Training in progress, step 500
Browse files- README.md +331 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_TestTask1_vocabulary
|
| 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_TestTask1_vocabulary
|
| 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: 0.6377
|
| 19 |
+
- Qwk: 0.6434
|
| 20 |
+
- Mse: 0.6377
|
| 21 |
+
- Rmse: 0.7986
|
| 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 | 0.0213 | 2 | 4.7716 | 0.0061 | 4.7716 | 2.1844 |
|
| 53 |
+
| No log | 0.0426 | 4 | 3.4176 | 0.0642 | 3.4176 | 1.8487 |
|
| 54 |
+
| No log | 0.0638 | 6 | 1.7463 | 0.0613 | 1.7463 | 1.3215 |
|
| 55 |
+
| No log | 0.0851 | 8 | 1.0577 | 0.1272 | 1.0577 | 1.0285 |
|
| 56 |
+
| No log | 0.1064 | 10 | 0.8767 | 0.0681 | 0.8767 | 0.9363 |
|
| 57 |
+
| No log | 0.1277 | 12 | 0.8856 | 0.0163 | 0.8856 | 0.9410 |
|
| 58 |
+
| No log | 0.1489 | 14 | 0.8603 | 0.1925 | 0.8603 | 0.9275 |
|
| 59 |
+
| No log | 0.1702 | 16 | 0.7581 | 0.2550 | 0.7581 | 0.8707 |
|
| 60 |
+
| No log | 0.1915 | 18 | 0.7899 | 0.2904 | 0.7899 | 0.8888 |
|
| 61 |
+
| No log | 0.2128 | 20 | 0.7188 | 0.2600 | 0.7188 | 0.8478 |
|
| 62 |
+
| No log | 0.2340 | 22 | 0.6563 | 0.3695 | 0.6563 | 0.8101 |
|
| 63 |
+
| No log | 0.2553 | 24 | 0.6800 | 0.4289 | 0.6800 | 0.8246 |
|
| 64 |
+
| No log | 0.2766 | 26 | 0.6434 | 0.4623 | 0.6434 | 0.8021 |
|
| 65 |
+
| No log | 0.2979 | 28 | 0.5992 | 0.4024 | 0.5992 | 0.7741 |
|
| 66 |
+
| No log | 0.3191 | 30 | 0.6116 | 0.3470 | 0.6116 | 0.7820 |
|
| 67 |
+
| No log | 0.3404 | 32 | 0.6149 | 0.3969 | 0.6149 | 0.7842 |
|
| 68 |
+
| No log | 0.3617 | 34 | 0.5521 | 0.4691 | 0.5521 | 0.7430 |
|
| 69 |
+
| No log | 0.3830 | 36 | 0.6994 | 0.4862 | 0.6994 | 0.8363 |
|
| 70 |
+
| No log | 0.4043 | 38 | 0.7922 | 0.5029 | 0.7922 | 0.8901 |
|
| 71 |
+
| No log | 0.4255 | 40 | 0.6624 | 0.5139 | 0.6624 | 0.8139 |
|
| 72 |
+
| No log | 0.4468 | 42 | 0.5370 | 0.5638 | 0.5370 | 0.7328 |
|
| 73 |
+
| No log | 0.4681 | 44 | 0.5833 | 0.5196 | 0.5833 | 0.7638 |
|
| 74 |
+
| No log | 0.4894 | 46 | 0.6491 | 0.4356 | 0.6491 | 0.8056 |
|
| 75 |
+
| No log | 0.5106 | 48 | 0.6396 | 0.4795 | 0.6396 | 0.7998 |
|
| 76 |
+
| No log | 0.5319 | 50 | 0.5493 | 0.5539 | 0.5493 | 0.7411 |
|
| 77 |
+
| No log | 0.5532 | 52 | 0.5610 | 0.6330 | 0.5610 | 0.7490 |
|
| 78 |
+
| No log | 0.5745 | 54 | 0.5613 | 0.5191 | 0.5613 | 0.7492 |
|
| 79 |
+
| No log | 0.5957 | 56 | 0.5956 | 0.4969 | 0.5956 | 0.7718 |
|
| 80 |
+
| No log | 0.6170 | 58 | 0.6653 | 0.4589 | 0.6653 | 0.8157 |
|
| 81 |
+
| No log | 0.6383 | 60 | 0.6855 | 0.4498 | 0.6855 | 0.8280 |
|
| 82 |
+
| No log | 0.6596 | 62 | 0.7015 | 0.4511 | 0.7015 | 0.8375 |
