |
|
| 113 |
+
| No log | 1.3053 | 124 | 0.5890 | 0.6990 | 0.5890 | 0.7675 |
|
| 114 |
+
| No log | 1.3263 | 126 | 0.7976 | 0.6094 | 0.7976 | 0.8931 |
|
| 115 |
+
| No log | 1.3474 | 128 | 0.8679 | 0.5984 | 0.8679 | 0.9316 |
|
| 116 |
+
| No log | 1.3684 | 130 | 0.6639 | 0.6713 | 0.6639 | 0.8148 |
|
| 117 |
+
| No log | 1.3895 | 132 | 0.5800 | 0.6552 | 0.5800 | 0.7616 |
|
| 118 |
+
| No log | 1.4105 | 134 | 0.5750 | 0.6310 | 0.5750 | 0.7583 |
|
| 119 |
+
| No log | 1.4316 | 136 | 0.6188 | 0.6459 | 0.6188 | 0.7866 |
|
| 120 |
+
| No log | 1.4526 | 138 | 0.6616 | 0.6396 | 0.6616 | 0.8134 |
|
| 121 |
+
| No log | 1.4737 | 140 | 0.6312 | 0.6692 | 0.6312 | 0.7945 |
|
| 122 |
+
| No log | 1.4947 | 142 | 0.6053 | 0.6751 | 0.6053 | 0.7780 |
|
| 123 |
+
| No log | 1.5158 | 144 | 0.6325 | 0.6930 | 0.6325 | 0.7953 |
|
| 124 |
+
| No log | 1.5368 | 146 | 0.5984 | 0.6594 | 0.5984 | 0.7736 |
|
| 125 |
+
| No log | 1.5579 | 148 | 0.6138 | 0.6293 | 0.6138 | 0.7835 |
|
| 126 |
+
| No log | 1.5789 | 150 | 0.6684 | 0.6620 | 0.6684 | 0.8175 |
|
| 127 |
+
| No log | 1.6 | 152 | 0.6163 | 0.6570 | 0.6163 | 0.7851 |
|
| 128 |
+
| No log | 1.6211 | 154 | 0.5949 | 0.6846 | 0.5949 | 0.7713 |
|
| 129 |
+
| No log | 1.6421 | 156 | 0.5803 | 0.6932 | 0.5803 | 0.7618 |
|
| 130 |
+
| No log | 1.6632 | 158 | 0.5973 | 0.6675 | 0.5973 | 0.7728 |
|
| 131 |
+
| No log | 1.6842 | 160 | 0.6769 | 0.6132 | 0.6769 | 0.8227 |
|
| 132 |
+
| No log | 1.7053 | 162 | 0.6419 | 0.6626 | 0.6419 | 0.8012 |
|
| 133 |
+
| No log | 1.7263 | 164 | 0.5783 | 0.7193 | 0.5783 | 0.7605 |
|
| 134 |
+
| No log | 1.7474 | 166 | 0.6700 | 0.6922 | 0.6700 | 0.8185 |
|
| 135 |
+
| No log | 1.7684 | 168 | 0.6775 | 0.6487 | 0.6775 | 0.8231 |
|
| 136 |
+
| No log | 1.7895 | 170 | 0.5522 | 0.6680 | 0.5522 | 0.7431 |
|
| 137 |
+
| No log | 1.8105 | 172 | 0.5820 | 0.6278 | 0.5820 | 0.7629 |
|
| 138 |
+
| No log | 1.8316 | 174 | 0.6181 | 0.6461 | 0.6181 | 0.7862 |
|
| 139 |
+
| No log | 1.8526 | 176 | 0.5881 | 0.6644 | 0.5881 | 0.7669 |
|
| 140 |
+
| No log | 1.8737 | 178 | 0.6206 | 0.6589 | 0.6206 | 0.7878 |
|
| 141 |
+
| No log | 1.8947 | 180 | 0.6887 | 0.6520 | 0.6887 | 0.8299 |
