Training in progress, step 500
Browse files- README.md +322 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_TestTask8_style
|
| 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_TestTask8_style
|
| 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: 0.5481
|
| 19 |
+
- Qwk: 0.6163
|
| 20 |
+
- Mse: 0.5481
|
| 21 |
+
- Rmse: 0.7404
|
| 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 | 0.0196 | 2 | 4.5012 | 0.0097 | 4.5012 | 2.1216 |
|
| 53 |
+
| No log | 0.0392 | 4 | 3.5589 | 0.0382 | 3.5589 | 1.8865 |
|
| 54 |
+
| No log | 0.0588 | 6 | 1.9737 | 0.1331 | 1.9737 | 1.4049 |
|
| 55 |
+
| No log | 0.0784 | 8 | 0.9322 | 0.2035 | 0.9322 | 0.9655 |
|
| 56 |
+
| No log | 0.0980 | 10 | 0.8332 | 0.1912 | 0.8332 | 0.9128 |
|
| 57 |
+
| No log | 0.1176 | 12 | 0.9038 | 0.0744 | 0.9038 | 0.9507 |
|
| 58 |
+
| No log | 0.1373 | 14 | 0.8321 | 0.1429 | 0.8321 | 0.9122 |
|
| 59 |
+
| No log | 0.1569 | 16 | 0.7784 | 0.3863 | 0.7784 | 0.8823 |
|
| 60 |
+
| No log | 0.1765 | 18 | 0.7100 | 0.3684 | 0.7100 | 0.8426 |
|
| 61 |
+
| No log | 0.1961 | 20 | 0.7243 | 0.3222 | 0.7243 | 0.8511 |
|
| 62 |
+
| No log | 0.2157 | 22 | 0.7571 | 0.2788 | 0.7571 | 0.8701 |
|
| 63 |
+
| No log | 0.2353 | 24 | 0.8078 | 0.2411 | 0.8078 | 0.8988 |
|
| 64 |
+
| No log | 0.2549 | 26 | 0.7100 | 0.2813 | 0.7100 | 0.8426 |
|
| 65 |
+
| No log | 0.2745 | 28 | 0.6065 | 0.3935 | 0.6065 | 0.7788 |
|
| 66 |
+
| No log | 0.2941 | 30 | 0.5933 | 0.4553 | 0.5933 | 0.7702 |
|
| 67 |
+
| No log | 0.3137 | 32 | 0.6127 | 0.4947 | 0.6127 | 0.7827 |
|
| 68 |
+
| No log | 0.3333 | 34 | 0.6987 | 0.5092 | 0.6987 | 0.8359 |
|
| 69 |
+
| No log | 0.3529 | 36 | 0.7228 | 0.5372 | 0.7228 | 0.8502 |
|
| 70 |
+
| No log | 0.3725 | 38 | 0.6945 | 0.5412 | 0.6945 | 0.8334 |
|
| 71 |
+
| No log | 0.3922 | 40 | 0.6205 | 0.5585 | 0.6205 | 0.7877 |
|
| 72 |
+
| No log | 0.4118 | 42 | 0.5929 | 0.5466 | 0.5929 | 0.7700 |
|
| 73 |
+
| No log | 0.4314 | 44 | 0.5801 | 0.5163 | 0.5801 | 0.7616 |
|
| 74 |
+
| No log | 0.4510 | 46 | 0.5336 | 0.5283 | 0.5336 | 0.7305 |
|
| 75 |
+
| No log | 0.4706 | 48 | 0.5219 | 0.5327 | 0.5219 | 0.7224 |
|
| 76 |
+
| No log | 0.4902 | 50 | 0.5319 | 0.5140 | 0.5319 | 0.7293 |
|
| 77 |
+
| No log | 0.5098 | 52 | 0.5986 | 0.4348 | 0.5986 | 0.7737 |
|
| 78 |
+
| No log | 0.5294 | 54 | 0.7148 | 0.3649 | 0.7148 | 0.8454 |
|
| 79 |
+
| No log | 0.5490 | 56 | 0.7513 | 0.3305 | 0.7513 | 0.8668 |
|
| 80 |
+
| No log | 0.5686 | 58 | 0.7103 | 0.3212 | 0.7103 | 0.8428 |
|
| 81 |
+
| No log | 0.5882 | 60 | 0.7013 | 0.3370 | 0.7013 | 0.8374 |