|
| 83 |
+
| No log | 0.6809 | 64 | 0.6243 | 0.4537 | 0.6243 | 0.7901 |
|
| 84 |
+
| No log | 0.7021 | 66 | 0.5675 | 0.5476 | 0.5675 | 0.7533 |
|
| 85 |
+
| No log | 0.7234 | 68 | 0.5642 | 0.5976 | 0.5642 | 0.7511 |
|
| 86 |
+
| No log | 0.7447 | 70 | 0.5920 | 0.6045 | 0.5920 | 0.7694 |
|
| 87 |
+
| No log | 0.7660 | 72 | 0.5988 | 0.5822 | 0.5988 | 0.7738 |
|
| 88 |
+
| No log | 0.7872 | 74 | 0.6028 | 0.5872 | 0.6028 | 0.7764 |
|
| 89 |
+
| No log | 0.8085 | 76 | 0.5218 | 0.5139 | 0.5218 | 0.7224 |
|
| 90 |
+
| No log | 0.8298 | 78 | 0.5210 | 0.5310 | 0.5210 | 0.7218 |
|
| 91 |
+
| No log | 0.8511 | 80 | 0.5217 | 0.4901 | 0.5217 | 0.7223 |
|
| 92 |
+
| No log | 0.8723 | 82 | 0.5189 | 0.4856 | 0.5189 | 0.7203 |
|
| 93 |
+
| No log | 0.8936 | 84 | 0.6043 | 0.4811 | 0.6043 | 0.7774 |
|
| 94 |
+
| No log | 0.9149 | 86 | 0.7216 | 0.4858 | 0.7216 | 0.8495 |
|
| 95 |
+
| No log | 0.9362 | 88 | 0.6549 | 0.5043 | 0.6549 | 0.8093 |
|
| 96 |
+
| No log | 0.9574 | 90 | 0.5761 | 0.5735 | 0.5761 | 0.7590 |
|
| 97 |
+
| No log | 0.9787 | 92 | 0.5426 | 0.5965 | 0.5426 | 0.7366 |
|
| 98 |
+
| No log | 1.0 | 94 | 0.5143 | 0.5733 | 0.5143 | 0.7172 |
|
| 99 |
+
| No log | 1.0213 | 96 | 0.5158 | 0.6104 | 0.5158 | 0.7182 |
|
| 100 |
+
| No log | 1.0426 | 98 | 0.5344 | 0.5831 | 0.5344 | 0.7310 |
|
| 101 |
+
| No log | 1.0638 | 100 | 0.5019 | 0.5828 | 0.5019 | 0.7084 |
|
| 102 |
+
| No log | 1.0851 | 102 | 0.4923 | 0.5992 | 0.4923 | 0.7017 |
|
| 103 |
+
| No log | 1.1064 | 104 | 0.5280 | 0.5581 | 0.5280 | 0.7266 |
|
| 104 |
+
| No log | 1.1277 | 106 | 0.6018 | 0.4617 | 0.6018 | 0.7758 |
|
| 105 |
+
| No log | 1.1489 | 108 | 0.6414 | 0.4221 | 0.6414 | 0.8009 |
|
| 106 |
+
| No log | 1.1702 | 110 | 0.6469 | 0.4570 | 0.6469 | 0.8043 |
|
| 107 |
+
| No log | 1.1915 | 112 | 0.5485 | 0.5323 | 0.5485 | 0.7406 |
|
| 108 |
+
| No log | 1.2128 | 114 | 0.5689 | 0.5935 | 0.5689 | 0.7543 |
|
| 109 |
+
| No log | 1.2340 | 116 | 0.5362 | 0.6423 | 0.5362 | 0.7322 |
|
| 110 |
+
| No log | 1.2553 | 118 | 0.5473 | 0.5671 | 0.5473 | 0.7398 |
|
| 111 |
+
| No log | 1.2766 | 120 | 0.7222 | 0.4384 | 0.7222 | 0.8498 |
|
| 112 |
+
| No log | 1.2979 | 122 | 0.7842 | 0.3728 | 0.7842 | 0.8856 |
|
| 113 |
+
| No log | 1.3191 | 124 | 0.6842 | 0.4401 | 0.6842 | 0.8272 |
|
| 114 |
+
| No log | 1.3404 | 126 | 0.5328 | 0.5969 | 0.5328 | 0.7299 |
|
| 115 |
+
| No log | 1.3617 | 128 | 0.5080 | 0.6219 | 0.5080 | 0.7127 |
|
| 116 |
+
| No log | 1.3830 | 130 | 0.5044 | 0.6137 | 0.5044 | 0.7102 |
|
| 117 |
+
| No log | 1.4043 | 132 | 0.6019 | 0.5261 | 0.6019 | 0.7758 |
|
| 118 |
+
