Training in progress, step 500
Browse files- README.md +314 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_k17_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_k17_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: 0.6271
|
| 19 |
+
- Qwk: 0.5339
|
| 20 |
+
- Mse: 0.6271
|
| 21 |
+
- Rmse: 0.7919
|
| 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 | 0.0235 | 2 | 4.1445 | -0.0020 | 4.1445 | 2.0358 |
|
| 53 |
+
| No log | 0.0471 | 4 | 2.2479 | 0.0790 | 2.2479 | 1.4993 |
|
| 54 |
+
| No log | 0.0706 | 6 | 1.5649 | 0.0143 | 1.5649 | 1.2510 |
|
| 55 |
+
| No log | 0.0941 | 8 | 1.0879 | 0.1711 | 1.0879 | 1.0430 |
|
| 56 |
+
| No log | 0.1176 | 10 | 1.0040 | 0.3130 | 1.0040 | 1.0020 |
|
| 57 |
+
| No log | 0.1412 | 12 | 1.0047 | 0.2643 | 1.0047 | 1.0023 |
|
| 58 |
+
| No log | 0.1647 | 14 | 1.0981 | 0.1851 | 1.0981 | 1.0479 |
|
| 59 |
+
| No log | 0.1882 | 16 | 1.1770 | 0.2075 | 1.1770 | 1.0849 |
|
| 60 |
+
| No log | 0.2118 | 18 | 0.8374 | 0.3590 | 0.8374 | 0.9151 |
|
| 61 |
+
| No log | 0.2353 | 20 | 0.7653 | 0.4192 | 0.7653 | 0.8748 |
|
| 62 |
+
| No log | 0.2588 | 22 | 0.7185 | 0.4304 | 0.7185 | 0.8477 |
|
| 63 |
+
| No log | 0.2824 | 24 | 1.1932 | 0.3561 | 1.1932 | 1.0923 |
|
| 64 |
+
| No log | 0.3059 | 26 | 1.8345 | 0.2324 | 1.8345 | 1.3544 |
|
| 65 |
+
| No log | 0.3294 | 28 | 1.4785 | 0.3329 | 1.4785 | 1.2159 |
|
| 66 |
+
| No log | 0.3529 | 30 | 0.7518 | 0.6357 | 0.7518 | 0.8671 |
|
| 67 |
+
| No log | 0.3765 | 32 | 0.6501 | 0.6365 | 0.6501 | 0.8063 |
|
| 68 |
+
| No log | 0.4 | 34 | 0.6344 | 0.6186 | 0.6344 | 0.7965 |
|
| 69 |
+
| No log | 0.4235 | 36 | 0.7981 | 0.5348 | 0.7981 | 0.8934 |
|
| 70 |
+
| No log | 0.4471 | 38 | 0.9656 | 0.4693 | 0.9656 | 0.9827 |
|
| 71 |
+
| No log | 0.4706 | 40 | 0.8436 | 0.5345 | 0.8436 | 0.9185 |
|
| 72 |
+
| No log | 0.4941 | 42 | 0.7330 | 0.5940 | 0.7330 | 0.8562 |
|
| 73 |
+
| No log | 0.5176 | 44 | 0.7906 | 0.5541 | 0.7906 | 0.8891 |
|
| 74 |
+
| No log | 0.5412 | 46 | 0.7715 | 0.5640 | 0.7715 | 0.8784 |
|
| 75 |
+
| No log | 0.5647 | 48 | 0.7559 | 0.6175 | 0.7559 | 0.8694 |
|
| 76 |
+
| No log | 0.5882 | 50 | 0.7426 | 0.6113 | 0.7426 | 0.8617 |
|
| 77 |
+
| No log | 0.6118 | 52 | 0.7196 | 0.6038 | 0.7196 | 0.8483 |
|
| 78 |
+
| No log | 0.6353 | 54 | 0.7580 | 0.5718 | 0.7580 | 0.8707 |
|
| 79 |
+
| No log | 0.6588 | 56 | 0.7378 | 0.5339 | 0.7378 | 0.8590 |
|
| 80 |
+
| No log | 0.6824 | 58 | 0.6326 | 0.6374 | 0.6326 | 0.7954 |
|
| 81 |
