End of training
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: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_development
|
| 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 |
+
# Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_development
|
| 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: 0.5806
|
| 19 |
+
- Qwk: 0.5631
|
| 20 |
+
- Mse: 0.5806
|
| 21 |
+
- Rmse: 0.7620
|
| 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 | 0.0202 | 2 | 3.8201 | -0.0048 | 3.8201 | 1.9545 |
|
| 53 |
+
| No log | 0.0404 | 4 | 2.8516 | 0.0557 | 2.8516 | 1.6887 |
|
| 54 |
+
| No log | 0.0606 | 6 | 1.6463 | 0.0997 | 1.6463 | 1.2831 |
|
| 55 |
+
| No log | 0.0808 | 8 | 0.7609 | 0.1997 | 0.7609 | 0.8723 |
|
| 56 |
+
| No log | 0.1010 | 10 | 0.7725 | 0.0256 | 0.7725 | 0.8789 |
|
| 57 |
+
| No log | 0.1212 | 12 | 0.9123 | -0.0172 | 0.9123 | 0.9551 |
|
| 58 |
+
| No log | 0.1414 | 14 | 0.8664 | 0.0026 | 0.8664 | 0.9308 |
|
| 59 |
+
| No log | 0.1616 | 16 | 0.7816 | 0.0328 | 0.7816 | 0.8841 |
|
| 60 |
+
| No log | 0.1818 | 18 | 0.6613 | 0.0892 | 0.6613 | 0.8132 |
|
| 61 |
+
| No log | 0.2020 | 20 | 0.6727 | 0.3461 | 0.6727 | 0.8202 |
|
| 62 |
+
| No log | 0.2222 | 22 | 0.7231 | 0.2589 | 0.7231 | 0.8503 |
|
| 63 |
+
| No log | 0.2424 | 24 | 0.6292 | 0.3518 | 0.6292 | 0.7932 |
|
| 64 |
+
| No log | 0.2626 | 26 | 0.5721 | 0.3695 | 0.5721 | 0.7564 |
|
| 65 |
+
| No log | 0.2828 | 28 | 0.6909 | 0.1568 | 0.6909 | 0.8312 |
|
| 66 |
+
| No log | 0.3030 | 30 | 0.6832 | 0.2332 | 0.6832 | 0.8265 |
|
| 67 |
+
| No log | 0.3232 | 32 | 0.6265 | 0.3172 | 0.6265 | 0.7915 |
|
| 68 |
+
| No log | 0.3434 | 34 | 0.5742 | 0.4019 | 0.5742 | 0.7577 |
|
| 69 |
+
| No log | 0.3636 | 36 | 0.5533 | 0.4235 | 0.5533 | 0.7438 |
|
| 70 |
+
| No log | 0.3838 | 38 | 0.5750 | 0.3371 | 0.5750 | 0.7583 |
|
| 71 |
+
| No log | 0.4040 | 40 | 0.5739 | 0.3326 | 0.5739 | 0.7576 |
|
| 72 |
+
| No log | 0.4242 | 42 | 0.5582 | 0.3674 | 0.5582 | 0.7471 |
|
| 73 |
+
| No log | 0.4444 | 44 | 0.5163 | 0.4235 | 0.5163 | 0.7186 |
|
| 74 |
+
| No log | 0.4646 | 46 | 0.5340 | 0.4104 | 0.5340 | 0.7308 |
|
| 75 |
+
| No log | 0.4848 | 48 | 0.6408 | 0.2833 | 0.6408 | 0.8005 |
|
| 76 |
+
| No log | 0.5051 | 50 | 0.6745 | 0.2680 | 0.6745 | 0.8212 |
|
| 77 |
+
| No log | 0.5253 | 52 | 0.6289 | 0.3398 | 0.6289 | 0.7930 |
|
| 78 |
+
| No log | 0.5455 | 54 | 0.5498 | 0.4331 | 0.5498 | 0.7415 |
|
| 79 |
+
| No log | 0.5657 | 56 | 0.5390 | 0.5119 | 0.5390 | 0.7342 |