|
| 82 |
+
| No log | 0.6078 | 62 | 0.6029 | 0.4719 | 0.6029 | 0.7764 |
|
| 83 |
+
| No log | 0.6275 | 64 | 0.5921 | 0.5229 | 0.5921 | 0.7695 |
|
| 84 |
+
| No log | 0.6471 | 66 | 0.7300 | 0.5555 | 0.7300 | 0.8544 |
|
| 85 |
+
| No log | 0.6667 | 68 | 0.8322 | 0.5105 | 0.8322 | 0.9123 |
|
| 86 |
+
| No log | 0.6863 | 70 | 0.5997 | 0.5934 | 0.5997 | 0.7744 |
|
| 87 |
+
| No log | 0.7059 | 72 | 0.4693 | 0.6234 | 0.4693 | 0.6851 |
|
| 88 |
+
| No log | 0.7255 | 74 | 0.5310 | 0.5911 | 0.5310 | 0.7287 |
|
| 89 |
+
| No log | 0.7451 | 76 | 0.4699 | 0.6129 | 0.4699 | 0.6855 |
|
| 90 |
+
| No log | 0.7647 | 78 | 0.7034 | 0.5381 | 0.7034 | 0.8387 |
|
| 91 |
+
| No log | 0.7843 | 80 | 0.8957 | 0.5152 | 0.8957 | 0.9464 |
|
| 92 |
+
| No log | 0.8039 | 82 | 0.7039 | 0.5338 | 0.7039 | 0.8390 |
|
| 93 |
+
| No log | 0.8235 | 84 | 0.5157 | 0.5961 | 0.5157 | 0.7181 |
|
| 94 |
+
| No log | 0.8431 | 86 | 0.4820 | 0.6323 | 0.4820 | 0.6943 |
|
| 95 |
+
| No log | 0.8627 | 88 | 0.4681 | 0.6329 | 0.4681 | 0.6842 |
|
| 96 |
+
| No log | 0.8824 | 90 | 0.5062 | 0.6297 | 0.5062 | 0.7114 |
|
| 97 |
+
| No log | 0.9020 | 92 | 0.6096 | 0.5525 | 0.6096 | 0.7808 |
|
| 98 |
+
| No log | 0.9216 | 94 | 0.5743 | 0.5719 | 0.5743 | 0.7578 |
|
| 99 |
+
| No log | 0.9412 | 96 | 0.4714 | 0.6372 | 0.4714 | 0.6866 |
|
| 100 |
+
| No log | 0.9608 | 98 | 0.4468 | 0.6548 | 0.4468 | 0.6684 |
|
| 101 |
+
| No log | 0.9804 | 100 | 0.4550 | 0.6411 | 0.4550 | 0.6746 |
|
| 102 |
+
| No log | 1.0 | 102 | 0.4540 | 0.6290 | 0.4540 | 0.6738 |
|
| 103 |
+
| No log | 1.0196 | 104 | 0.4774 | 0.6338 | 0.4774 | 0.6909 |
|
| 104 |
+
| No log | 1.0392 | 106 | 0.5666 | 0.5885 | 0.5666 | 0.7527 |
|
| 105 |
+
| No log | 1.0588 | 108 | 0.6683 | 0.5723 | 0.6683 | 0.8175 |
|
| 106 |
+
| No log | 1.0784 | 110 | 0.5837 | 0.6378 | 0.5837 | 0.7640 |
|
| 107 |
+
| No log | 1.0980 | 112 | 0.4836 | 0.6487 | 0.4836 | 0.6954 |
|
| 108 |
+
| No log | 1.1176 | 114 | 0.4727 | 0.6474 | 0.4727 | 0.6875 |
|
| 109 |
+
| No log | 1.1373 | 116 | 0.5726 | 0.6162 | 0.5726 | 0.7567 |
|
| 110 |
+
| No log | 1.1569 | 118 | 0.5640 | 0.6191 | 0.5640 | 0.7510 |
|
| 111 |
+
| No log | 1.1765 | 120 | 0.5662 | 0.6270 | 0.5662 | 0.7525 |
|
| 112 |
+
| No log | 1.1961 | 122 | 0.5329 | 0.6525 | 0.5329 | 0.7300 |
|
| 113 |
+
| No log | 1.2157 | 124 | 0.4365 | 0.7008 | 0.4365 | 0.6607 |
|
| 114 |
+
| No log | 1.2353 | 126 | 0.4252 | 0.6873 | 0.4252 | 0.6520 |
|
| 115 |
+
| No log | 1.2549 | 128 | 0.4296 | 0.6882 | 0.4296 | 0.6554 |
|
| 116 |
+