|
| 142 |
+
| No log | 1.9158 | 182 | 0.6456 | 0.7226 | 0.6456 | 0.8035 |
|
| 143 |
+
| No log | 1.9368 | 184 | 0.6433 | 0.6220 | 0.6433 | 0.8020 |
|
| 144 |
+
| No log | 1.9579 | 186 | 0.6541 | 0.7174 | 0.6541 | 0.8088 |
|
| 145 |
+
| No log | 1.9789 | 188 | 0.6748 | 0.6628 | 0.6748 | 0.8215 |
|
| 146 |
+
| No log | 2.0 | 190 | 0.6454 | 0.6868 | 0.6454 | 0.8033 |
|
| 147 |
+
| No log | 2.0211 | 192 | 0.6695 | 0.6231 | 0.6695 | 0.8183 |
|
| 148 |
+
| No log | 2.0421 | 194 | 0.6996 | 0.6461 | 0.6996 | 0.8364 |
|
| 149 |
+
| No log | 2.0632 | 196 | 0.7140 | 0.6348 | 0.7140 | 0.8450 |
|
| 150 |
+
| No log | 2.0842 | 198 | 0.8265 | 0.5304 | 0.8265 | 0.9091 |
|
| 151 |
+
| No log | 2.1053 | 200 | 0.8465 | 0.4829 | 0.8465 | 0.9201 |
|
| 152 |
+
| No log | 2.1263 | 202 | 0.7478 | 0.5708 | 0.7478 | 0.8647 |
|
| 153 |
+
| No log | 2.1474 | 204 | 0.6311 | 0.7012 | 0.6311 | 0.7944 |
|
| 154 |
+
| No log | 2.1684 | 206 | 0.6371 | 0.6869 | 0.6371 | 0.7982 |
|
| 155 |
+
| No log | 2.1895 | 208 | 0.6172 | 0.7012 | 0.6172 | 0.7856 |
|
| 156 |
+
| No log | 2.2105 | 210 | 0.6939 | 0.6289 | 0.6939 | 0.8330 |
|
| 157 |
+
| No log | 2.2316 | 212 | 0.7061 | 0.6615 | 0.7061 | 0.8403 |
|
| 158 |
+
| No log | 2.2526 | 214 | 0.6537 | 0.6728 | 0.6537 | 0.8085 |
|
| 159 |
+
| No log | 2.2737 | 216 | 0.6448 | 0.6430 | 0.6448 | 0.8030 |
|
| 160 |
+
| No log | 2.2947 | 218 | 0.6879 | 0.6476 | 0.6879 | 0.8294 |
|
| 161 |
+
| No log | 2.3158 | 220 | 0.6718 | 0.6305 | 0.6718 | 0.8196 |
|
| 162 |
+
| No log | 2.3368 | 222 | 0.6308 | 0.6123 | 0.6308 | 0.7942 |
|
| 163 |
+
| No log | 2.3579 | 224 | 0.6382 | 0.6770 | 0.6382 | 0.7989 |
|
| 164 |
+
| No log | 2.3789 | 226 | 0.6449 | 0.7064 | 0.6449 | 0.8031 |
|
| 165 |
+
| No log | 2.4 | 228 | 0.6717 | 0.6758 | 0.6717 | 0.8196 |
|
| 166 |
+
| No log | 2.4211 | 230 | 0.6875 | 0.7077 | 0.6875 | 0.8292 |
|
| 167 |
+
| No log | 2.4421 | 232 | 0.6536 | 0.6857 | 0.6536 | 0.8085 |
|
| 168 |
+
| No log | 2.4632 | 234 | 0.6187 | 0.6902 | 0.6187 | 0.7866 |
|
| 169 |
+
| No log | 2.4842 | 236 | 0.6066 | 0.6983 | 0.6066 | 0.7789 |
|
| 170 |
+
| No log | 2.5053 | 238 | 0.5857 | 0.7126 | 0.5857 | 0.7653 |
|
| 171 |