|
| 80 |
+
| No log | 0.5859 | 58 | 0.5254 | 0.5022 | 0.5254 | 0.7248 |
|
| 81 |
+
| No log | 0.6061 | 60 | 0.5307 | 0.4131 | 0.5307 | 0.7285 |
|
| 82 |
+
| No log | 0.6263 | 62 | 0.5910 | 0.3423 | 0.5910 | 0.7688 |
|
| 83 |
+
| No log | 0.6465 | 64 | 0.7147 | 0.2449 | 0.7147 | 0.8454 |
|
| 84 |
+
| No log | 0.6667 | 66 | 0.7491 | 0.2421 | 0.7491 | 0.8655 |
|
| 85 |
+
| No log | 0.6869 | 68 | 0.6881 | 0.3737 | 0.6881 | 0.8295 |
|
| 86 |
+
| No log | 0.7071 | 70 | 0.6412 | 0.5019 | 0.6412 | 0.8007 |
|
| 87 |
+
| No log | 0.7273 | 72 | 0.5705 | 0.5596 | 0.5705 | 0.7553 |
|
| 88 |
+
| No log | 0.7475 | 74 | 0.4957 | 0.5507 | 0.4957 | 0.7040 |
|
| 89 |
+
| No log | 0.7677 | 76 | 0.4640 | 0.5208 | 0.4640 | 0.6812 |
|
| 90 |
+
| No log | 0.7879 | 78 | 0.4573 | 0.5272 | 0.4573 | 0.6762 |
|
| 91 |
+
| No log | 0.8081 | 80 | 0.4450 | 0.5088 | 0.4450 | 0.6671 |
|
| 92 |
+
| No log | 0.8283 | 82 | 0.4706 | 0.4794 | 0.4706 | 0.6860 |
|
| 93 |
+
| No log | 0.8485 | 84 | 0.5419 | 0.3899 | 0.5419 | 0.7361 |
|
| 94 |
+
| No log | 0.8687 | 86 | 0.6341 | 0.3609 | 0.6341 | 0.7963 |
|
| 95 |
+
| No log | 0.8889 | 88 | 0.5732 | 0.4481 | 0.5732 | 0.7571 |
|
| 96 |
+
| No log | 0.9091 | 90 | 0.5485 | 0.5585 | 0.5485 | 0.7406 |
|
| 97 |
+
| No log | 0.9293 | 92 | 0.4730 | 0.5883 | 0.4730 | 0.6877 |
|
| 98 |
+
| No log | 0.9495 | 94 | 0.4443 | 0.6155 | 0.4443 | 0.6666 |
|
| 99 |
+
| No log | 0.9697 | 96 | 0.4999 | 0.6115 | 0.4999 | 0.7071 |
|
| 100 |
+
| No log | 0.9899 | 98 | 0.4884 | 0.6075 | 0.4884 | 0.6988 |
|
| 101 |
+
| No log | 1.0101 | 100 | 0.5933 | 0.5814 | 0.5933 | 0.7703 |
|
| 102 |
+
| No log | 1.0303 | 102 | 0.6671 | 0.5429 | 0.6671 | 0.8167 |
|
| 103 |
+
| No log | 1.0505 | 104 | 0.6513 | 0.5636 | 0.6513 | 0.8070 |
|
| 104 |
+
| No log | 1.0707 | 106 | 0.5374 | 0.5934 | 0.5374 | 0.7331 |
|
| 105 |
+
| No log | 1.0909 | 108 | 0.5365 | 0.5972 | 0.5365 | 0.7325 |
|
| 106 |
+
| No log | 1.1111 | 110 | 0.5230 | 0.5371 | 0.5230 | 0.7232 |
|
| 107 |
+
| No log | 1.1313 | 112 | 0.5504 | 0.4835 | 0.5504 | 0.7419 |
|
| 108 |
+
| No log | 1.1515 | 114 | 0.5192 | 0.4909 | 0.5192 | 0.7205 |
|
| 109 |
+
| No log | 1.1717 | 116 | 0.5146 | 0.5294 | 0.5146 | 0.7173 |
|
| 110 |
+
| No log | 1.1919 | 118 | 0.4893 | 0.5260 | 0.4893 | 0.6995 |
|
| 111 |
+
| No log | 1.2121 | 120 | 0.4794 | 0.5402 | 0.4794 | 0.6924 |
|
| 112 |
+
| No log | 1.2323 | 122 | 0.4597 | 0.5205 | 0.4597 | 0.6780 |
|
| 113 |