| No log | 1.2745 | 130 | 0.5168 | 0.6598 | 0.5168 | 0.7189 |
|
| 117 |
+
| No log | 1.2941 | 132 | 0.5355 | 0.6639 | 0.5355 | 0.7318 |
|
| 118 |
+
| No log | 1.3137 | 134 | 0.6045 | 0.6181 | 0.6045 | 0.7775 |
|
| 119 |
+
| No log | 1.3333 | 136 | 0.5470 | 0.6436 | 0.5470 | 0.7396 |
|
| 120 |
+
| No log | 1.3529 | 138 | 0.4052 | 0.6873 | 0.4052 | 0.6365 |
|
| 121 |
+
| No log | 1.3725 | 140 | 0.3945 | 0.7177 | 0.3945 | 0.6281 |
|
| 122 |
+
| No log | 1.3922 | 142 | 0.3997 | 0.7284 | 0.3997 | 0.6322 |
|
| 123 |
+
| No log | 1.4118 | 144 | 0.5193 | 0.6504 | 0.5193 | 0.7206 |
|
| 124 |
+
| No log | 1.4314 | 146 | 0.7289 | 0.5757 | 0.7289 | 0.8537 |
|
| 125 |
+
| No log | 1.4510 | 148 | 0.7045 | 0.5772 | 0.7045 | 0.8394 |
|
| 126 |
+
| No log | 1.4706 | 150 | 0.4622 | 0.6680 | 0.4622 | 0.6798 |
|
| 127 |
+
| No log | 1.4902 | 152 | 0.4117 | 0.7097 | 0.4117 | 0.6416 |
|
| 128 |
+
| No log | 1.5098 | 154 | 0.4211 | 0.6848 | 0.4211 | 0.6489 |
|
| 129 |
+
| No log | 1.5294 | 156 | 0.4492 | 0.6040 | 0.4492 | 0.6702 |
|
| 130 |
+
| No log | 1.5490 | 158 | 0.6618 | 0.5621 | 0.6618 | 0.8135 |
|
| 131 |
+
| No log | 1.5686 | 160 | 0.8027 | 0.4827 | 0.8027 | 0.8959 |
|
| 132 |
+
| No log | 1.5882 | 162 | 0.8408 | 0.4095 | 0.8408 | 0.9170 |
|
| 133 |
+
| No log | 1.6078 | 164 | 0.7924 | 0.4268 | 0.7924 | 0.8902 |
|
| 134 |
+
| No log | 1.6275 | 166 | 0.6695 | 0.5054 | 0.6695 | 0.8182 |
|
| 135 |
+
| No log | 1.6471 | 168 | 0.5852 | 0.5396 | 0.5852 | 0.7650 |
|
| 136 |
+
| No log | 1.6667 | 170 | 0.6418 | 0.5461 | 0.6418 | 0.8011 |
|
| 137 |
+
| No log | 1.6863 | 172 | 0.7538 | 0.4643 | 0.7538 | 0.8682 |
|
| 138 |
+
| No log | 1.7059 | 174 | 0.7169 | 0.3996 | 0.7169 | 0.8467 |
|
| 139 |
+
| No log | 1.7255 | 176 | 0.6124 | 0.4255 | 0.6124 | 0.7826 |
|
| 140 |
+
| No log | 1.7451 | 178 | 0.5922 | 0.5146 | 0.5922 | 0.7696 |
|
| 141 |
+
| No log | 1.7647 | 180 | 0.5797 | 0.5493 | 0.5797 | 0.7614 |
|
| 142 |
+
| No log | 1.7843 | 182 | 0.5468 | 0.5765 | 0.5468 | 0.7394 |
|
| 143 |
+
| No log | 1.8039 | 184 | 0.5458 | 0.5197 | 0.5458 | 0.7388 |
|
| 144 |
+
| No log | 1.8235 | 186 | 0.5733 | 0.5939 | 0.5733 | 0.7572 |
|
| 145 |
+
| No log | 1.8431 | 188 | 0.6078 | 0.6222 | 0.6078 | 0.7796 |
|
| 146 |
+
| No log | 1.8627 | 190 | 0.6313 | 0.6255 | 0.6313 | 0.7946 |
|
| 147 |
+
| No log | 1.8824 | 192 | 0.4942 | 0.6457 | 0.4942 | 0.7030 |
|
| 148 |
+
| No log | 1.9020 | 194 | 0.4699 | 0.6878 | 0.4699 | 0.6855 |
|
| 149 |
+
| No log | 1.9216 | 196 | 0.5484 | 0.6332 | 0.5484 | 0.7405 |
|
| 150 |
+