+
| No log | 2.5263 | 240 | 0.6272 | 0.7009 | 0.6272 | 0.7919 |
|
| 172 |
+
| No log | 2.5474 | 242 | 0.6439 | 0.6888 | 0.6439 | 0.8024 |
|
| 173 |
+
| No log | 2.5684 | 244 | 0.5953 | 0.7687 | 0.5953 | 0.7715 |
|
| 174 |
+
| No log | 2.5895 | 246 | 0.5694 | 0.7284 | 0.5694 | 0.7546 |
|
| 175 |
+
| No log | 2.6105 | 248 | 0.5786 | 0.7175 | 0.5786 | 0.7606 |
|
| 176 |
+
| No log | 2.6316 | 250 | 0.5666 | 0.6770 | 0.5666 | 0.7527 |
|
| 177 |
+
| No log | 2.6526 | 252 | 0.6055 | 0.6187 | 0.6055 | 0.7781 |
|
| 178 |
+
| No log | 2.6737 | 254 | 0.6692 | 0.5833 | 0.6692 | 0.8180 |
|
| 179 |
+
| No log | 2.6947 | 256 | 0.6912 | 0.5677 | 0.6912 | 0.8314 |
|
| 180 |
+
| No log | 2.7158 | 258 | 0.6354 | 0.6337 | 0.6354 | 0.7971 |
|
| 181 |
+
| No log | 2.7368 | 260 | 0.6018 | 0.7216 | 0.6018 | 0.7757 |
|
| 182 |
+
| No log | 2.7579 | 262 | 0.7222 | 0.5739 | 0.7222 | 0.8498 |
|
| 183 |
+
| No log | 2.7789 | 264 | 0.7305 | 0.5739 | 0.7305 | 0.8547 |
|
| 184 |
+
| No log | 2.8 | 266 | 0.6039 | 0.7223 | 0.6039 | 0.7771 |
|
| 185 |
+
| No log | 2.8211 | 268 | 0.6219 | 0.6821 | 0.6219 | 0.7886 |
|
| 186 |
+
| No log | 2.8421 | 270 | 0.8043 | 0.5194 | 0.8043 | 0.8968 |
|
| 187 |
+
| No log | 2.8632 | 272 | 0.8270 | 0.5185 | 0.8270 | 0.9094 |
|
| 188 |
+
| No log | 2.8842 | 274 | 0.6777 | 0.6189 | 0.6777 | 0.8232 |
|
| 189 |
+
| No log | 2.9053 | 276 | 0.5854 | 0.6537 | 0.5854 | 0.7651 |
|
| 190 |
+
| No log | 2.9263 | 278 | 0.5758 | 0.6575 | 0.5758 | 0.7588 |
|
| 191 |
+
| No log | 2.9474 | 280 | 0.5765 | 0.6575 | 0.5765 | 0.7592 |
|
| 192 |
+
| No log | 2.9684 | 282 | 0.5887 | 0.6500 | 0.5887 | 0.7673 |
|
| 193 |
+
| No log | 2.9895 | 284 | 0.7231 | 0.6269 | 0.7231 | 0.8504 |
|
| 194 |
+
| No log | 3.0105 | 286 | 0.8698 | 0.6312 | 0.8698 | 0.9326 |
|
| 195 |
+
| No log | 3.0316 | 288 | 0.8543 | 0.6009 | 0.8543 | 0.9243 |
|
| 196 |
+
| No log | 3.0526 | 290 | 0.7911 | 0.6406 | 0.7911 | 0.8895 |
|
| 197 |
+
| No log | 3.0737 | 292 | 0.7258 | 0.6869 | 0.7258 | 0.8519 |
|
| 198 |
+
| No log | 3.0947 | 294 | 0.6683 | 0.6358 | 0.6683 | 0.8175 |
|
| 199 |
+
| No log | 3.1158 | 296 | 0.6232 | 0.6697 | 0.6232 | 0.7894 |
|
| 200 |