| No log | 1.4255 | 134 | 0.6758 | 0.4582 | 0.6758 | 0.8221 |
|
| 119 |
+
| No log | 1.4468 | 136 | 0.6587 | 0.4847 | 0.6587 | 0.8116 |
|
| 120 |
+
| No log | 1.4681 | 138 | 0.5721 | 0.4918 | 0.5721 | 0.7564 |
|
| 121 |
+
| No log | 1.4894 | 140 | 0.5246 | 0.5352 | 0.5246 | 0.7243 |
|
| 122 |
+
| No log | 1.5106 | 142 | 0.5141 | 0.5633 | 0.5141 | 0.7170 |
|
| 123 |
+
| No log | 1.5319 | 144 | 0.4976 | 0.5624 | 0.4976 | 0.7054 |
|
| 124 |
+
| No log | 1.5532 | 146 | 0.4759 | 0.5524 | 0.4759 | 0.6899 |
|
| 125 |
+
| No log | 1.5745 | 148 | 0.4959 | 0.5723 | 0.4959 | 0.7042 |
|
| 126 |
+
| No log | 1.5957 | 150 | 0.5241 | 0.5809 | 0.5241 | 0.7239 |
|
| 127 |
+
| No log | 1.6170 | 152 | 0.6275 | 0.5153 | 0.6275 | 0.7922 |
|
| 128 |
+
| No log | 1.6383 | 154 | 0.6568 | 0.5019 | 0.6568 | 0.8104 |
|
| 129 |
+
| No log | 1.6596 | 156 | 0.5710 | 0.5822 | 0.5710 | 0.7556 |
|
| 130 |
+
| No log | 1.6809 | 158 | 0.5898 | 0.6435 | 0.5898 | 0.7680 |
|
| 131 |
+
| No log | 1.7021 | 160 | 0.7633 | 0.5911 | 0.7633 | 0.8737 |
|
| 132 |
+
| No log | 1.7234 | 162 | 0.7968 | 0.5549 | 0.7968 | 0.8926 |
|
| 133 |
+
| No log | 1.7447 | 164 | 0.6056 | 0.5889 | 0.6056 | 0.7782 |
|
| 134 |
+
| No log | 1.7660 | 166 | 0.4716 | 0.6147 | 0.4716 | 0.6867 |
|
| 135 |
+
| No log | 1.7872 | 168 | 0.5585 | 0.4651 | 0.5585 | 0.7473 |
|
| 136 |
+
| No log | 1.8085 | 170 | 0.6903 | 0.3404 | 0.6903 | 0.8308 |
|
| 137 |
+
| No log | 1.8298 | 172 | 0.7039 | 0.3352 | 0.7039 | 0.8390 |
|
| 138 |
+
| No log | 1.8511 | 174 | 0.6382 | 0.4701 | 0.6382 | 0.7989 |
|
| 139 |
+
| No log | 1.8723 | 176 | 0.5344 | 0.5368 | 0.5344 | 0.7310 |
|
| 140 |
+
| No log | 1.8936 | 178 | 0.4968 | 0.5533 | 0.4968 | 0.7048 |
|
| 141 |
+
| No log | 1.9149 | 180 | 0.4936 | 0.5845 | 0.4936 | 0.7026 |
|
| 142 |
+
| No log | 1.9362 | 182 | 0.5393 | 0.6101 | 0.5393 | 0.7344 |
|
| 143 |
+
| No log | 1.9574 | 184 | 0.5899 | 0.5861 | 0.5899 | 0.7681 |
|
| 144 |
+
| No log | 1.9787 | 186 | 0.5855 | 0.6134 | 0.5855 | 0.7652 |
|
| 145 |
+
| No log | 2.0 | 188 | 0.5335 | 0.6314 | 0.5335 | 0.7304 |
|
| 146 |
+
| No log | 2.0213 | 190 | 0.5366 | 0.6201 | 0.5366 | 0.7325 |
|
| 147 |
+
| No log | 2.0426 | 192 | 0.5183 | 0.5672 | 0.5183 | 0.7199 |
|
| 148 |
+
| No log | 2.0638 | 194 | 0.5136 | 0.5783 | 0.5136 | 0.7166 |
|
| 149 |
+
| No log | 2.0851 | 196 | 0.5012 | 0.5835 | 0.5012 | 0.7080 |
|
| 150 |
+
| No log | 2.1064 | 198 | 0.4903 | 0.5846 | 0.4903 | 0.7002 |
|
| 151 |
+
| No log | 2.1277 | 200 | 0.5011 | 0.5795 | 0.5011 | 0.7079 |
|
| 152 |
+
| No log | 2.1489 | 202 | 0.4787 | 0.6120 | 0.4787 | 0.6919 |
|
| 153 |
+
| No log | 2.1702 | 204 | 0.4758 | 0.6155 | 0.4758 | 0.6898 |