+
| No log | 0.7059 | 60 | 0.6344 | 0.6374 | 0.6344 | 0.7965 |
|
| 82 |
+
| No log | 0.7294 | 62 | 0.6595 | 0.6203 | 0.6595 | 0.8121 |
|
| 83 |
+
| No log | 0.7529 | 64 | 0.9634 | 0.5464 | 0.9634 | 0.9815 |
|
| 84 |
+
| No log | 0.7765 | 66 | 1.0746 | 0.4779 | 1.0746 | 1.0366 |
|
| 85 |
+
| No log | 0.8 | 68 | 0.7777 | 0.6645 | 0.7777 | 0.8819 |
|
| 86 |
+
| No log | 0.8235 | 70 | 0.6178 | 0.6230 | 0.6178 | 0.7860 |
|
| 87 |
+
| No log | 0.8471 | 72 | 0.6071 | 0.6493 | 0.6071 | 0.7792 |
|
| 88 |
+
| No log | 0.8706 | 74 | 0.6667 | 0.6795 | 0.6667 | 0.8165 |
|
| 89 |
+
| No log | 0.8941 | 76 | 0.6854 | 0.6221 | 0.6854 | 0.8279 |
|
| 90 |
+
| No log | 0.9176 | 78 | 0.7047 | 0.6048 | 0.7047 | 0.8395 |
|
| 91 |
+
| No log | 0.9412 | 80 | 0.6494 | 0.5524 | 0.6494 | 0.8058 |
|
| 92 |
+
| No log | 0.9647 | 82 | 0.6250 | 0.5726 | 0.6250 | 0.7905 |
|
| 93 |
+
| No log | 0.9882 | 84 | 0.6032 | 0.6780 | 0.6032 | 0.7767 |
|
| 94 |
+
| No log | 1.0118 | 86 | 0.6201 | 0.6667 | 0.6201 | 0.7874 |
|
| 95 |
+
| No log | 1.0353 | 88 | 0.6351 | 0.5999 | 0.6351 | 0.7969 |
|
| 96 |
+
| No log | 1.0588 | 90 | 0.6906 | 0.6175 | 0.6906 | 0.8310 |
|
| 97 |
+
| No log | 1.0824 | 92 | 0.9067 | 0.5772 | 0.9067 | 0.9522 |
|
| 98 |
+
| No log | 1.1059 | 94 | 0.9197 | 0.5457 | 0.9197 | 0.9590 |
|
| 99 |
+
| No log | 1.1294 | 96 | 0.7663 | 0.6612 | 0.7663 | 0.8754 |
|
| 100 |
+
| No log | 1.1529 | 98 | 0.8336 | 0.6166 | 0.8336 | 0.9130 |
|
| 101 |
+
| No log | 1.1765 | 100 | 0.7524 | 0.5884 | 0.7524 | 0.8674 |
|
| 102 |
+
| No log | 1.2 | 102 | 0.7185 | 0.6559 | 0.7185 | 0.8477 |
|
| 103 |
+
| No log | 1.2235 | 104 | 1.1409 | 0.4594 | 1.1409 | 1.0681 |
|
| 104 |
+
| No log | 1.2471 | 106 | 1.2753 | 0.4289 | 1.2753 | 1.1293 |
|
| 105 |
+
| No log | 1.2706 | 108 | 1.0246 | 0.5191 | 1.0246 | 1.0122 |
|
| 106 |
+
| No log | 1.2941 | 110 | 0.7460 | 0.6350 | 0.7460 | 0.8637 |
|
| 107 |
+
| No log | 1.3176 | 112 | 0.7713 | 0.6535 | 0.7713 | 0.8782 |
|
| 108 |
+
| No log | 1.3412 | 114 | 0.7919 | 0.6741 | 0.7919 | 0.8899 |
|
| 109 |
+
| No log | 1.3647 | 116 | 0.7326 | 0.6287 | 0.7326 | 0.8559 |
|
| 110 |
+
| No log | 1.3882 | 118 | 0.7023 | 0.5824 | 0.7023 | 0.8380 |
|
| 111 |
+
| No log | 1.4118 | 120 | 0.8496 | 0.5800 | 0.8496 | 0.9217 |
|
| 112 |
+
| No log | 1.4353 | 122 | 0.8197 | 0.5687 | 0.8197 | 0.9054 |
|
| 113 |
+
| No log | 1.4588 | 124 | 0.6830 | 0.5481 | 0.6830 | 0.8264 |
|
| 114 |
+
| No log | 1.4824 | 126 | 0.6486 | 0.6169 | 0.6486 | 0.8054 |