+
| No log | 3.1368 | 298 | 0.6581 | 0.6122 | 0.6581 | 0.8112 |
|
| 201 |
+
| No log | 3.1579 | 300 | 0.6970 | 0.5846 | 0.6970 | 0.8349 |
|
| 202 |
+
| No log | 3.1789 | 302 | 0.7206 | 0.5777 | 0.7206 | 0.8489 |
|
| 203 |
+
| No log | 3.2 | 304 | 0.6766 | 0.5983 | 0.6766 | 0.8226 |
|
| 204 |
+
| No log | 3.2211 | 306 | 0.6035 | 0.6219 | 0.6035 | 0.7768 |
|
| 205 |
+
| No log | 3.2421 | 308 | 0.5986 | 0.6555 | 0.5986 | 0.7737 |
|
| 206 |
+
| No log | 3.2632 | 310 | 0.5862 | 0.6470 | 0.5862 | 0.7657 |
|
| 207 |
+
| No log | 3.2842 | 312 | 0.6050 | 0.6510 | 0.6050 | 0.7778 |
|
| 208 |
+
| No log | 3.3053 | 314 | 0.7172 | 0.5222 | 0.7172 | 0.8469 |
|
| 209 |
+
| No log | 3.3263 | 316 | 0.7092 | 0.5636 | 0.7092 | 0.8421 |
|
| 210 |
+
| No log | 3.3474 | 318 | 0.6190 | 0.6188 | 0.6190 | 0.7868 |
|
| 211 |
+
| No log | 3.3684 | 320 | 0.5842 | 0.6699 | 0.5842 | 0.7643 |
|
| 212 |
+
| No log | 3.3895 | 322 | 0.5932 | 0.6854 | 0.5932 | 0.7702 |
|
| 213 |
+
| No log | 3.4105 | 324 | 0.5838 | 0.6978 | 0.5838 | 0.7641 |
|
| 214 |
+
| No log | 3.4316 | 326 | 0.6177 | 0.6528 | 0.6177 | 0.7859 |
|
| 215 |
+
| No log | 3.4526 | 328 | 0.6374 | 0.6821 | 0.6374 | 0.7984 |
|
| 216 |
+
| No log | 3.4737 | 330 | 0.6392 | 0.6914 | 0.6392 | 0.7995 |
|
| 217 |
+
| No log | 3.4947 | 332 | 0.6377 | 0.6914 | 0.6377 | 0.7986 |
|
| 218 |
+
| No log | 3.5158 | 334 | 0.6317 | 0.6228 | 0.6317 | 0.7948 |
|
| 219 |
+
| No log | 3.5368 | 336 | 0.6021 | 0.5905 | 0.6021 | 0.7760 |
|
| 220 |
+
| No log | 3.5579 | 338 | 0.5945 | 0.6518 | 0.5945 | 0.7710 |
|
| 221 |
+
| No log | 3.5789 | 340 | 0.5976 | 0.6219 | 0.5976 | 0.7730 |
|
| 222 |
+
| No log | 3.6 | 342 | 0.6155 | 0.5993 | 0.6155 | 0.7846 |
|
| 223 |
+
| No log | 3.6211 | 344 | 0.5973 | 0.7124 | 0.5973 | 0.7728 |
|
| 224 |
+
| No log | 3.6421 | 346 | 0.6166 | 0.6875 | 0.6166 | 0.7852 |
|
| 225 |
+
| No log | 3.6632 | 348 | 0.7269 | 0.6090 | 0.7269 | 0.8526 |
|
| 226 |
+
| No log | 3.6842 | 350 | 0.7832 | 0.5961 | 0.7832 | 0.8850 |
|
| 227 |
+
| No log | 3.7053 | 352 | 0.7071 | 0.6035 | 0.7071 | 0.8409 |
|
| 228 |
+
| No log | 3.7263 | 354 | 0.6252 | 0.6916 | 0.6252 | 0.7907 |
|
| 229 |
+