+
| No log | 1.2525 | 124 | 0.4893 | 0.5129 | 0.4893 | 0.6995 |
|
| 114 |
+
| No log | 1.2727 | 126 | 0.5888 | 0.4181 | 0.5888 | 0.7673 |
|
| 115 |
+
| No log | 1.2929 | 128 | 0.5927 | 0.3581 | 0.5927 | 0.7698 |
|
| 116 |
+
| No log | 1.3131 | 130 | 0.5709 | 0.3834 | 0.5709 | 0.7556 |
|
| 117 |
+
| No log | 1.3333 | 132 | 0.5217 | 0.4659 | 0.5217 | 0.7223 |
|
| 118 |
+
| No log | 1.3535 | 134 | 0.4838 | 0.5322 | 0.4838 | 0.6956 |
|
| 119 |
+
| No log | 1.3737 | 136 | 0.5128 | 0.5551 | 0.5128 | 0.7161 |
|
| 120 |
+
| No log | 1.3939 | 138 | 0.6273 | 0.5480 | 0.6273 | 0.7920 |
|
| 121 |
+
| No log | 1.4141 | 140 | 0.6923 | 0.5571 | 0.6923 | 0.8321 |
|
| 122 |
+
| No log | 1.4343 | 142 | 0.6351 | 0.5576 | 0.6351 | 0.7969 |
|
| 123 |
+
| No log | 1.4545 | 144 | 0.6667 | 0.5239 | 0.6667 | 0.8165 |
|
| 124 |
+
| No log | 1.4747 | 146 | 0.7168 | 0.4242 | 0.7168 | 0.8466 |
|
| 125 |
+
| No log | 1.4949 | 148 | 0.6381 | 0.4236 | 0.6381 | 0.7988 |
|
| 126 |
+
| No log | 1.5152 | 150 | 0.6385 | 0.3783 | 0.6385 | 0.7991 |
|
| 127 |
+
| No log | 1.5354 | 152 | 0.6551 | 0.3322 | 0.6551 | 0.8094 |
|
| 128 |
+
| No log | 1.5556 | 154 | 0.6203 | 0.3688 | 0.6203 | 0.7876 |
|
| 129 |
+
| No log | 1.5758 | 156 | 0.5377 | 0.4622 | 0.5377 | 0.7333 |
|
| 130 |
+
| No log | 1.5960 | 158 | 0.6562 | 0.5153 | 0.6562 | 0.8101 |
|
| 131 |
+
| No log | 1.6162 | 160 | 0.9157 | 0.4221 | 0.9157 | 0.9569 |
|
| 132 |
+
| No log | 1.6364 | 162 | 0.9608 | 0.4583 | 0.9608 | 0.9802 |
|
| 133 |
+
| No log | 1.6566 | 164 | 1.0409 | 0.4389 | 1.0409 | 1.0203 |
|
| 134 |
+
| No log | 1.6768 | 166 | 0.9013 | 0.4864 | 0.9013 | 0.9494 |
|
| 135 |
+
| No log | 1.6970 | 168 | 0.6828 | 0.5692 | 0.6828 | 0.8263 |
|
| 136 |
+
| No log | 1.7172 | 170 | 0.5449 | 0.5895 | 0.5449 | 0.7382 |
|
| 137 |
+
| No log | 1.7374 | 172 | 0.5228 | 0.5939 | 0.5228 | 0.7231 |
|
| 138 |
+
| No log | 1.7576 | 174 | 0.4980 | 0.5880 | 0.4980 | 0.7057 |
|
| 139 |
+
| No log | 1.7778 | 176 | 0.4385 | 0.5636 | 0.4385 | 0.6622 |
|
| 140 |
+
| No log | 1.7980 | 178 | 0.4946 | 0.4494 | 0.4946 | 0.7033 |
|
| 141 |
+
| No log | 1.8182 | 180 | 0.7067 | 0.2774 | 0.7067 | 0.8406 |
|
| 142 |
+
| No log | 1.8384 | 182 | 0.9071 | 0.1782 | 0.9071 | 0.9524 |
|
| 143 |
+
| No log | 1.8586 | 184 | 0.9211 | 0.1128 | 0.9211 | 0.9597 |
|
| 144 |
+
| No log | 1.8788 | 186 | 0.8185 | 0.0547 | 0.8185 | 0.9047 |
|
| 145 |
+
| No log | 1.8990 | 188 | 0.6726 | 0.1653 | 0.6726 | 0.8201 |