|
| 115 |
+
| No log | 1.5059 | 128 | 0.6399 | 0.6510 | 0.6399 | 0.7999 |
|
| 116 |
+
| No log | 1.5294 | 130 | 0.6991 | 0.5406 | 0.6991 | 0.8361 |
|
| 117 |
+
| No log | 1.5529 | 132 | 0.9188 | 0.5357 | 0.9188 | 0.9585 |
|
| 118 |
+
| No log | 1.5765 | 134 | 0.9676 | 0.5181 | 0.9676 | 0.9837 |
|
| 119 |
+
| No log | 1.6 | 136 | 0.7649 | 0.6219 | 0.7649 | 0.8746 |
|
| 120 |
+
| No log | 1.6235 | 138 | 0.6645 | 0.5937 | 0.6645 | 0.8151 |
|
| 121 |
+
| No log | 1.6471 | 140 | 0.7014 | 0.6676 | 0.7014 | 0.8375 |
|
| 122 |
+
| No log | 1.6706 | 142 | 0.6716 | 0.6840 | 0.6716 | 0.8195 |
|
| 123 |
+
| No log | 1.6941 | 144 | 0.6629 | 0.5951 | 0.6629 | 0.8142 |
|
| 124 |
+
| No log | 1.7176 | 146 | 0.6787 | 0.6043 | 0.6787 | 0.8238 |
|
| 125 |
+
| No log | 1.7412 | 148 | 0.6479 | 0.6260 | 0.6479 | 0.8049 |
|
| 126 |
+
| No log | 1.7647 | 150 | 0.6267 | 0.6508 | 0.6267 | 0.7917 |
|
| 127 |
+
| No log | 1.7882 | 152 | 0.6142 | 0.6804 | 0.6142 | 0.7837 |
|
| 128 |
+
| No log | 1.8118 | 154 | 0.6128 | 0.6564 | 0.6128 | 0.7828 |
|
| 129 |
+
| No log | 1.8353 | 156 | 0.6720 | 0.6019 | 0.6720 | 0.8198 |
|
| 130 |
+
| No log | 1.8588 | 158 | 0.7340 | 0.5812 | 0.7340 | 0.8567 |
|
| 131 |
+
| No log | 1.8824 | 160 | 0.6755 | 0.6091 | 0.6755 | 0.8219 |
|
| 132 |
+
| No log | 1.9059 | 162 | 0.6447 | 0.6790 | 0.6447 | 0.8029 |
|
| 133 |
+
| No log | 1.9294 | 164 | 0.7480 | 0.6029 | 0.7480 | 0.8649 |
|
| 134 |
+
| No log | 1.9529 | 166 | 0.7255 | 0.6013 | 0.7255 | 0.8518 |
|
| 135 |
+
| No log | 1.9765 | 168 | 0.6574 | 0.6479 | 0.6574 | 0.8108 |
|
| 136 |
+
| No log | 2.0 | 170 | 0.6886 | 0.6555 | 0.6886 | 0.8298 |
|
| 137 |
+
| No log | 2.0235 | 172 | 0.6956 | 0.6426 | 0.6956 | 0.8341 |
|
| 138 |
+
| No log | 2.0471 | 174 | 0.6380 | 0.6695 | 0.6380 | 0.7988 |
|
| 139 |
+
| No log | 2.0706 | 176 | 0.6728 | 0.6427 | 0.6728 | 0.8202 |
|
| 140 |
+
| No log | 2.0941 | 178 | 0.6796 | 0.6388 | 0.6796 | 0.8244 |
|
| 141 |
+
| No log | 2.1176 | 180 | 0.6237 | 0.6518 | 0.6237 | 0.7898 |
|
| 142 |
+
| No log | 2.1412 | 182 | 0.6714 | 0.6035 | 0.6714 | 0.8194 |
|
| 143 |
+
| No log | 2.1647 | 184 | 0.7415 | 0.5157 | 0.7415 | 0.8611 |
|
| 144 |
+
| No log | 2.1882 | 186 | 0.7191 | 0.5739 | 0.7191 | 0.8480 |
|
| 145 |
+
| No log | 2.2118 | 188 | 0.6364 | 0.6089 | 0.6364 | 0.7978 |
|
| 146 |
+
| No log | 2.2353 | 190 | 0.6116 | 0.6979 | 0.6116 | 0.7821 |
|
| 147 |
+
| No log | 2.2588 | 192 | 0.5980 | 0.6664 | 0.5980 | 0.7733 |