| No log | 3.7474 | 356 | 0.6650 | 0.6626 | 0.6650 | 0.8155 |
|
| 230 |
+
| No log | 3.7684 | 358 | 0.7168 | 0.6201 | 0.7168 | 0.8466 |
|
| 231 |
+
| No log | 3.7895 | 360 | 0.6952 | 0.6549 | 0.6952 | 0.8338 |
|
| 232 |
+
| No log | 3.8105 | 362 | 0.6241 | 0.6938 | 0.6241 | 0.7900 |
|
| 233 |
+
| No log | 3.8316 | 364 | 0.6292 | 0.6528 | 0.6292 | 0.7932 |
|
| 234 |
+
| No log | 3.8526 | 366 | 0.6738 | 0.5819 | 0.6738 | 0.8208 |
|
| 235 |
+
| No log | 3.8737 | 368 | 0.6383 | 0.6337 | 0.6383 | 0.7989 |
|
| 236 |
+
| No log | 3.8947 | 370 | 0.5866 | 0.6370 | 0.5866 | 0.7659 |
|
| 237 |
+
| No log | 3.9158 | 372 | 0.5925 | 0.6307 | 0.5925 | 0.7697 |
|
| 238 |
+
| No log | 3.9368 | 374 | 0.5968 | 0.6846 | 0.5968 | 0.7725 |
|
| 239 |
+
| No log | 3.9579 | 376 | 0.5948 | 0.6781 | 0.5948 | 0.7712 |
|
| 240 |
+
| No log | 3.9789 | 378 | 0.6029 | 0.7077 | 0.6029 | 0.7765 |
|
| 241 |
+
| No log | 4.0 | 380 | 0.6153 | 0.6615 | 0.6153 | 0.7844 |
|
| 242 |
+
| No log | 4.0211 | 382 | 0.5990 | 0.7218 | 0.5990 | 0.7740 |
|
| 243 |
+
| No log | 4.0421 | 384 | 0.5920 | 0.7278 | 0.5920 | 0.7694 |
|
| 244 |
+
| No log | 4.0632 | 386 | 0.5866 | 0.7423 | 0.5866 | 0.7659 |
|
| 245 |
+
| No log | 4.0842 | 388 | 0.5948 | 0.6838 | 0.5948 | 0.7712 |
|
| 246 |
+
| No log | 4.1053 | 390 | 0.6231 | 0.6555 | 0.6231 | 0.7893 |
|
| 247 |
+
| No log | 4.1263 | 392 | 0.6310 | 0.6157 | 0.6310 | 0.7944 |
|
| 248 |
+
| No log | 4.1474 | 394 | 0.6066 | 0.6335 | 0.6066 | 0.7788 |
|
| 249 |
+
| No log | 4.1684 | 396 | 0.5663 | 0.6720 | 0.5663 | 0.7526 |
|
| 250 |
+
| No log | 4.1895 | 398 | 0.5868 | 0.7286 | 0.5868 | 0.7660 |
|
| 251 |
+
| No log | 4.2105 | 400 | 0.6701 | 0.6109 | 0.6701 | 0.8186 |
|
| 252 |
+
| No log | 4.2316 | 402 | 0.6446 | 0.6765 | 0.6446 | 0.8029 |
|
| 253 |
+
| No log | 4.2526 | 404 | 0.5849 | 0.6972 | 0.5849 | 0.7648 |
|
| 254 |
+
| No log | 4.2737 | 406 | 0.6144 | 0.7506 | 0.6144 | 0.7838 |
|
| 255 |
+
| No log | 4.2947 | 408 | 0.6270 | 0.7177 | 0.6270 | 0.7918 |
|
| 256 |
+
| No log | 4.3158 | 410 | 0.5770 | 0.7219 | 0.5770 | 0.7596 |
|
| 257 |
+
| No log | 4.3368 | 412 | 0.5659 | 0.7103 | 0.5659 | 0.7523 |
|
| 258 |
+