|
| 146 |
+
| No log | 1.9192 | 190 | 0.5304 | 0.3613 | 0.5304 | 0.7283 |
|
| 147 |
+
| No log | 1.9394 | 192 | 0.4775 | 0.5232 | 0.4775 | 0.6910 |
|
| 148 |
+
| No log | 1.9596 | 194 | 0.6332 | 0.3338 | 0.6332 | 0.7957 |
|
| 149 |
+
| No log | 1.9798 | 196 | 0.7073 | 0.2729 | 0.7073 | 0.8410 |
|
| 150 |
+
| No log | 2.0 | 198 | 0.6526 | 0.3217 | 0.6526 | 0.8078 |
|
| 151 |
+
| No log | 2.0202 | 200 | 0.5171 | 0.4965 | 0.5171 | 0.7191 |
|
| 152 |
+
| No log | 2.0404 | 202 | 0.4123 | 0.6020 | 0.4123 | 0.6421 |
|
| 153 |
+
| No log | 2.0606 | 204 | 0.4445 | 0.4542 | 0.4445 | 0.6667 |
|
| 154 |
+
| No log | 2.0808 | 206 | 0.5704 | 0.4695 | 0.5704 | 0.7553 |
|
| 155 |
+
| No log | 2.1010 | 208 | 0.7118 | 0.4495 | 0.7118 | 0.8437 |
|
| 156 |
+
| No log | 2.1212 | 210 | 0.7145 | 0.4902 | 0.7145 | 0.8453 |
|
| 157 |
+
| No log | 2.1414 | 212 | 0.5935 | 0.6089 | 0.5935 | 0.7704 |
|
| 158 |
+
| No log | 2.1616 | 214 | 0.5078 | 0.6403 | 0.5078 | 0.7126 |
|
| 159 |
+
| No log | 2.1818 | 216 | 0.5159 | 0.6563 | 0.5159 | 0.7182 |
|
| 160 |
+
| No log | 2.2020 | 218 | 0.4520 | 0.6339 | 0.4520 | 0.6723 |
|
| 161 |
+
| No log | 2.2222 | 220 | 0.4077 | 0.6269 | 0.4077 | 0.6385 |
|
| 162 |
+
| No log | 2.2424 | 222 | 0.4984 | 0.5571 | 0.4984 | 0.7060 |
|
| 163 |
+
| No log | 2.2626 | 224 | 0.5830 | 0.4955 | 0.5830 | 0.7635 |
|
| 164 |
+
| No log | 2.2828 | 226 | 0.5514 | 0.4611 | 0.5514 | 0.7425 |
|
| 165 |
+
| No log | 2.3030 | 228 | 0.5456 | 0.4514 | 0.5456 | 0.7387 |
|
| 166 |
+
| No log | 2.3232 | 230 | 0.4845 | 0.5259 | 0.4845 | 0.6961 |
|
| 167 |
+
| No log | 2.3434 | 232 | 0.4351 | 0.5211 | 0.4351 | 0.6596 |
|
| 168 |
+
| No log | 2.3636 | 234 | 0.4361 | 0.5370 | 0.4361 | 0.6604 |
|
| 169 |
+
| No log | 2.3838 | 236 | 0.4190 | 0.5777 | 0.4190 | 0.6473 |
|
| 170 |
+
| No log | 2.4040 | 238 | 0.4437 | 0.5362 | 0.4437 | 0.6661 |
|
| 171 |
+
| No log | 2.4242 | 240 | 0.5630 | 0.5341 | 0.5630 | 0.7503 |
|
| 172 |
+
| No log | 2.4444 | 242 | 0.6251 | 0.5162 | 0.6251 | 0.7906 |
|
| 173 |
+
| No log | 2.4646 | 244 | 0.6731 | 0.5253 | 0.6731 | 0.8204 |
|
| 174 |
+
| No log | 2.4848 | 246 | 0.5797 | 0.5555 | 0.5797 | 0.7614 |
|
| 175 |
+
| No log | 2.5051 | 248 | 0.4386 | 0.6368 | 0.4386 | 0.6622 |
|
| 176 |
+
| No log | 2.5253 | 250 | 0.4205 | 0.6658 | 0.4205 | 0.6484 |
|
| 177 |
+
| No log | 2.5455 | 252 | 0.4122 | 0.6556 | 0.4122 | 0.6420 |
|
| 178 |
+
| No log | 2.5657 | 254 | 0.4206 | 0.6222 | 0.4206 | 0.6486 |