|
| 148 |
+
| No log | 2.2824 | 194 | 0.5824 | 0.6701 | 0.5824 | 0.7631 |
|
| 149 |
+
| No log | 2.3059 | 196 | 0.5707 | 0.6578 | 0.5707 | 0.7555 |
|
| 150 |
+
| No log | 2.3294 | 198 | 0.5890 | 0.6246 | 0.5890 | 0.7675 |
|
| 151 |
+
| No log | 2.3529 | 200 | 0.6042 | 0.6089 | 0.6042 | 0.7773 |
|
| 152 |
+
| No log | 2.3765 | 202 | 0.6000 | 0.5879 | 0.6000 | 0.7746 |
|
| 153 |
+
| No log | 2.4 | 204 | 0.5661 | 0.6762 | 0.5661 | 0.7524 |
|
| 154 |
+
| No log | 2.4235 | 206 | 0.5570 | 0.6988 | 0.5570 | 0.7463 |
|
| 155 |
+
| No log | 2.4471 | 208 | 0.5890 | 0.5966 | 0.5890 | 0.7675 |
|
| 156 |
+
| No log | 2.4706 | 210 | 0.7765 | 0.5832 | 0.7765 | 0.8812 |
|
| 157 |
+
| No log | 2.4941 | 212 | 0.8740 | 0.5840 | 0.8740 | 0.9349 |
|
| 158 |
+
| No log | 2.5176 | 214 | 0.7621 | 0.6281 | 0.7621 | 0.8730 |
|
| 159 |
+
| No log | 2.5412 | 216 | 0.6043 | 0.6144 | 0.6043 | 0.7774 |
|
| 160 |
+
| No log | 2.5647 | 218 | 0.6264 | 0.6511 | 0.6264 | 0.7914 |
|
| 161 |
+
| No log | 2.5882 | 220 | 0.6894 | 0.6502 | 0.6894 | 0.8303 |
|
| 162 |
+
| No log | 2.6118 | 222 | 0.6606 | 0.6397 | 0.6606 | 0.8128 |
|
| 163 |
+
| No log | 2.6353 | 224 | 0.6475 | 0.5301 | 0.6475 | 0.8047 |
|
| 164 |
+
| No log | 2.6588 | 226 | 0.7459 | 0.6013 | 0.7459 | 0.8637 |
|
| 165 |
+
| No log | 2.6824 | 228 | 0.8423 | 0.5832 | 0.8423 | 0.9178 |
|
| 166 |
+
| No log | 2.7059 | 230 | 0.8166 | 0.5924 | 0.8166 | 0.9037 |
|
| 167 |
+
| No log | 2.7294 | 232 | 0.7044 | 0.5847 | 0.7044 | 0.8393 |
|
| 168 |
+
| No log | 2.7529 | 234 | 0.6263 | 0.5851 | 0.6263 | 0.7914 |
|
| 169 |
+
| No log | 2.7765 | 236 | 0.6478 | 0.6573 | 0.6478 | 0.8048 |
|
| 170 |
+
| No log | 2.8 | 238 | 0.6407 | 0.6575 | 0.6407 | 0.8004 |
|
| 171 |
+
| No log | 2.8235 | 240 | 0.6071 | 0.6360 | 0.6071 | 0.7792 |
|
| 172 |
+
| No log | 2.8471 | 242 | 0.6400 | 0.4975 | 0.6400 | 0.8000 |
|
| 173 |
+
| No log | 2.8706 | 244 | 0.7048 | 0.5134 | 0.7048 | 0.8395 |
|
| 174 |
+
| No log | 2.8941 | 246 | 0.6495 | 0.5571 | 0.6495 | 0.8059 |
|
| 175 |
+
| No log | 2.9176 | 248 | 0.5960 | 0.6377 | 0.5960 | 0.7720 |
|
| 176 |
+
| No log | 2.9412 | 250 | 0.6098 | 0.6636 | 0.6098 | 0.7809 |
|
| 177 |
+
| No log | 2.9647 | 252 | 0.6207 | 0.6714 | 0.6207 | 0.7879 |
|
| 178 |
+
| No log | 2.9882 | 254 | 0.6292 | 0.6441 | 0.6292 | 0.7932 |
|
| 179 |
+
| No log | 3.0118 | 256 | 0.6727 | 0.6091 | 0.6727 | 0.8202 |
|
| 180 |
+
| No log | 3.0353 | 258 | 0.6685 | 0.5922 | 0.6685 | 0.8176 |