| No log | 1.9412 | 198 | 0.7298 | 0.5847 | 0.7298 | 0.8543 |
|
| 151 |
+
| No log | 1.9608 | 200 | 0.6525 | 0.6186 | 0.6525 | 0.8078 |
|
| 152 |
+
| No log | 1.9804 | 202 | 0.5272 | 0.6561 | 0.5272 | 0.7261 |
|
| 153 |
+
| No log | 2.0 | 204 | 0.4594 | 0.6834 | 0.4594 | 0.6778 |
|
| 154 |
+
| No log | 2.0196 | 206 | 0.4300 | 0.7201 | 0.4300 | 0.6558 |
|
| 155 |
+
| No log | 2.0392 | 208 | 0.4927 | 0.7024 | 0.4927 | 0.7020 |
|
| 156 |
+
| No log | 2.0588 | 210 | 0.5898 | 0.6439 | 0.5898 | 0.7680 |
|
| 157 |
+
| No log | 2.0784 | 212 | 0.5739 | 0.6544 | 0.5739 | 0.7576 |
|
| 158 |
+
| No log | 2.0980 | 214 | 0.5909 | 0.6445 | 0.5909 | 0.7687 |
|
| 159 |
+
| No log | 2.1176 | 216 | 0.5896 | 0.5616 | 0.5896 | 0.7678 |
|
| 160 |
+
| No log | 2.1373 | 218 | 0.5324 | 0.5817 | 0.5324 | 0.7297 |
|
| 161 |
+
| No log | 2.1569 | 220 | 0.4842 | 0.6386 | 0.4842 | 0.6959 |
|
| 162 |
+
| No log | 2.1765 | 222 | 0.4917 | 0.6157 | 0.4917 | 0.7012 |
|
| 163 |
+
| No log | 2.1961 | 224 | 0.6489 | 0.5785 | 0.6489 | 0.8055 |
|
| 164 |
+
| No log | 2.2157 | 226 | 0.8584 | 0.5536 | 0.8584 | 0.9265 |
|
| 165 |
+
| No log | 2.2353 | 228 | 0.8313 | 0.5576 | 0.8313 | 0.9117 |
|
| 166 |
+
| No log | 2.2549 | 230 | 0.5957 | 0.5842 | 0.5957 | 0.7718 |
|
| 167 |
+
| No log | 2.2745 | 232 | 0.4395 | 0.6952 | 0.4395 | 0.6630 |
|
| 168 |
+
| No log | 2.2941 | 234 | 0.4156 | 0.7197 | 0.4156 | 0.6447 |
|
| 169 |
+
| No log | 2.3137 | 236 | 0.5118 | 0.6446 | 0.5118 | 0.7154 |
|
| 170 |
+
| No log | 2.3333 | 238 | 0.9220 | 0.5434 | 0.9220 | 0.9602 |
|
| 171 |
+
| No log | 2.3529 | 240 | 1.0599 | 0.5115 | 1.0599 | 1.0295 |
|
| 172 |
+
| No log | 2.3725 | 242 | 0.7943 | 0.5960 | 0.7943 | 0.8912 |
|
| 173 |
+
| No log | 2.3922 | 244 | 0.4594 | 0.6694 | 0.4594 | 0.6778 |
|
| 174 |
+
| No log | 2.4118 | 246 | 0.4625 | 0.6855 | 0.4625 | 0.6801 |
|
| 175 |
+
| No log | 2.4314 | 248 | 0.4228 | 0.6918 | 0.4228 | 0.6502 |
|
| 176 |
+
| No log | 2.4510 | 250 | 0.4770 | 0.6634 | 0.4770 | 0.6907 |
|
| 177 |
+
| No log | 2.4706 | 252 | 0.5658 | 0.5897 | 0.5658 | 0.7522 |
|
| 178 |
+
| No log | 2.4902 | 254 | 0.5687 | 0.5615 | 0.5687 | 0.7541 |
|
| 179 |
+
| No log | 2.5098 | 256 | 0.6668 | 0.5400 | 0.6668 | 0.8166 |
|
| 180 |
+
| No log | 2.5294 | 258 | 0.8650 | 0.4988 | 0.8650 | 0.9301 |
|
| 181 |
+
| No log | 2.5490 | 260 | 1.0891 | 0.4581 | 1.0891 | 1.0436 |
|
| 182 |
+
| No log | 2.5686 | 262 | 0.9992 | 0.4945 | 0.9992 | 0.9996 |
|
| 183 |
+
| No log | 2.5882 | 264 | 0.6867 | 0.6087 | 0.6867 | 0.8287 |
|
| 184 |
+
| No log | 2.6078 | 266 | 0.5045 | 0.7015 | 0.5045 | 0.7103 |