|
| 154 |
+
| No log | 2.1915 | 206 | 0.4784 | 0.5994 | 0.4784 | 0.6917 |
|
| 155 |
+
| No log | 2.2128 | 208 | 0.4765 | 0.5642 | 0.4765 | 0.6903 |
|
| 156 |
+
| No log | 2.2340 | 210 | 0.4780 | 0.5461 | 0.4780 | 0.6914 |
|
| 157 |
+
| No log | 2.2553 | 212 | 0.4949 | 0.5748 | 0.4949 | 0.7035 |
|
| 158 |
+
| No log | 2.2766 | 214 | 0.4878 | 0.5223 | 0.4878 | 0.6984 |
|
| 159 |
+
| No log | 2.2979 | 216 | 0.4922 | 0.5546 | 0.4922 | 0.7016 |
|
| 160 |
+
| No log | 2.3191 | 218 | 0.4981 | 0.5928 | 0.4981 | 0.7057 |
|
| 161 |
+
| No log | 2.3404 | 220 | 0.5922 | 0.6073 | 0.5922 | 0.7695 |
|
| 162 |
+
| No log | 2.3617 | 222 | 0.6866 | 0.5840 | 0.6866 | 0.8286 |
|
| 163 |
+
| No log | 2.3830 | 224 | 0.6672 | 0.6017 | 0.6672 | 0.8168 |
|
| 164 |
+
| No log | 2.4043 | 226 | 0.6191 | 0.6104 | 0.6191 | 0.7868 |
|
| 165 |
+
| No log | 2.4255 | 228 | 0.6296 | 0.6115 | 0.6296 | 0.7935 |
|
| 166 |
+
| No log | 2.4468 | 230 | 0.6725 | 0.5196 | 0.6725 | 0.8201 |
|
| 167 |
+
| No log | 2.4681 | 232 | 0.6915 | 0.4334 | 0.6915 | 0.8316 |
|
| 168 |
+
| No log | 2.4894 | 234 | 0.6488 | 0.4212 | 0.6488 | 0.8055 |
|
| 169 |
+
| No log | 2.5106 | 236 | 0.5642 | 0.4620 | 0.5642 | 0.7511 |
|
| 170 |
+
| No log | 2.5319 | 238 | 0.5180 | 0.4945 | 0.5180 | 0.7197 |
|
| 171 |
+
| No log | 2.5532 | 240 | 0.5095 | 0.5406 | 0.5095 | 0.7138 |
|
| 172 |
+
| No log | 2.5745 | 242 | 0.5203 | 0.5520 | 0.5203 | 0.7213 |
|
| 173 |
+
| No log | 2.5957 | 244 | 0.5425 | 0.6137 | 0.5425 | 0.7366 |
|
| 174 |
+
| No log | 2.6170 | 246 | 0.5983 | 0.6209 | 0.5983 | 0.7735 |
|
| 175 |
+
| No log | 2.6383 | 248 | 0.6130 | 0.6065 | 0.6130 | 0.7829 |
|
| 176 |
+
| No log | 2.6596 | 250 | 0.5760 | 0.6206 | 0.5760 | 0.7590 |
|
| 177 |
+
| No log | 2.6809 | 252 | 0.5368 | 0.5982 | 0.5368 | 0.7326 |
|
| 178 |
+
| No log | 2.7021 | 254 | 0.5099 | 0.5644 | 0.5099 | 0.7141 |
|
| 179 |
+
| No log | 2.7234 | 256 | 0.4996 | 0.5601 | 0.4996 | 0.7068 |
|
| 180 |
+
| No log | 2.7447 | 258 | 0.4969 | 0.5458 | 0.4969 | 0.7049 |
|
| 181 |
+
| No log | 2.7660 | 260 | 0.5030 | 0.5160 | 0.5030 | 0.7092 |
|
| 182 |
+
| No log | 2.7872 | 262 | 0.5239 | 0.5190 | 0.5239 | 0.7238 |
|
| 183 |
+
| No log | 2.8085 | 264 | 0.5471 | 0.4927 | 0.5471 | 0.7396 |
|
| 184 |
+
| No log | 2.8298 | 266 | 0.5691 | 0.5584 | 0.5691 | 0.7544 |
|
| 185 |
+
| No log | 2.8511 | 268 | 0.5465 | 0.6024 | 0.5465 | 0.7392 |
|
| 186 |
+
| No log | 2.8723 | 270 | 0.5054 | 0.6450 | 0.5054 | 0.7109 |
|
| 187 |
+
| No log | 2.8936 | 272 | 0.5277 | 0.6269 | 0.5277 | 0.7264 |
|
| 188 |
+
| No log | 2.9149 | 274 | 0.5175 | 0.5816 | 0.5175 | 0.7193 |