|
| 181 |
+
| No log | 3.0588 | 260 | 0.6667 | 0.6045 | 0.6667 | 0.8165 |
|
| 182 |
+
| No log | 3.0824 | 262 | 0.6567 | 0.6586 | 0.6567 | 0.8103 |
|
| 183 |
+
| No log | 3.1059 | 264 | 0.6523 | 0.6613 | 0.6523 | 0.8077 |
|
| 184 |
+
| No log | 3.1294 | 266 | 0.6501 | 0.6518 | 0.6501 | 0.8063 |
|
| 185 |
+
| No log | 3.1529 | 268 | 0.6486 | 0.6492 | 0.6486 | 0.8053 |
|
| 186 |
+
| No log | 3.1765 | 270 | 0.6289 | 0.6392 | 0.6289 | 0.7930 |
|
| 187 |
+
| No log | 3.2 | 272 | 0.6260 | 0.5950 | 0.6260 | 0.7912 |
|
| 188 |
+
| No log | 3.2235 | 274 | 0.6214 | 0.5879 | 0.6214 | 0.7883 |
|
| 189 |
+
| No log | 3.2471 | 276 | 0.6226 | 0.6154 | 0.6226 | 0.7890 |
|
| 190 |
+
| No log | 3.2706 | 278 | 0.6255 | 0.7153 | 0.6255 | 0.7909 |
|
| 191 |
+
| No log | 3.2941 | 280 | 0.6621 | 0.6221 | 0.6621 | 0.8137 |
|
| 192 |
+
| No log | 3.3176 | 282 | 0.6451 | 0.6350 | 0.6451 | 0.8032 |
|
| 193 |
+
| No log | 3.3412 | 284 | 0.6525 | 0.6426 | 0.6525 | 0.8078 |
|
| 194 |
+
| No log | 3.3647 | 286 | 0.7297 | 0.5648 | 0.7297 | 0.8542 |
|
| 195 |
+
| No log | 3.3882 | 288 | 0.7733 | 0.5658 | 0.7733 | 0.8794 |
|
| 196 |
+
| No log | 3.4118 | 290 | 0.6604 | 0.5583 | 0.6604 | 0.8126 |
|
| 197 |
+
| No log | 3.4353 | 292 | 0.5797 | 0.6230 | 0.5797 | 0.7614 |
|
| 198 |
+
| No log | 3.4588 | 294 | 0.6096 | 0.6291 | 0.6096 | 0.7808 |
|
| 199 |
+
| No log | 3.4824 | 296 | 0.6138 | 0.6575 | 0.6138 | 0.7835 |
|
| 200 |
+
| No log | 3.5059 | 298 | 0.5891 | 0.6545 | 0.5891 | 0.7676 |
|
| 201 |
+
| No log | 3.5294 | 300 | 0.6114 | 0.6354 | 0.6114 | 0.7819 |
|
| 202 |
+
| No log | 3.5529 | 302 | 0.6225 | 0.6269 | 0.6225 | 0.7890 |
|
| 203 |
+
| No log | 3.5765 | 304 | 0.6699 | 0.5617 | 0.6699 | 0.8185 |
|
| 204 |
+
| No log | 3.6 | 306 | 0.6541 | 0.6065 | 0.6541 | 0.8087 |
|
| 205 |
+
| No log | 3.6235 | 308 | 0.6110 | 0.6545 | 0.6110 | 0.7817 |
|
| 206 |
+
| No log | 3.6471 | 310 | 0.6125 | 0.6641 | 0.6125 | 0.7826 |
|
| 207 |
+
| No log | 3.6706 | 312 | 0.6238 | 0.6096 | 0.6238 | 0.7898 |
|
| 208 |
+
| No log | 3.6941 | 314 | 0.6921 | 0.5548 | 0.6921 | 0.8319 |
|
| 209 |
+
| No log | 3.7176 | 316 | 0.7626 | 0.5132 | 0.7626 | 0.8733 |
|
| 210 |
+
| No log | 3.7412 | 318 | 0.7107 | 0.5335 | 0.7107 | 0.8430 |
|
| 211 |
+
| No log | 3.7647 | 320 | 0.6370 | 0.5524 | 0.6370 | 0.7981 |
|
| 212 |
+
| No log | 3.7882 | 322 | 0.6284 | 0.6038 | 0.6284 | 0.7927 |
|
| 213 |
+
| No log | 3.8118 | 324 | 0.6536 | 0.5905 | 0.6536 | 0.8084 |