|
| 185 |
+
| No log | 2.6275 | 268 | 0.5304 | 0.6921 | 0.5304 | 0.7283 |
|
| 186 |
+
| No log | 2.6471 | 270 | 0.6508 | 0.6650 | 0.6508 | 0.8067 |
|
| 187 |
+
| No log | 2.6667 | 272 | 0.6739 | 0.6419 | 0.6739 | 0.8209 |
|
| 188 |
+
| No log | 2.6863 | 274 | 0.5553 | 0.6380 | 0.5553 | 0.7452 |
|
| 189 |
+
| No log | 2.7059 | 276 | 0.5093 | 0.6870 | 0.5093 | 0.7136 |
|
| 190 |
+
| No log | 2.7255 | 278 | 0.4990 | 0.6681 | 0.4990 | 0.7064 |
|
| 191 |
+
| No log | 2.7451 | 280 | 0.4894 | 0.6509 | 0.4894 | 0.6996 |
|
| 192 |
+
| No log | 2.7647 | 282 | 0.4733 | 0.6596 | 0.4733 | 0.6880 |
|
| 193 |
+
| No log | 2.7843 | 284 | 0.4679 | 0.6653 | 0.4679 | 0.6840 |
|
| 194 |
+
| No log | 2.8039 | 286 | 0.4337 | 0.7021 | 0.4337 | 0.6586 |
|
| 195 |
+
| No log | 2.8235 | 288 | 0.4327 | 0.7090 | 0.4327 | 0.6578 |
|
| 196 |
+
| No log | 2.8431 | 290 | 0.5612 | 0.6278 | 0.5612 | 0.7492 |
|
| 197 |
+
| No log | 2.8627 | 292 | 0.8774 | 0.5359 | 0.8774 | 0.9367 |
|
| 198 |
+
| No log | 2.8824 | 294 | 0.9346 | 0.4930 | 0.9346 | 0.9667 |
|
| 199 |
+
| No log | 2.9020 | 296 | 0.7562 | 0.5786 | 0.7562 | 0.8696 |
|
| 200 |
+
| No log | 2.9216 | 298 | 0.5329 | 0.6475 | 0.5329 | 0.7300 |
|
| 201 |
+
| No log | 2.9412 | 300 | 0.4211 | 0.6961 | 0.4211 | 0.6490 |
|
| 202 |
+
| No log | 2.9608 | 302 | 0.4121 | 0.6785 | 0.4121 | 0.6420 |
|
| 203 |
+
| No log | 2.9804 | 304 | 0.4565 | 0.6325 | 0.4565 | 0.6757 |
|
| 204 |
+
| No log | 3.0 | 306 | 0.5830 | 0.6238 | 0.5830 | 0.7636 |
|
| 205 |
+
| No log | 3.0196 | 308 | 0.7815 | 0.5441 | 0.7815 | 0.8840 |
|
| 206 |
+
| No log | 3.0392 | 310 | 0.8049 | 0.5240 | 0.8049 | 0.8972 |
|
| 207 |
+
| No log | 3.0588 | 312 | 0.7507 | 0.5471 | 0.7507 | 0.8664 |
|
| 208 |
+
| No log | 3.0784 | 314 | 0.6218 | 0.6158 | 0.6218 | 0.7885 |
|
| 209 |
+
| No log | 3.0980 | 316 | 0.4504 | 0.6842 | 0.4504 | 0.6711 |
|
| 210 |
+
| No log | 3.1176 | 318 | 0.4056 | 0.7036 | 0.4056 | 0.6369 |
|
| 211 |
+
| No log | 3.1373 | 320 | 0.4101 | 0.7098 | 0.4101 | 0.6404 |
|
| 212 |
+
| No log | 3.1569 | 322 | 0.4066 | 0.7228 | 0.4066 | 0.6376 |
|
| 213 |
+
| No log | 3.1765 | 324 | 0.4543 | 0.7044 | 0.4543 | 0.6740 |
|
| 214 |
+
| No log | 3.1961 | 326 | 0.7520 | 0.5775 | 0.7520 | 0.8672 |
|
| 215 |
+
| No log | 3.2157 | 328 | 0.8543 | 0.5466 | 0.8543 | 0.9243 |
|
| 216 |
+
| No log | 3.2353 | 330 | 0.6143 | 0.6129 | 0.6143 | 0.7838 |
|
| 217 |
+
| No log | 3.2549 | 332 | 0.4540 | 0.6614 | 0.4540 | 0.6738 |
|
| 218 |
+
| No log | 3.2745 | 334 | 0.4571 | 0.6522 | 0.4571 | 0.6761 |