|
| 189 |
+
| No log | 2.9362 | 276 | 0.4845 | 0.5675 | 0.4845 | 0.6960 |
|
| 190 |
+
| No log | 2.9574 | 278 | 0.4750 | 0.5561 | 0.4750 | 0.6892 |
|
| 191 |
+
| No log | 2.9787 | 280 | 0.5710 | 0.5066 | 0.5710 | 0.7557 |
|
| 192 |
+
| No log | 3.0 | 282 | 0.7884 | 0.4395 | 0.7884 | 0.8879 |
|
| 193 |
+
| No log | 3.0213 | 284 | 0.9016 | 0.3855 | 0.9016 | 0.9495 |
|
| 194 |
+
| No log | 3.0426 | 286 | 0.8320 | 0.4236 | 0.8320 | 0.9121 |
|
| 195 |
+
| No log | 3.0638 | 288 | 0.6560 | 0.5090 | 0.6560 | 0.8099 |
|
| 196 |
+
| No log | 3.0851 | 290 | 0.4908 | 0.6146 | 0.4908 | 0.7006 |
|
| 197 |
+
| No log | 3.1064 | 292 | 0.5060 | 0.6165 | 0.5060 | 0.7114 |
|
| 198 |
+
| No log | 3.1277 | 294 | 0.5082 | 0.5958 | 0.5082 | 0.7129 |
|
| 199 |
+
| No log | 3.1489 | 296 | 0.4775 | 0.6095 | 0.4775 | 0.6910 |
|
| 200 |
+
| No log | 3.1702 | 298 | 0.5017 | 0.6353 | 0.5017 | 0.7083 |
|
| 201 |
+
| No log | 3.1915 | 300 | 0.5844 | 0.6236 | 0.5844 | 0.7645 |
|
| 202 |
+
| No log | 3.2128 | 302 | 0.6292 | 0.6038 | 0.6292 | 0.7932 |
|
| 203 |
+
| No log | 3.2340 | 304 | 0.5900 | 0.6390 | 0.5900 | 0.7681 |
|
| 204 |
+
| No log | 3.2553 | 306 | 0.5435 | 0.6533 | 0.5435 | 0.7372 |
|
| 205 |
+
| No log | 3.2766 | 308 | 0.5075 | 0.6516 | 0.5075 | 0.7124 |
|
| 206 |
+
| No log | 3.2979 | 310 | 0.4728 | 0.6765 | 0.4728 | 0.6876 |
|
| 207 |
+
| No log | 3.3191 | 312 | 0.4638 | 0.5316 | 0.4638 | 0.6811 |
|
| 208 |
+
| No log | 3.3404 | 314 | 0.4794 | 0.5076 | 0.4794 | 0.6924 |
|
| 209 |
+
| No log | 3.3617 | 316 | 0.5126 | 0.5036 | 0.5126 | 0.7160 |
|
| 210 |
+
| No log | 3.3830 | 318 | 0.5378 | 0.5102 | 0.5378 | 0.7333 |
|
| 211 |
+
| No log | 3.4043 | 320 | 0.5123 | 0.5251 | 0.5123 | 0.7158 |
|
| 212 |
+
| No log | 3.4255 | 322 | 0.4869 | 0.6058 | 0.4869 | 0.6978 |
|
| 213 |
+
| No log | 3.4468 | 324 | 0.4952 | 0.6338 | 0.4952 | 0.7037 |
|
| 214 |
+
| No log | 3.4681 | 326 | 0.5593 | 0.5639 | 0.5593 | 0.7479 |
|
| 215 |
+
| No log | 3.4894 | 328 | 0.5734 | 0.5563 | 0.5734 | 0.7572 |
|
| 216 |
+
| No log | 3.5106 | 330 | 0.5525 | 0.5975 | 0.5525 | 0.7433 |
|
| 217 |
+
| No log | 3.5319 | 332 | 0.4959 | 0.6745 | 0.4959 | 0.7042 |
|
| 218 |
+
| No log | 3.5532 | 334 | 0.5144 | 0.6619 | 0.5144 | 0.7172 |
|
| 219 |
+
| No log | 3.5745 | 336 | 0.5128 | 0.6759 | 0.5128 | 0.7161 |
|
| 220 |
+
| No log | 3.5957 | 338 | 0.4769 | 0.6600 | 0.4769 | 0.6906 |
|
| 221 |
+
| No log | 3.6170 | 340 | 0.5182 | 0.5624 | 0.5182 | 0.7199 |
|
| 222 |
+
| No log | 3.6383 | 342 | 0.5468 | 0.5151 | 0.5468 | 0.7395 |
|
| 223 |
+
| No log | 3.6596 | 344 | 0.5336 | 0.5216 | 0.5336 | 0.7305 |
|
| 224 |
+