|
| 179 |
+
| No log | 2.5859 | 256 | 0.5747 | 0.5804 | 0.5747 | 0.7581 |
|
| 180 |
+
| No log | 2.6061 | 258 | 0.7764 | 0.4642 | 0.7764 | 0.8811 |
|
| 181 |
+
| No log | 2.6263 | 260 | 0.7382 | 0.4742 | 0.7382 | 0.8592 |
|
| 182 |
+
| No log | 2.6465 | 262 | 0.5983 | 0.4951 | 0.5983 | 0.7735 |
|
| 183 |
+
| No log | 2.6667 | 264 | 0.4368 | 0.5626 | 0.4368 | 0.6609 |
|
| 184 |
+
| No log | 2.6869 | 266 | 0.4332 | 0.5797 | 0.4332 | 0.6582 |
|
| 185 |
+
| No log | 2.7071 | 268 | 0.4273 | 0.5756 | 0.4273 | 0.6537 |
|
| 186 |
+
| No log | 2.7273 | 270 | 0.5086 | 0.5001 | 0.5086 | 0.7132 |
|
| 187 |
+
| No log | 2.7475 | 272 | 0.5652 | 0.4814 | 0.5652 | 0.7518 |
|
| 188 |
+
| No log | 2.7677 | 274 | 0.5486 | 0.4847 | 0.5486 | 0.7407 |
|
| 189 |
+
| No log | 2.7879 | 276 | 0.4850 | 0.5055 | 0.4850 | 0.6964 |
|
| 190 |
+
| No log | 2.8081 | 278 | 0.4041 | 0.6093 | 0.4041 | 0.6357 |
|
| 191 |
+
| No log | 2.8283 | 280 | 0.3914 | 0.6175 | 0.3914 | 0.6257 |
|
| 192 |
+
| No log | 2.8485 | 282 | 0.3953 | 0.6292 | 0.3953 | 0.6287 |
|
| 193 |
+
| No log | 2.8687 | 284 | 0.5139 | 0.5607 | 0.5139 | 0.7169 |
|
| 194 |
+
| No log | 2.8889 | 286 | 0.6306 | 0.5397 | 0.6306 | 0.7941 |
|
| 195 |
+
| No log | 2.9091 | 288 | 0.6704 | 0.5437 | 0.6704 | 0.8188 |
|
| 196 |
+
| No log | 2.9293 | 290 | 0.6487 | 0.5360 | 0.6487 | 0.8054 |
|
| 197 |
+
| No log | 2.9495 | 292 | 0.5224 | 0.5928 | 0.5224 | 0.7228 |
|
| 198 |
+
| No log | 2.9697 | 294 | 0.4781 | 0.6161 | 0.4781 | 0.6915 |
|
| 199 |
+
| No log | 2.9899 | 296 | 0.5448 | 0.5328 | 0.5448 | 0.7381 |
|
| 200 |
+
| No log | 3.0101 | 298 | 0.5716 | 0.4956 | 0.5716 | 0.7561 |
|
| 201 |
+
| No log | 3.0303 | 300 | 0.5130 | 0.4976 | 0.5130 | 0.7163 |
|
| 202 |
+
| No log | 3.0505 | 302 | 0.5222 | 0.4777 | 0.5222 | 0.7226 |
|
| 203 |
+
| No log | 3.0707 | 304 | 0.5823 | 0.4544 | 0.5823 | 0.7631 |
|
| 204 |
+
| No log | 3.0909 | 306 | 0.5318 | 0.5025 | 0.5318 | 0.7293 |
|
| 205 |
+
| No log | 3.1111 | 308 | 0.4175 | 0.5744 | 0.4175 | 0.6461 |
|
| 206 |
+
| No log | 3.1313 | 310 | 0.3828 | 0.5991 | 0.3828 | 0.6187 |
|
| 207 |
+
| No log | 3.1515 | 312 | 0.3858 | 0.6115 | 0.3858 | 0.6212 |
|
| 208 |
+
| No log | 3.1717 | 314 | 0.3837 | 0.6326 | 0.3837 | 0.6194 |
|
| 209 |
+
| No log | 3.1919 | 316 | 0.3843 | 0.6532 | 0.3843 | 0.6199 |
|
| 210 |
+
| No log | 3.2121 | 318 | 0.4211 | 0.5706 | 0.4211 | 0.6489 |
|
| 211 |
+
| No log | 3.2323 | 320 | 0.6338 | 0.5258 | 0.6338 | 0.7961 |