|
| 214 |
+
| No log | 3.8353 | 326 | 0.6610 | 0.5905 | 0.6610 | 0.8130 |
|
| 215 |
+
| No log | 3.8588 | 328 | 0.6478 | 0.5794 | 0.6478 | 0.8049 |
|
| 216 |
+
| No log | 3.8824 | 330 | 0.7330 | 0.5525 | 0.7330 | 0.8562 |
|
| 217 |
+
| No log | 3.9059 | 332 | 0.7625 | 0.5730 | 0.7625 | 0.8732 |
|
| 218 |
+
| No log | 3.9294 | 334 | 0.6919 | 0.5849 | 0.6919 | 0.8318 |
|
| 219 |
+
| No log | 3.9529 | 336 | 0.6539 | 0.4938 | 0.6539 | 0.8086 |
|
| 220 |
+
| No log | 3.9765 | 338 | 0.6870 | 0.5375 | 0.6870 | 0.8289 |
|
| 221 |
+
| No log | 4.0 | 340 | 0.7180 | 0.5858 | 0.7180 | 0.8473 |
|
| 222 |
+
| No log | 4.0235 | 342 | 0.6673 | 0.6177 | 0.6673 | 0.8169 |
|
| 223 |
+
| No log | 4.0471 | 344 | 0.6046 | 0.5955 | 0.6046 | 0.7776 |
|
| 224 |
+
| No log | 4.0706 | 346 | 0.6390 | 0.6173 | 0.6390 | 0.7993 |
|
| 225 |
+
| No log | 4.0941 | 348 | 0.7269 | 0.5924 | 0.7269 | 0.8526 |
|
| 226 |
+
| No log | 4.1176 | 350 | 0.7188 | 0.6092 | 0.7188 | 0.8478 |
|
| 227 |
+
| No log | 4.1412 | 352 | 0.7020 | 0.5992 | 0.7020 | 0.8379 |
|
| 228 |
+
| No log | 4.1647 | 354 | 0.6306 | 0.6721 | 0.6306 | 0.7941 |
|
| 229 |
+
| No log | 4.1882 | 356 | 0.6081 | 0.6737 | 0.6081 | 0.7798 |
|
| 230 |
+
| No log | 4.2118 | 358 | 0.6089 | 0.6896 | 0.6089 | 0.7803 |
|
| 231 |
+
| No log | 4.2353 | 360 | 0.6002 | 0.6896 | 0.6002 | 0.7747 |
|
| 232 |
+
| No log | 4.2588 | 362 | 0.5899 | 0.6561 | 0.5899 | 0.7681 |
|
| 233 |
+
| No log | 4.2824 | 364 | 0.6125 | 0.6386 | 0.6125 | 0.7826 |
|
| 234 |
+
| No log | 4.3059 | 366 | 0.6110 | 0.6386 | 0.6110 | 0.7817 |
|
| 235 |
+
| No log | 4.3294 | 368 | 0.6232 | 0.6603 | 0.6232 | 0.7894 |
|
| 236 |
+
| No log | 4.3529 | 370 | 0.6068 | 0.5839 | 0.6068 | 0.7790 |
|
| 237 |
+
| No log | 4.3765 | 372 | 0.6439 | 0.5215 | 0.6439 | 0.8024 |
|
| 238 |
+
| No log | 4.4 | 374 | 0.6537 | 0.5342 | 0.6537 | 0.8085 |
|
| 239 |
+
| No log | 4.4235 | 376 | 0.6199 | 0.5982 | 0.6199 | 0.7873 |
|
| 240 |
+
| No log | 4.4471 | 378 | 0.6160 | 0.6135 | 0.6160 | 0.7849 |
|
| 241 |
+
| No log | 4.4706 | 380 | 0.6258 | 0.6299 | 0.6258 | 0.7911 |
|
| 242 |
+
| No log | 4.4941 | 382 | 0.6871 | 0.6619 | 0.6871 | 0.8289 |
|
| 243 |
+
| No log | 4.5176 | 384 | 0.7156 | 0.6251 | 0.7156 | 0.8459 |
|
| 244 |
+
| No log | 4.5412 | 386 | 0.6747 | 0.5835 | 0.6747 | 0.8214 |
|
| 245 |
+
| No log | 4.5647 | 388 | 0.6205 | 0.6410 | 0.6205 | 0.7877 |
|
| 246 |
+
| No log | 4.5882 | 390 | 0.5929 | 0.6598 | 0.5929 | 0.7700 |