| No log | 3.6809 | 346 | 0.5008 | 0.5387 | 0.5008 | 0.7077 |
|
| 225 |
+
| No log | 3.7021 | 348 | 0.4933 | 0.5845 | 0.4933 | 0.7023 |
|
| 226 |
+
| No log | 3.7234 | 350 | 0.4902 | 0.6447 | 0.4902 | 0.7002 |
|
| 227 |
+
| No log | 3.7447 | 352 | 0.5012 | 0.6573 | 0.5012 | 0.7079 |
|
| 228 |
+
| No log | 3.7660 | 354 | 0.5840 | 0.6027 | 0.5840 | 0.7642 |
|
| 229 |
+
| No log | 3.7872 | 356 | 0.6105 | 0.6151 | 0.6105 | 0.7814 |
|
| 230 |
+
| No log | 3.8085 | 358 | 0.5571 | 0.6468 | 0.5571 | 0.7464 |
|
| 231 |
+
| No log | 3.8298 | 360 | 0.5278 | 0.6600 | 0.5278 | 0.7265 |
|
| 232 |
+
| No log | 3.8511 | 362 | 0.5155 | 0.6891 | 0.5155 | 0.7180 |
|
| 233 |
+
| No log | 3.8723 | 364 | 0.4963 | 0.6760 | 0.4963 | 0.7045 |
|
| 234 |
+
| No log | 3.8936 | 366 | 0.4723 | 0.6145 | 0.4723 | 0.6872 |
|
| 235 |
+
| No log | 3.9149 | 368 | 0.4949 | 0.6081 | 0.4949 | 0.7035 |
|
| 236 |
+
| No log | 3.9362 | 370 | 0.5497 | 0.5543 | 0.5497 | 0.7414 |
|
| 237 |
+
| No log | 3.9574 | 372 | 0.5452 | 0.5645 | 0.5452 | 0.7384 |
|
| 238 |
+
| No log | 3.9787 | 374 | 0.5031 | 0.5909 | 0.5031 | 0.7093 |
|
| 239 |
+
| No log | 4.0 | 376 | 0.4719 | 0.5916 | 0.4719 | 0.6869 |
|
| 240 |
+
| No log | 4.0213 | 378 | 0.4921 | 0.5870 | 0.4921 | 0.7015 |
|
| 241 |
+
| No log | 4.0426 | 380 | 0.4837 | 0.5792 | 0.4837 | 0.6955 |
|
| 242 |
+
| No log | 4.0638 | 382 | 0.4731 | 0.5916 | 0.4731 | 0.6878 |
|
| 243 |
+
| No log | 4.0851 | 384 | 0.4640 | 0.5876 | 0.4640 | 0.6812 |
|
| 244 |
+
| No log | 4.1064 | 386 | 0.4405 | 0.6145 | 0.4405 | 0.6637 |
|
| 245 |
+
| No log | 4.1277 | 388 | 0.4468 | 0.6613 | 0.4468 | 0.6684 |
|
| 246 |
+
| No log | 4.1489 | 390 | 0.4895 | 0.6400 | 0.4895 | 0.6997 |
|
| 247 |
+
| No log | 4.1702 | 392 | 0.5003 | 0.6409 | 0.5003 | 0.7073 |
|
| 248 |
+
| No log | 4.1915 | 394 | 0.4725 | 0.6444 | 0.4725 | 0.6874 |
|
| 249 |
+
| No log | 4.2128 | 396 | 0.4922 | 0.6368 | 0.4922 | 0.7015 |
|
| 250 |
+
| No log | 4.2340 | 398 | 0.4947 | 0.6560 | 0.4947 | 0.7034 |
|
| 251 |
+
| No log | 4.2553 | 400 | 0.5087 | 0.6566 | 0.5087 | 0.7132 |
|
| 252 |
+
| No log | 4.2766 | 402 | 0.5227 | 0.6507 | 0.5227 | 0.7230 |
|
| 253 |
+
| No log | 4.2979 | 404 | 0.6030 | 0.6553 | 0.6030 | 0.7765 |
|
| 254 |
+
| No log | 4.3191 | 406 | 0.5933 | 0.6427 | 0.5933 | 0.7702 |
|
| 255 |
+
| No log | 4.3404 | 408 | 0.7392 | 0.5619 | 0.7392 | 0.8598 |
|
| 256 |
+
| No log | 4.3617 | 410 | 0.8708 | 0.4618 | 0.8708 | 0.9332 |
|
| 257 |
+
| No log | 4.3830 | 412 | 0.8260 | 0.3587 | 0.8260 | 0.9088 |
|
| 258 |
+
| No log | 4.4043 | 414 | 0.6579 | 0.4740 | 0.6579 | 0.8111 |
|
| 259 |
+