|
| 219 |
+
| No log | 3.2941 | 336 | 0.5199 | 0.6228 | 0.5199 | 0.7211 |
|
| 220 |
+
| No log | 3.3137 | 338 | 0.8379 | 0.5476 | 0.8379 | 0.9154 |
|
| 221 |
+
| No log | 3.3333 | 340 | 0.9752 | 0.5071 | 0.9752 | 0.9875 |
|
| 222 |
+
| No log | 3.3529 | 342 | 0.7991 | 0.5722 | 0.7991 | 0.8939 |
|
| 223 |
+
| No log | 3.3725 | 344 | 0.6223 | 0.6089 | 0.6223 | 0.7889 |
|
| 224 |
+
| No log | 3.3922 | 346 | 0.4640 | 0.6840 | 0.4640 | 0.6812 |
|
| 225 |
+
| No log | 3.4118 | 348 | 0.4244 | 0.6990 | 0.4244 | 0.6514 |
|
| 226 |
+
| No log | 3.4314 | 350 | 0.4572 | 0.6796 | 0.4572 | 0.6761 |
|
| 227 |
+
| No log | 3.4510 | 352 | 0.6189 | 0.6130 | 0.6189 | 0.7867 |
|
| 228 |
+
| No log | 3.4706 | 354 | 0.6935 | 0.6068 | 0.6935 | 0.8327 |
|
| 229 |
+
| No log | 3.4902 | 356 | 0.5612 | 0.6350 | 0.5612 | 0.7491 |
|
| 230 |
+
| No log | 3.5098 | 358 | 0.4767 | 0.6808 | 0.4767 | 0.6904 |
|
| 231 |
+
| No log | 3.5294 | 360 | 0.4450 | 0.7024 | 0.4450 | 0.6671 |
|
| 232 |
+
| No log | 3.5490 | 362 | 0.4874 | 0.6898 | 0.4874 | 0.6981 |
|
| 233 |
+
| No log | 3.5686 | 364 | 0.6688 | 0.5501 | 0.6688 | 0.8178 |
|
| 234 |
+
| No log | 3.5882 | 366 | 0.7047 | 0.5633 | 0.7047 | 0.8395 |
|
| 235 |
+
| No log | 3.6078 | 368 | 0.5952 | 0.6039 | 0.5952 | 0.7715 |
|
| 236 |
+
| No log | 3.6275 | 370 | 0.4792 | 0.6949 | 0.4792 | 0.6922 |
|
| 237 |
+
| No log | 3.6471 | 372 | 0.4994 | 0.6786 | 0.4994 | 0.7067 |
|
| 238 |
+
| No log | 3.6667 | 374 | 0.5921 | 0.6537 | 0.5921 | 0.7695 |
|
| 239 |
+
| No log | 3.6863 | 376 | 0.6141 | 0.6547 | 0.6141 | 0.7837 |
|
| 240 |
+
| No log | 3.7059 | 378 | 0.5623 | 0.6503 | 0.5623 | 0.7498 |
|
| 241 |
+
| No log | 3.7255 | 380 | 0.5398 | 0.6714 | 0.5398 | 0.7347 |
|
| 242 |
+
| No log | 3.7451 | 382 | 0.5298 | 0.6823 | 0.5298 | 0.7279 |
|
| 243 |
+
| No log | 3.7647 | 384 | 0.6892 | 0.6088 | 0.6892 | 0.8302 |
|
| 244 |
+
| No log | 3.7843 | 386 | 1.0657 | 0.5212 | 1.0657 | 1.0323 |
|
| 245 |
+
| No log | 3.8039 | 388 | 1.0023 | 0.5025 | 1.0023 | 1.0011 |
|
| 246 |
+
| No log | 3.8235 | 390 | 0.6591 | 0.5741 | 0.6591 | 0.8119 |
|
| 247 |
+
| No log | 3.8431 | 392 | 0.5033 | 0.6371 | 0.5033 | 0.7094 |
|
| 248 |
+
| No log | 3.8627 | 394 | 0.4951 | 0.6509 | 0.4951 | 0.7036 |
|
| 249 |
+
| No log | 3.8824 | 396 | 0.5559 | 0.6363 | 0.5559 | 0.7456 |
|
| 250 |
+
| No log | 3.9020 | 398 | 0.6587 | 0.5866 | 0.6587 | 0.8116 |
|
| 251 |
+
| No log | 3.9216 | 400 | 0.9212 | 0.5662 | 0.9212 | 0.9598 |
|
| 252 |
+
| No log | 3.9412 | 402 | 0.9632 | 0.5724 | 0.9632 | 0.9814 |