|
| 247 |
+
| No log | 4.6118 | 392 | 0.5907 | 0.6853 | 0.5907 | 0.7686 |
|
| 248 |
+
| No log | 4.6353 | 394 | 0.5987 | 0.6528 | 0.5987 | 0.7737 |
|
| 249 |
+
| No log | 4.6588 | 396 | 0.6086 | 0.6451 | 0.6086 | 0.7801 |
|
| 250 |
+
| No log | 4.6824 | 398 | 0.6086 | 0.6557 | 0.6086 | 0.7801 |
|
| 251 |
+
| No log | 4.7059 | 400 | 0.6126 | 0.6557 | 0.6126 | 0.7827 |
|
| 252 |
+
| No log | 4.7294 | 402 | 0.6102 | 0.6292 | 0.6102 | 0.7811 |
|
| 253 |
+
| No log | 4.7529 | 404 | 0.6324 | 0.5653 | 0.6324 | 0.7953 |
|
| 254 |
+
| No log | 4.7765 | 406 | 0.6145 | 0.5653 | 0.6145 | 0.7839 |
|
| 255 |
+
| No log | 4.8 | 408 | 0.5885 | 0.6830 | 0.5885 | 0.7671 |
|
| 256 |
+
| No log | 4.8235 | 410 | 0.5865 | 0.6748 | 0.5865 | 0.7658 |
|
| 257 |
+
| No log | 4.8471 | 412 | 0.5750 | 0.6748 | 0.5750 | 0.7583 |
|
| 258 |
+
| No log | 4.8706 | 414 | 0.5669 | 0.6561 | 0.5669 | 0.7529 |
|
| 259 |
+
| No log | 4.8941 | 416 | 0.6028 | 0.6701 | 0.6028 | 0.7764 |
|
| 260 |
+
| No log | 4.9176 | 418 | 0.6023 | 0.6701 | 0.6023 | 0.7761 |
|
| 261 |
+
| No log | 4.9412 | 420 | 0.5819 | 0.6097 | 0.5819 | 0.7628 |
|
| 262 |
+
| No log | 4.9647 | 422 | 0.5870 | 0.6230 | 0.5870 | 0.7662 |
|
| 263 |
+
| No log | 4.9882 | 424 | 0.6140 | 0.6117 | 0.6140 | 0.7836 |
|
| 264 |
+
| No log | 5.0118 | 426 | 0.6287 | 0.6198 | 0.6287 | 0.7929 |
|
| 265 |
+
| No log | 5.0353 | 428 | 0.6164 | 0.5796 | 0.6164 | 0.7851 |
|
| 266 |
+
| No log | 5.0588 | 430 | 0.6125 | 0.5562 | 0.6125 | 0.7826 |
|
| 267 |
+
| No log | 5.0824 | 432 | 0.6024 | 0.5542 | 0.6024 | 0.7761 |
|
| 268 |
+
| No log | 5.1059 | 434 | 0.5998 | 0.6444 | 0.5998 | 0.7745 |
|
| 269 |
+
| No log | 5.1294 | 436 | 0.6151 | 0.6891 | 0.6151 | 0.7843 |
|
| 270 |
+
| No log | 5.1529 | 438 | 0.6153 | 0.6934 | 0.6153 | 0.7844 |
|
| 271 |
+
| No log | 5.1765 | 440 | 0.6065 | 0.6761 | 0.6065 | 0.7788 |
|
| 272 |
+
| No log | 5.2 | 442 | 0.5923 | 0.6307 | 0.5923 | 0.7696 |
|
| 273 |
+
| No log | 5.2235 | 444 | 0.5970 | 0.6343 | 0.5970 | 0.7726 |
|
| 274 |
+
| No log | 5.2471 | 446 | 0.6003 | 0.5679 | 0.6003 | 0.7748 |
|
| 275 |
+
| No log | 5.2706 | 448 | 0.6252 | 0.5459 | 0.6252 | 0.7907 |
|
| 276 |
+
| No log | 5.2941 | 450 | 0.6037 | 0.5459 | 0.6037 | 0.7770 |
|
| 277 |
+
| No log | 5.3176 | 452 | 0.5879 | 0.6139 | 0.5879 | 0.7668 |
|
| 278 |
+
| No log | 5.3412 | 454 | 0.5925 | 0.6445 | 0.5925 | 0.7698 |
|
| 279 |
+
| No log | 5.3647 | 456 | 0.6326 | 0.5810 | 0.6326 | 0.7954 |