|
| 212 |
+
| No log | 3.2525 | 322 | 0.7523 | 0.4875 | 0.7523 | 0.8673 |
|
| 213 |
+
| No log | 3.2727 | 324 | 0.6793 | 0.4836 | 0.6793 | 0.8242 |
|
| 214 |
+
| No log | 3.2929 | 326 | 0.5077 | 0.5505 | 0.5077 | 0.7125 |
|
| 215 |
+
| No log | 3.3131 | 328 | 0.4411 | 0.5805 | 0.4411 | 0.6641 |
|
| 216 |
+
| No log | 3.3333 | 330 | 0.4461 | 0.5620 | 0.4461 | 0.6679 |
|
| 217 |
+
| No log | 3.3535 | 332 | 0.4497 | 0.5484 | 0.4497 | 0.6706 |
|
| 218 |
+
| No log | 3.3737 | 334 | 0.5390 | 0.5454 | 0.5390 | 0.7342 |
|
| 219 |
+
| No log | 3.3939 | 336 | 0.6627 | 0.5445 | 0.6627 | 0.8141 |
|
| 220 |
+
| No log | 3.4141 | 338 | 0.6997 | 0.5645 | 0.6997 | 0.8365 |
|
| 221 |
+
| No log | 3.4343 | 340 | 0.6324 | 0.5804 | 0.6324 | 0.7952 |
|
| 222 |
+
| No log | 3.4545 | 342 | 0.5730 | 0.6036 | 0.5730 | 0.7570 |
|
| 223 |
+
| No log | 3.4747 | 344 | 0.5281 | 0.6255 | 0.5281 | 0.7267 |
|
| 224 |
+
| No log | 3.4949 | 346 | 0.4826 | 0.6587 | 0.4826 | 0.6947 |
|
| 225 |
+
| No log | 3.5152 | 348 | 0.4558 | 0.6407 | 0.4558 | 0.6751 |
|
| 226 |
+
| No log | 3.5354 | 350 | 0.5483 | 0.5802 | 0.5483 | 0.7405 |
|
| 227 |
+
| No log | 3.5556 | 352 | 0.7012 | 0.5439 | 0.7012 | 0.8374 |
|
| 228 |
+
| No log | 3.5758 | 354 | 0.6683 | 0.5453 | 0.6683 | 0.8175 |
|
| 229 |
+
| No log | 3.5960 | 356 | 0.5045 | 0.5776 | 0.5045 | 0.7103 |
|
| 230 |
+
| No log | 3.6162 | 358 | 0.4279 | 0.5968 | 0.4279 | 0.6541 |
|
| 231 |
+
| No log | 3.6364 | 360 | 0.4173 | 0.5779 | 0.4173 | 0.6460 |
|
| 232 |
+
| No log | 3.6566 | 362 | 0.5126 | 0.5916 | 0.5126 | 0.7160 |
|
| 233 |
+
| No log | 3.6768 | 364 | 0.7432 | 0.5070 | 0.7432 | 0.8621 |
|
| 234 |
+
| No log | 3.6970 | 366 | 0.7413 | 0.5142 | 0.7413 | 0.8610 |
|
| 235 |
+
| No log | 3.7172 | 368 | 0.5595 | 0.5376 | 0.5595 | 0.7480 |
|
| 236 |
+
| No log | 3.7374 | 370 | 0.4554 | 0.5365 | 0.4554 | 0.6748 |
|
| 237 |
+
| No log | 3.7576 | 372 | 0.4155 | 0.5693 | 0.4155 | 0.6446 |
|
| 238 |
+
| No log | 3.7778 | 374 | 0.4052 | 0.6221 | 0.4052 | 0.6365 |
|
| 239 |
+
| No log | 3.7980 | 376 | 0.3938 | 0.6386 | 0.3938 | 0.6275 |
|
| 240 |
+
| No log | 3.8182 | 378 | 0.3988 | 0.6046 | 0.3988 | 0.6315 |
|
| 241 |
+
| No log | 3.8384 | 380 | 0.5153 | 0.5774 | 0.5153 | 0.7179 |
|
| 242 |
+
| No log | 3.8586 | 382 | 0.6085 | 0.5489 | 0.6085 | 0.7801 |
|
| 243 |
+
| No log | 3.8788 | 384 | 0.7164 | 0.5411 | 0.7164 | 0.8464 |
|
| 244 |
+
| No log | 3.8990 | 386 | 0.6803 | 0.5186 | 0.6803 | 0.8248 |