| No log | 4.3579 | 414 | 0.6125 | 0.6758 | 0.6125 | 0.7826 |
|
| 259 |
+
| No log | 4.3789 | 416 | 0.6086 | 0.6826 | 0.6086 | 0.7801 |
|
| 260 |
+
| No log | 4.4 | 418 | 0.5717 | 0.7085 | 0.5717 | 0.7561 |
|
| 261 |
+
| No log | 4.4211 | 420 | 0.5855 | 0.6853 | 0.5855 | 0.7652 |
|
| 262 |
+
| No log | 4.4421 | 422 | 0.6547 | 0.6142 | 0.6547 | 0.8091 |
|
| 263 |
+
| No log | 4.4632 | 424 | 0.6593 | 0.6047 | 0.6593 | 0.8120 |
|
| 264 |
+
| No log | 4.4842 | 426 | 0.6367 | 0.6179 | 0.6367 | 0.7979 |
|
| 265 |
+
| No log | 4.5053 | 428 | 0.5852 | 0.6455 | 0.5852 | 0.7650 |
|
| 266 |
+
| No log | 4.5263 | 430 | 0.5500 | 0.6830 | 0.5500 | 0.7416 |
|
| 267 |
+
| No log | 4.5474 | 432 | 0.5428 | 0.7216 | 0.5428 | 0.7367 |
|
| 268 |
+
| No log | 4.5684 | 434 | 0.5378 | 0.7077 | 0.5378 | 0.7333 |
|
| 269 |
+
| No log | 4.5895 | 436 | 0.5377 | 0.7122 | 0.5377 | 0.7333 |
|
| 270 |
+
| No log | 4.6105 | 438 | 0.5444 | 0.7122 | 0.5444 | 0.7378 |
|
| 271 |
+
| No log | 4.6316 | 440 | 0.5514 | 0.7056 | 0.5514 | 0.7426 |
|
| 272 |
+
| No log | 4.6526 | 442 | 0.5634 | 0.6307 | 0.5634 | 0.7506 |
|
| 273 |
+
| No log | 4.6737 | 444 | 0.5816 | 0.6296 | 0.5816 | 0.7626 |
|
| 274 |
+
| No log | 4.6947 | 446 | 0.5885 | 0.6325 | 0.5885 | 0.7671 |
|
| 275 |
+
| No log | 4.7158 | 448 | 0.6373 | 0.6189 | 0.6373 | 0.7983 |
|
| 276 |
+
| No log | 4.7368 | 450 | 0.6513 | 0.6471 | 0.6513 | 0.8070 |
|
| 277 |
+
| No log | 4.7579 | 452 | 0.6037 | 0.6845 | 0.6037 | 0.7770 |
|
| 278 |
+
| No log | 4.7789 | 454 | 0.5885 | 0.7411 | 0.5885 | 0.7672 |
|
| 279 |
+
| No log | 4.8 | 456 | 0.5891 | 0.7225 | 0.5891 | 0.7675 |
|
| 280 |
+
| No log | 4.8211 | 458 | 0.6162 | 0.6998 | 0.6162 | 0.7850 |
|
| 281 |
+
| No log | 4.8421 | 460 | 0.6469 | 0.6228 | 0.6469 | 0.8043 |
|
| 282 |
+
| No log | 4.8632 | 462 | 0.6082 | 0.6415 | 0.6082 | 0.7799 |
|
| 283 |
+
| No log | 4.8842 | 464 | 0.6019 | 0.6498 | 0.6019 | 0.7758 |
|
| 284 |
+
| No log | 4.9053 | 466 | 0.6214 | 0.5879 | 0.6214 | 0.7883 |
|
| 285 |
+
| No log | 4.9263 | 468 | 0.6013 | 0.6437 | 0.6013 | 0.7755 |
|
| 286 |
+
| No log | 4.9474 | 470 | 0.5787 | 0.6610 | 0.5787 | 0.7607 |
|
| 287 |
+