|
| 253 |
+
| No log | 3.9608 | 404 | 0.7895 | 0.6341 | 0.7895 | 0.8886 |
|
| 254 |
+
| No log | 3.9804 | 406 | 0.5204 | 0.6989 | 0.5204 | 0.7214 |
|
| 255 |
+
| No log | 4.0 | 408 | 0.4415 | 0.7221 | 0.4415 | 0.6644 |
|
| 256 |
+
| No log | 4.0196 | 410 | 0.4265 | 0.7044 | 0.4265 | 0.6531 |
|
| 257 |
+
| No log | 4.0392 | 412 | 0.4571 | 0.6915 | 0.4571 | 0.6761 |
|
| 258 |
+
| No log | 4.0588 | 414 | 0.6361 | 0.6377 | 0.6361 | 0.7976 |
|
| 259 |
+
| No log | 4.0784 | 416 | 0.8217 | 0.5366 | 0.8217 | 0.9065 |
|
| 260 |
+
| No log | 4.0980 | 418 | 0.7615 | 0.5525 | 0.7615 | 0.8726 |
|
| 261 |
+
| No log | 4.1176 | 420 | 0.5582 | 0.6772 | 0.5582 | 0.7472 |
|
| 262 |
+
| No log | 4.1373 | 422 | 0.4815 | 0.6838 | 0.4815 | 0.6939 |
|
| 263 |
+
| No log | 4.1569 | 424 | 0.5152 | 0.6846 | 0.5152 | 0.7178 |
|
| 264 |
+
| No log | 4.1765 | 426 | 0.6221 | 0.6461 | 0.6221 | 0.7887 |
|
| 265 |
+
| No log | 4.1961 | 428 | 0.6344 | 0.6319 | 0.6344 | 0.7965 |
|
| 266 |
+
| No log | 4.2157 | 430 | 0.5485 | 0.6879 | 0.5485 | 0.7406 |
|
| 267 |
+
| No log | 4.2353 | 432 | 0.5434 | 0.6637 | 0.5434 | 0.7371 |
|
| 268 |
+
| No log | 4.2549 | 434 | 0.5340 | 0.6569 | 0.5340 | 0.7307 |
|
| 269 |
+
| No log | 4.2745 | 436 | 0.5126 | 0.6488 | 0.5126 | 0.7160 |
|
| 270 |
+
| No log | 4.2941 | 438 | 0.4612 | 0.6187 | 0.4612 | 0.6791 |
|
| 271 |
+
| No log | 4.3137 | 440 | 0.4537 | 0.6225 | 0.4537 | 0.6735 |
|
| 272 |
+
| No log | 4.3333 | 442 | 0.5004 | 0.6538 | 0.5004 | 0.7074 |
|
| 273 |
+
| No log | 4.3529 | 444 | 0.5687 | 0.6712 | 0.5687 | 0.7541 |
|
| 274 |
+
| No log | 4.3725 | 446 | 0.5497 | 0.6737 | 0.5497 | 0.7414 |
|
| 275 |
+
| No log | 4.3922 | 448 | 0.5350 | 0.6620 | 0.5350 | 0.7314 |
|
| 276 |
+
| No log | 4.4118 | 450 | 0.5968 | 0.6493 | 0.5968 | 0.7725 |
|
| 277 |
+
| No log | 4.4314 | 452 | 0.5599 | 0.6701 | 0.5599 | 0.7483 |
|
| 278 |
+
| No log | 4.4510 | 454 | 0.4940 | 0.7123 | 0.4940 | 0.7028 |
|
| 279 |
+
| No log | 4.4706 | 456 | 0.4659 | 0.7136 | 0.4659 | 0.6826 |
|
| 280 |
+
| No log | 4.4902 | 458 | 0.5570 | 0.7007 | 0.5570 | 0.7463 |
|
| 281 |
+
| No log | 4.5098 | 460 | 0.6112 | 0.6676 | 0.6112 | 0.7818 |
|
| 282 |
+
| No log | 4.5294 | 462 | 0.7127 | 0.6083 | 0.7127 | 0.8442 |
|
| 283 |
+
| No log | 4.5490 | 464 | 0.6289 | 0.6273 | 0.6289 | 0.7930 |
|
| 284 |
+
| No log | 4.5686 | 466 | 0.6343 | 0.6377 | 0.6343 | 0.7964 |
|
| 285 |
+
| No log | 4.5882 | 468 | 0.6344 | 0.6279 | 0.6344 | 0.7965 |
|
| 286 |
+
| No log | 4.6078 | 470 | 0.7247 | 0.5906 | 0.7247 | 0.8513 |
|
| 287 |