|
| 245 |
+
| No log | 3.9192 | 388 | 0.6235 | 0.5188 | 0.6235 | 0.7896 |
|
| 246 |
+
| No log | 3.9394 | 390 | 0.5010 | 0.5640 | 0.5010 | 0.7078 |
|
| 247 |
+
| No log | 3.9596 | 392 | 0.4012 | 0.6279 | 0.4012 | 0.6334 |
|
| 248 |
+
| No log | 3.9798 | 394 | 0.4024 | 0.6738 | 0.4024 | 0.6343 |
|
| 249 |
+
| No log | 4.0 | 396 | 0.3957 | 0.6689 | 0.3957 | 0.6291 |
|
| 250 |
+
| No log | 4.0202 | 398 | 0.3937 | 0.6219 | 0.3937 | 0.6275 |
|
| 251 |
+
| No log | 4.0404 | 400 | 0.4746 | 0.5574 | 0.4746 | 0.6889 |
|
| 252 |
+
| No log | 4.0606 | 402 | 0.5537 | 0.5130 | 0.5537 | 0.7441 |
|
| 253 |
+
| No log | 4.0808 | 404 | 0.5097 | 0.5569 | 0.5097 | 0.7139 |
|
| 254 |
+
| No log | 4.1010 | 406 | 0.4290 | 0.6113 | 0.4290 | 0.6550 |
|
| 255 |
+
| No log | 4.1212 | 408 | 0.4468 | 0.6207 | 0.4468 | 0.6684 |
|
| 256 |
+
| No log | 4.1414 | 410 | 0.5683 | 0.5570 | 0.5683 | 0.7538 |
|
| 257 |
+
| No log | 4.1616 | 412 | 0.6967 | 0.5373 | 0.6967 | 0.8347 |
|
| 258 |
+
| No log | 4.1818 | 414 | 0.6549 | 0.5198 | 0.6549 | 0.8093 |
|
| 259 |
+
| No log | 4.2020 | 416 | 0.5890 | 0.5640 | 0.5890 | 0.7675 |
|
| 260 |
+
| No log | 4.2222 | 418 | 0.5093 | 0.5807 | 0.5093 | 0.7136 |
|
| 261 |
+
| No log | 4.2424 | 420 | 0.4590 | 0.6166 | 0.4590 | 0.6775 |
|
| 262 |
+
| No log | 4.2626 | 422 | 0.4381 | 0.6547 | 0.4381 | 0.6619 |
|
| 263 |
+
| No log | 4.2828 | 424 | 0.4865 | 0.6325 | 0.4865 | 0.6975 |
|
| 264 |
+
| No log | 4.3030 | 426 | 0.7020 | 0.5403 | 0.7020 | 0.8378 |
|
| 265 |
+
| No log | 4.3232 | 428 | 0.8226 | 0.4940 | 0.8226 | 0.9070 |
|
| 266 |
+
| No log | 4.3434 | 430 | 0.7989 | 0.5047 | 0.7989 | 0.8938 |
|
| 267 |
+
| No log | 4.3636 | 432 | 0.6589 | 0.5190 | 0.6589 | 0.8117 |
|
| 268 |
+
| No log | 4.3838 | 434 | 0.5398 | 0.5569 | 0.5398 | 0.7347 |
|
| 269 |
+
| No log | 4.4040 | 436 | 0.4987 | 0.5374 | 0.4987 | 0.7062 |
|
| 270 |
+
| No log | 4.4242 | 438 | 0.5602 | 0.5124 | 0.5602 | 0.7485 |
|
| 271 |
+
| No log | 4.4444 | 440 | 0.6644 | 0.4928 | 0.6644 | 0.8151 |
|
| 272 |
+
| No log | 4.4646 | 442 | 0.6825 | 0.4928 | 0.6825 | 0.8261 |
|
| 273 |
+
| No log | 4.4848 | 444 | 0.5385 | 0.5496 | 0.5385 | 0.7338 |
|
| 274 |
+
| No log | 4.5051 | 446 | 0.4161 | 0.6074 | 0.4161 | 0.6451 |
|
| 275 |
+
| No log | 4.5253 | 448 | 0.4540 | 0.6028 | 0.4540 | 0.6738 |
|
| 276 |
+
| No log | 4.5455 | 450 | 0.4453 | 0.5870 | 0.4453 | 0.6673 |
|
| 277 |
+
| No log | 4.5657 | 452 | 0.4186 | 0.5888 | 0.4186 | 0.6470 |