|
| 280 |
+
| No log | 5.3882 | 458 | 0.6325 | 0.5835 | 0.6325 | 0.7953 |
|
| 281 |
+
| No log | 5.4118 | 460 | 0.6120 | 0.6117 | 0.6120 | 0.7823 |
|
| 282 |
+
| No log | 5.4353 | 462 | 0.5912 | 0.6648 | 0.5912 | 0.7689 |
|
| 283 |
+
| No log | 5.4588 | 464 | 0.5909 | 0.6358 | 0.5909 | 0.7687 |
|
| 284 |
+
| No log | 5.4824 | 466 | 0.6049 | 0.6525 | 0.6049 | 0.7778 |
|
| 285 |
+
| No log | 5.5059 | 468 | 0.6247 | 0.6330 | 0.6247 | 0.7904 |
|
| 286 |
+
| No log | 5.5294 | 470 | 0.6399 | 0.6135 | 0.6399 | 0.8000 |
|
| 287 |
+
| No log | 5.5529 | 472 | 0.6219 | 0.6771 | 0.6219 | 0.7886 |
|
| 288 |
+
| No log | 5.5765 | 474 | 0.5914 | 0.6772 | 0.5914 | 0.7691 |
|
| 289 |
+
| No log | 5.6 | 476 | 0.6232 | 0.6570 | 0.6232 | 0.7894 |
|
| 290 |
+
| No log | 5.6235 | 478 | 0.7032 | 0.6387 | 0.7032 | 0.8385 |
|
| 291 |
+
| No log | 5.6471 | 480 | 0.7382 | 0.6466 | 0.7382 | 0.8592 |
|
| 292 |
+
| No log | 5.6706 | 482 | 0.6886 | 0.6636 | 0.6886 | 0.8298 |
|
| 293 |
+
| No log | 5.6941 | 484 | 0.6048 | 0.6644 | 0.6048 | 0.7777 |
|
| 294 |
+
| No log | 5.7176 | 486 | 0.5782 | 0.6846 | 0.5782 | 0.7604 |
|
| 295 |
+
| No log | 5.7412 | 488 | 0.6104 | 0.5748 | 0.6104 | 0.7813 |
|
| 296 |
+
| No log | 5.7647 | 490 | 0.6269 | 0.5548 | 0.6269 | 0.7917 |
|
| 297 |
+
| No log | 5.7882 | 492 | 0.6097 | 0.5542 | 0.6097 | 0.7808 |
|
| 298 |
+
| No log | 5.8118 | 494 | 0.5833 | 0.6648 | 0.5833 | 0.7637 |
|
| 299 |
+
| No log | 5.8353 | 496 | 0.5787 | 0.6745 | 0.5787 | 0.7607 |
|
| 300 |
+
| No log | 5.8588 | 498 | 0.5726 | 0.6962 | 0.5726 | 0.7567 |
|
| 301 |
+
| 0.2743 | 5.8824 | 500 | 0.5681 | 0.6772 | 0.5681 | 0.7537 |
|
| 302 |
+
| 0.2743 | 5.9059 | 502 | 0.6416 | 0.6565 | 0.6416 | 0.8010 |
|
| 303 |
+
| 0.2743 | 5.9294 | 504 | 0.7245 | 0.6248 | 0.7245 | 0.8512 |
|
| 304 |
+
| 0.2743 | 5.9529 | 506 | 0.7520 | 0.6076 | 0.7520 | 0.8672 |
|
| 305 |
+
| 0.2743 | 5.9765 | 508 | 0.6949 | 0.5690 | 0.6949 | 0.8336 |
|
| 306 |
+
| 0.2743 | 6.0 | 510 | 0.6271 | 0.5339 | 0.6271 | 0.7919 |
|
| 307 |
+
|
| 308 |
+
|
| 309 |
+
### Framework versions
|
| 310 |
+
|
| 311 |
+
- Transformers 4.44.2
|
| 312 |
+
- Pytorch 2.4.0+cu118
|
| 313 |
+
- Datasets 2.21.0
|
| 314 |
+
- 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:ca0af89f8eabe4c3d3d4dce63af450b24af66b4baf4bc57bbe6f5df5cfc0f4a6
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36487650009344dacf6d76a2be98418b2355019c31364445907d96d6b315556d
|
| 3 |
+
size 5304
|