+
| No log | 4.6275 | 472 | 0.7941 | 0.5592 | 0.7941 | 0.8912 |
|
| 288 |
+
| No log | 4.6471 | 474 | 0.6750 | 0.6014 | 0.6750 | 0.8216 |
|
| 289 |
+
| No log | 4.6667 | 476 | 0.6947 | 0.5890 | 0.6947 | 0.8335 |
|
| 290 |
+
| No log | 4.6863 | 478 | 0.6136 | 0.6115 | 0.6136 | 0.7833 |
|
| 291 |
+
| No log | 4.7059 | 480 | 0.4663 | 0.6630 | 0.4663 | 0.6828 |
|
| 292 |
+
| No log | 4.7255 | 482 | 0.4313 | 0.6658 | 0.4313 | 0.6567 |
|
| 293 |
+
| No log | 4.7451 | 484 | 0.4342 | 0.6702 | 0.4342 | 0.6589 |
|
| 294 |
+
| No log | 4.7647 | 486 | 0.4333 | 0.6589 | 0.4333 | 0.6582 |
|
| 295 |
+
| No log | 4.7843 | 488 | 0.5749 | 0.6203 | 0.5749 | 0.7582 |
|
| 296 |
+
| No log | 4.8039 | 490 | 0.7231 | 0.5642 | 0.7231 | 0.8503 |
|
| 297 |
+
| No log | 4.8235 | 492 | 0.7060 | 0.6014 | 0.7060 | 0.8402 |
|
| 298 |
+
| No log | 4.8431 | 494 | 0.6294 | 0.6277 | 0.6294 | 0.7934 |
|
| 299 |
+
| No log | 4.8627 | 496 | 0.4694 | 0.6604 | 0.4694 | 0.6851 |
|
| 300 |
+
| No log | 4.8824 | 498 | 0.4374 | 0.6854 | 0.4374 | 0.6614 |
|
| 301 |
+
| 0.4613 | 4.9020 | 500 | 0.5373 | 0.6669 | 0.5373 | 0.7330 |
|
| 302 |
+
| 0.4613 | 4.9216 | 502 | 0.6638 | 0.6127 | 0.6638 | 0.8147 |
|
| 303 |
+
| 0.4613 | 4.9412 | 504 | 0.5950 | 0.6394 | 0.5950 | 0.7714 |
|
| 304 |
+
| 0.4613 | 4.9608 | 506 | 0.6190 | 0.6310 | 0.6190 | 0.7868 |
|
| 305 |
+
| 0.4613 | 4.9804 | 508 | 0.6055 | 0.6242 | 0.6055 | 0.7781 |
|
| 306 |
+
| 0.4613 | 5.0 | 510 | 0.4982 | 0.6886 | 0.4982 | 0.7058 |
|
| 307 |
+
| 0.4613 | 5.0196 | 512 | 0.4938 | 0.6930 | 0.4938 | 0.7027 |
|
| 308 |
+
| 0.4613 | 5.0392 | 514 | 0.5469 | 0.6655 | 0.5469 | 0.7395 |
|
| 309 |
+
| 0.4613 | 5.0588 | 516 | 0.4965 | 0.6704 | 0.4965 | 0.7046 |
|
| 310 |
+
| 0.4613 | 5.0784 | 518 | 0.5196 | 0.6644 | 0.5196 | 0.7208 |
|
| 311 |
+
| 0.4613 | 5.0980 | 520 | 0.7073 | 0.6145 | 0.7073 | 0.8410 |
|
| 312 |
+
| 0.4613 | 5.1176 | 522 | 0.9007 | 0.5406 | 0.9007 | 0.9491 |
|
| 313 |
+
| 0.4613 | 5.1373 | 524 | 0.8276 | 0.5510 | 0.8276 | 0.9097 |
|
| 314 |
+
| 0.4613 | 5.1569 | 526 | 0.5481 | 0.6163 | 0.5481 | 0.7404 |
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
### Framework versions
|
| 318 |
+
|
| 319 |
+
- Transformers 4.44.2
|
| 320 |
+
- Pytorch 2.4.0+cu118
|
| 321 |
+
- Datasets 2.21.0
|
| 322 |
+
- 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 sha256:017c4f66e17364ba04eafc7a12d8289007cf69cad3fc71b72339d0968824f810
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe61e2a2308dcf1362baaccb0d3dd78b06ddeff68774b19a4f84e994aa740e3e
|
| 3 |
+
size 5240
|