|
| 278 |
+
| No log | 4.5859 | 454 | 0.5353 | 0.4886 | 0.5353 | 0.7317 |
|
| 279 |
+
| No log | 4.6061 | 456 | 0.6863 | 0.4699 | 0.6863 | 0.8284 |
|
| 280 |
+
| No log | 4.6263 | 458 | 0.7319 | 0.4628 | 0.7319 | 0.8555 |
|
| 281 |
+
| No log | 4.6465 | 460 | 0.6445 | 0.4558 | 0.6445 | 0.8028 |
|
| 282 |
+
| No log | 4.6667 | 462 | 0.4903 | 0.4908 | 0.4903 | 0.7002 |
|
| 283 |
+
| No log | 4.6869 | 464 | 0.4119 | 0.5848 | 0.4119 | 0.6418 |
|
| 284 |
+
| No log | 4.7071 | 466 | 0.4092 | 0.6340 | 0.4092 | 0.6397 |
|
| 285 |
+
| No log | 4.7273 | 468 | 0.4545 | 0.6240 | 0.4545 | 0.6741 |
|
| 286 |
+
| No log | 4.7475 | 470 | 0.5332 | 0.6392 | 0.5332 | 0.7302 |
|
| 287 |
+
| No log | 4.7677 | 472 | 0.6801 | 0.5491 | 0.6801 | 0.8247 |
|
| 288 |
+
| No log | 4.7879 | 474 | 0.7551 | 0.5393 | 0.7551 | 0.8689 |
|
| 289 |
+
| No log | 4.8081 | 476 | 0.6357 | 0.5539 | 0.6357 | 0.7973 |
|
| 290 |
+
| No log | 4.8283 | 478 | 0.4466 | 0.6553 | 0.4466 | 0.6683 |
|
| 291 |
+
| No log | 4.8485 | 480 | 0.4200 | 0.6928 | 0.4200 | 0.6481 |
|
| 292 |
+
| No log | 4.8687 | 482 | 0.4107 | 0.6719 | 0.4107 | 0.6408 |
|
| 293 |
+
| No log | 4.8889 | 484 | 0.4465 | 0.6082 | 0.4465 | 0.6682 |
|
| 294 |
+
| No log | 4.9091 | 486 | 0.6184 | 0.5220 | 0.6184 | 0.7864 |
|
| 295 |
+
| No log | 4.9293 | 488 | 0.7473 | 0.4747 | 0.7473 | 0.8645 |
|
| 296 |
+
| No log | 4.9495 | 490 | 0.7110 | 0.4797 | 0.7110 | 0.8432 |
|
| 297 |
+
| No log | 4.9697 | 492 | 0.7197 | 0.4793 | 0.7197 | 0.8483 |
|
| 298 |
+
| No log | 4.9899 | 494 | 0.7183 | 0.4885 | 0.7183 | 0.8475 |
|
| 299 |
+
| No log | 5.0101 | 496 | 0.5559 | 0.5454 | 0.5559 | 0.7456 |
|
| 300 |
+
| No log | 5.0303 | 498 | 0.4500 | 0.6346 | 0.4500 | 0.6708 |
|
| 301 |
+
| 0.4984 | 5.0505 | 500 | 0.4457 | 0.6332 | 0.4457 | 0.6676 |
|
| 302 |
+
| 0.4984 | 5.0707 | 502 | 0.5039 | 0.6049 | 0.5039 | 0.7099 |
|
| 303 |
+
| 0.4984 | 5.0909 | 504 | 0.6075 | 0.5791 | 0.6075 | 0.7794 |
|
| 304 |
+
| 0.4984 | 5.1111 | 506 | 0.7540 | 0.5272 | 0.7540 | 0.8684 |
|
| 305 |
+
| 0.4984 | 5.1313 | 508 | 0.6913 | 0.5311 | 0.6913 | 0.8314 |
|
| 306 |
+
| 0.4984 | 5.1515 | 510 | 0.5806 | 0.5631 | 0.5806 | 0.7620 |
|
| 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:aa28aef4390dd35371cf47d8dedea2cd3e563691b11452f052b568d6e02b57eb
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f35868342fc9865aa681717ec205d51a4a07583d409f19c9a978d299132485df
|
| 3 |
+
size 5240
|