| No log | 4.4255 | 416 | 0.5297 | 0.5927 | 0.5297 | 0.7278 |
|
| 260 |
+
| No log | 4.4468 | 418 | 0.4793 | 0.6309 | 0.4793 | 0.6923 |
|
| 261 |
+
| No log | 4.4681 | 420 | 0.4905 | 0.6669 | 0.4905 | 0.7003 |
|
| 262 |
+
| No log | 4.4894 | 422 | 0.5123 | 0.6676 | 0.5123 | 0.7158 |
|
| 263 |
+
| No log | 4.5106 | 424 | 0.6053 | 0.6100 | 0.6053 | 0.7780 |
|
| 264 |
+
| No log | 4.5319 | 426 | 0.6191 | 0.5812 | 0.6191 | 0.7869 |
|
| 265 |
+
| No log | 4.5532 | 428 | 0.5328 | 0.5989 | 0.5328 | 0.7300 |
|
| 266 |
+
| No log | 4.5745 | 430 | 0.5038 | 0.6172 | 0.5038 | 0.7098 |
|
| 267 |
+
| No log | 4.5957 | 432 | 0.5351 | 0.5602 | 0.5351 | 0.7315 |
|
| 268 |
+
| No log | 4.6170 | 434 | 0.4963 | 0.6021 | 0.4963 | 0.7045 |
|
| 269 |
+
| No log | 4.6383 | 436 | 0.5177 | 0.5727 | 0.5177 | 0.7195 |
|
| 270 |
+
| No log | 4.6596 | 438 | 0.5797 | 0.5573 | 0.5797 | 0.7614 |
|
| 271 |
+
| No log | 4.6809 | 440 | 0.7132 | 0.4918 | 0.7132 | 0.8445 |
|
| 272 |
+
| No log | 4.7021 | 442 | 0.7554 | 0.4999 | 0.7554 | 0.8692 |
|
| 273 |
+
| No log | 4.7234 | 444 | 0.6447 | 0.5903 | 0.6447 | 0.8029 |
|
| 274 |
+
| No log | 4.7447 | 446 | 0.5422 | 0.6641 | 0.5422 | 0.7363 |
|
| 275 |
+
| No log | 4.7660 | 448 | 0.5515 | 0.6300 | 0.5515 | 0.7426 |
|
| 276 |
+
| No log | 4.7872 | 450 | 0.5573 | 0.6430 | 0.5573 | 0.7465 |
|
| 277 |
+
| No log | 4.8085 | 452 | 0.6048 | 0.6215 | 0.6048 | 0.7777 |
|
| 278 |
+
| No log | 4.8298 | 454 | 0.5990 | 0.6033 | 0.5990 | 0.7740 |
|
| 279 |
+
| No log | 4.8511 | 456 | 0.5569 | 0.6497 | 0.5569 | 0.7462 |
|
| 280 |
+
| No log | 4.8723 | 458 | 0.5123 | 0.6473 | 0.5123 | 0.7157 |
|
| 281 |
+
| No log | 4.8936 | 460 | 0.5327 | 0.6765 | 0.5327 | 0.7299 |
|
| 282 |
+
| No log | 4.9149 | 462 | 0.5587 | 0.6612 | 0.5587 | 0.7475 |
|
| 283 |
+
| No log | 4.9362 | 464 | 0.6168 | 0.6318 | 0.6168 | 0.7853 |
|
| 284 |
+
| No log | 4.9574 | 466 | 0.6771 | 0.6061 | 0.6771 | 0.8229 |
|
| 285 |
+
| No log | 4.9787 | 468 | 0.6229 | 0.6409 | 0.6229 | 0.7892 |
|
| 286 |
+
| No log | 5.0 | 470 | 0.5680 | 0.6225 | 0.5680 | 0.7537 |
|
| 287 |
+
| No log | 5.0213 | 472 | 0.5931 | 0.6134 | 0.5931 | 0.7701 |
|
| 288 |
+
| No log | 5.0426 | 474 | 0.6065 | 0.5819 | 0.6065 | 0.7788 |
|
| 289 |
+
| No log | 5.0638 | 476 | 0.6540 | 0.5319 | 0.6540 | 0.8087 |
|
| 290 |
+
| No log | 5.0851 | 478 | 0.6785 | 0.5273 | 0.6785 | 0.8237 |
|
| 291 |
+
| No log | 5.1064 | 480 | 0.5893 | 0.5571 | 0.5893 | 0.7676 |
|
| 292 |
+
| No log | 5.1277 | 482 | 0.5194 | 0.6687 | 0.5194 | 0.7207 |
|
| 293 |
+
| No log | 5.1489 | 484 | 0.5091 | 0.6149 | 0.5091 | 0.7135 |
|
| 294 |
+
| No log | 5.1702 | 486 | 0.5073 | 0.6242 | 0.5073 | 0.7122 |