| No log | 4.9684 | 472 | 0.6352 | 0.6772 | 0.6352 | 0.7970 |
|
| 288 |
+
| No log | 4.9895 | 474 | 0.6676 | 0.6254 | 0.6676 | 0.8170 |
|
| 289 |
+
| No log | 5.0105 | 476 | 0.6489 | 0.6473 | 0.6489 | 0.8055 |
|
| 290 |
+
| No log | 5.0316 | 478 | 0.6344 | 0.6286 | 0.6344 | 0.7965 |
|
| 291 |
+
| No log | 5.0526 | 480 | 0.6292 | 0.6209 | 0.6292 | 0.7932 |
|
| 292 |
+
| No log | 5.0737 | 482 | 0.6317 | 0.5197 | 0.6317 | 0.7948 |
|
| 293 |
+
| No log | 5.0947 | 484 | 0.6094 | 0.5331 | 0.6094 | 0.7806 |
|
| 294 |
+
| No log | 5.1158 | 486 | 0.5813 | 0.6332 | 0.5813 | 0.7624 |
|
| 295 |
+
| No log | 5.1368 | 488 | 0.5700 | 0.6104 | 0.5700 | 0.7550 |
|
| 296 |
+
| No log | 5.1579 | 490 | 0.5757 | 0.6509 | 0.5757 | 0.7588 |
|
| 297 |
+
| No log | 5.1789 | 492 | 0.5747 | 0.6722 | 0.5747 | 0.7581 |
|
| 298 |
+
| No log | 5.2 | 494 | 0.5623 | 0.6543 | 0.5623 | 0.7498 |
|
| 299 |
+
| No log | 5.2211 | 496 | 0.6045 | 0.7217 | 0.6045 | 0.7775 |
|
| 300 |
+
| No log | 5.2421 | 498 | 0.6045 | 0.6880 | 0.6045 | 0.7775 |
|
| 301 |
+
| 0.274 | 5.2632 | 500 | 0.5470 | 0.7071 | 0.5470 | 0.7396 |
|
| 302 |
+
| 0.274 | 5.2842 | 502 | 0.5447 | 0.6959 | 0.5447 | 0.7380 |
|
| 303 |
+
| 0.274 | 5.3053 | 504 | 0.5578 | 0.7178 | 0.5578 | 0.7469 |
|
| 304 |
+
| 0.274 | 5.3263 | 506 | 0.6041 | 0.6221 | 0.6041 | 0.7773 |
|
| 305 |
+
| 0.274 | 5.3474 | 508 | 0.6177 | 0.6319 | 0.6177 | 0.7859 |
|
| 306 |
+
| 0.274 | 5.3684 | 510 | 0.6023 | 0.7032 | 0.6023 | 0.7761 |
|
| 307 |
+
| 0.274 | 5.3895 | 512 | 0.5465 | 0.6838 | 0.5465 | 0.7393 |
|
| 308 |
+
| 0.274 | 5.4105 | 514 | 0.5623 | 0.6455 | 0.5623 | 0.7499 |
|
| 309 |
+
|
| 310 |
+
|
| 311 |
+
### Framework versions
|
| 312 |
+
|
| 313 |
+
- Transformers 4.44.2
|
| 314 |
+
- Pytorch 2.4.0+cu118
|
| 315 |
+
- Datasets 2.21.0
|
| 316 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv02",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 64000
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc501ebc6f447fb09e44deaf8e4bb96a35eef95e1530d45fe6e7d4cbf5eaf683
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4700f6cf3123e9847f569c5729958e498e53ed34f9f756d10e36f6146c97f9db
|
| 3 |
+
size 5304
|