|
| 295 |
+
| No log | 5.1915 | 488 | 0.5084 | 0.6749 | 0.5084 | 0.7130 |
|
| 296 |
+
| No log | 5.2128 | 490 | 0.5243 | 0.6522 | 0.5243 | 0.7241 |
|
| 297 |
+
| No log | 5.2340 | 492 | 0.5612 | 0.5766 | 0.5612 | 0.7492 |
|
| 298 |
+
| No log | 5.2553 | 494 | 0.5529 | 0.5989 | 0.5529 | 0.7436 |
|
| 299 |
+
| No log | 5.2766 | 496 | 0.4907 | 0.6775 | 0.4907 | 0.7005 |
|
| 300 |
+
| No log | 5.2979 | 498 | 0.4758 | 0.6504 | 0.4758 | 0.6898 |
|
| 301 |
+
| 0.4903 | 5.3191 | 500 | 0.4783 | 0.6502 | 0.4783 | 0.6916 |
|
| 302 |
+
| 0.4903 | 5.3404 | 502 | 0.4929 | 0.6875 | 0.4929 | 0.7021 |
|
| 303 |
+
| 0.4903 | 5.3617 | 504 | 0.5380 | 0.6700 | 0.5380 | 0.7335 |
|
| 304 |
+
| 0.4903 | 5.3830 | 506 | 0.5280 | 0.6725 | 0.5280 | 0.7266 |
|
| 305 |
+
| 0.4903 | 5.4043 | 508 | 0.5505 | 0.5762 | 0.5505 | 0.7420 |
|
| 306 |
+
| 0.4903 | 5.4255 | 510 | 0.6012 | 0.5795 | 0.6012 | 0.7754 |
|
| 307 |
+
| 0.4903 | 5.4468 | 512 | 0.5882 | 0.5730 | 0.5882 | 0.7670 |
|
| 308 |
+
| 0.4903 | 5.4681 | 514 | 0.5662 | 0.5923 | 0.5662 | 0.7525 |
|
| 309 |
+
| 0.4903 | 5.4894 | 516 | 0.4951 | 0.6984 | 0.4951 | 0.7036 |
|
| 310 |
+
| 0.4903 | 5.5106 | 518 | 0.4560 | 0.6621 | 0.4560 | 0.6753 |
|
| 311 |
+
| 0.4903 | 5.5319 | 520 | 0.5183 | 0.5963 | 0.5183 | 0.7199 |
|
| 312 |
+
| 0.4903 | 5.5532 | 522 | 0.5063 | 0.5889 | 0.5063 | 0.7115 |
|
| 313 |
+
| 0.4903 | 5.5745 | 524 | 0.4577 | 0.6632 | 0.4577 | 0.6765 |
|
| 314 |
+
| 0.4903 | 5.5957 | 526 | 0.5053 | 0.6753 | 0.5053 | 0.7109 |
|
| 315 |
+
| 0.4903 | 5.6170 | 528 | 0.5438 | 0.6455 | 0.5438 | 0.7374 |
|
| 316 |
+
| 0.4903 | 5.6383 | 530 | 0.5412 | 0.6487 | 0.5412 | 0.7357 |
|
| 317 |
+
| 0.4903 | 5.6596 | 532 | 0.5052 | 0.6591 | 0.5052 | 0.7108 |
|
| 318 |
+
| 0.4903 | 5.6809 | 534 | 0.5270 | 0.6623 | 0.5270 | 0.7260 |
|
| 319 |
+
| 0.4903 | 5.7021 | 536 | 0.6447 | 0.6274 | 0.6447 | 0.8029 |
|
| 320 |
+
| 0.4903 | 5.7234 | 538 | 0.7549 | 0.6062 | 0.7549 | 0.8689 |
|
| 321 |
+
| 0.4903 | 5.7447 | 540 | 0.8034 | 0.6328 | 0.8034 | 0.8963 |
|
| 322 |
+
| 0.4903 | 5.7660 | 542 | 0.7529 | 0.6359 | 0.7529 | 0.8677 |
|
| 323 |
+
| 0.4903 | 5.7872 | 544 | 0.6377 | 0.6434 | 0.6377 | 0.7986 |
|
| 324 |
+
|
| 325 |
+
|
| 326 |
+
### Framework versions
|
| 327 |
+
|
| 328 |
+
- Transformers 4.44.2
|
| 329 |
+
- Pytorch 2.4.0+cu118
|
| 330 |
+
- Datasets 2.21.0
|
| 331 |
+
- 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:f23500a3ad083a9ec17d5e3f2bf00af903cfb09445d864d0f34e679a4ad46bc6
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c5d8f4c23e54129e07572331298be5d229e6bf3611a089f734d0883d1c4b8db
|
| 3 |
+
size 5240
|