Training in progress, step 500
Browse files- README.md +335 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,335 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_task7_organization
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_task7_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: 0.9024
|
| 19 |
+
- Qwk: 0.4213
|
| 20 |
+
- Mse: 0.9024
|
| 21 |
+
- Rmse: 0.9499
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 100
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:------:|
|
| 52 |
+
| No log | 0.0211 | 2 | 2.5039 | -0.0593 | 2.5039 | 1.5824 |
|
| 53 |
+
| No log | 0.0421 | 4 | 1.0942 | 0.1856 | 1.0942 | 1.0461 |
|
| 54 |
+
| No log | 0.0632 | 6 | 0.7171 | 0.0444 | 0.7171 | 0.8468 |
|
| 55 |
+
| No log | 0.0842 | 8 | 0.8750 | 0.1867 | 0.8750 | 0.9354 |
|
| 56 |
+
| No log | 0.1053 | 10 | 0.8115 | 0.2703 | 0.8115 | 0.9008 |
|
| 57 |
+
| No log | 0.1263 | 12 | 0.6432 | 0.2336 | 0.6432 | 0.8020 |
|
| 58 |
+
| No log | 0.1474 | 14 | 0.7057 | 0.2494 | 0.7057 | 0.8400 |
|
| 59 |
+
| No log | 0.1684 | 16 | 0.6328 | 0.1786 | 0.6328 | 0.7955 |
|
| 60 |
+
| No log | 0.1895 | 18 | 0.6263 | 0.2526 | 0.6263 | 0.7914 |
|
| 61 |
+
| No log | 0.2105 | 20 | 0.6324 | 0.3492 | 0.6324 | 0.7952 |
|
| 62 |
+
| No log | 0.2316 | 22 | 0.5549 | 0.3187 | 0.5549 | 0.7449 |
|
| 63 |
+
| No log | 0.2526 | 24 | 0.4852 | 0.5267 | 0.4852 | 0.6966 |
|
| 64 |
+
| No log | 0.2737 | 26 | 0.4829 | 0.5577 | 0.4829 | 0.6949 |
|
| 65 |
+
| No log | 0.2947 | 28 | 0.4681 | 0.5501 | 0.4681 | 0.6842 |
|
| 66 |
+
| No log | 0.3158 | 30 | 0.4473 | 0.6330 | 0.4473 | 0.6688 |
|
| 67 |
+
| No log | 0.3368 | 32 | 0.4496 | 0.6648 | 0.4496 | 0.6705 |
|
| 68 |
+
| No log | 0.3579 | 34 | 0.4609 | 0.6448 | 0.4609 | 0.6789 |
|
| 69 |
+
| No log | 0.3789 | 36 | 0.4809 | 0.6349 | 0.4809 | 0.6935 |
|
| 70 |
+
| No log | 0.4 | 38 | 0.4771 | 0.6349 | 0.4771 | 0.6907 |
|
| 71 |
+
| No log | 0.4211 | 40 | 0.4738 | 0.6196 | 0.4738 | 0.6883 |
|
| 72 |
+
| No log | 0.4421 | 42 | 0.5360 | 0.5650 | 0.5360 | 0.7321 |
|
| 73 |
+
| No log | 0.4632 | 44 | 0.4647 | 0.5846 | 0.4647 | 0.6817 |
|
| 74 |
+
| No log | 0.4842 | 46 | 0.4549 | 0.5488 | 0.4549 | 0.6745 |
|
| 75 |
+
| No log | 0.5053 | 48 | 0.4804 | 0.5184 | 0.4804 | 0.6931 |
|
| 76 |
+
| No log | 0.5263 | 50 | 0.5030 | 0.5673 | 0.5030 | 0.7092 |
|
| 77 |
+
| No log | 0.5474 | 52 | 0.6013 | 0.5584 | 0.6013 | 0.7754 |
|
| 78 |
+
| No log | 0.5684 | 54 | 0.7522 | 0.5160 | 0.7522 | 0.8673 |
|
| 79 |
+
| No log | 0.5895 | 56 | 0.7234 | 0.5354 | 0.7234 | 0.8505 |
|
| 80 |
+
| No log | 0.6105 | 58 | 0.7729 | 0.5576 | 0.7729 | 0.8791 |
|
| 81 |
+
| No log | 0.6316 | 60 | 0.6893 | 0.5608 | 0.6893 | 0.8303 |
|
| 82 |
+
| No log | 0.6526 | 62 | 0.5996 | 0.5521 | 0.5996 | 0.7743 |
|
| 83 |
+
| No log | 0.6737 | 64 | 0.5796 | 0.5521 | 0.5796 | 0.7613 |
|
| 84 |
+
| No log | 0.6947 | 66 | 0.6225 | 0.5692 | 0.6225 | 0.7890 |
|
| 85 |
+
| No log | 0.7158 | 68 | 0.6841 | 0.5589 | 0.6841 | 0.8271 |
|
| 86 |
+
| No log | 0.7368 | 70 | 0.6777 | 0.5159 | 0.6777 | 0.8232 |
|
| 87 |
+
| No log | 0.7579 | 72 | 0.6000 | 0.6003 | 0.6000 | 0.7746 |
|
| 88 |
+
| No log | 0.7789 | 74 | 0.5561 | 0.5889 | 0.5561 | 0.7457 |
|
| 89 |
+
| No log | 0.8 | 76 | 0.5633 | 0.5784 | 0.5633 | 0.7505 |
|
| 90 |
+
| No log | 0.8211 | 78 | 0.5463 | 0.5840 | 0.5463 | 0.7391 |
|
| 91 |
+
| No log | 0.8421 | 80 | 0.5458 | 0.5744 | 0.5458 | 0.7388 |
|
| 92 |
+
| No log | 0.8632 | 82 | 0.6079 | 0.5278 | 0.6079 | 0.7797 |
|
| 93 |
+
| No log | 0.8842 | 84 | 0.7862 | 0.5757 | 0.7862 | 0.8867 |
|
| 94 |
+
| No log | 0.9053 | 86 | 0.7841 | 0.5526 | 0.7841 | 0.8855 |
|
| 95 |
+
| No log | 0.9263 | 88 | 0.6504 | 0.5632 | 0.6504 | 0.8065 |
|
| 96 |
+
| No log | 0.9474 | 90 | 0.5641 | 0.5117 | 0.5641 | 0.7511 |
|
| 97 |
+
| No log | 0.9684 | 92 | 0.5536 | 0.5149 | 0.5536 | 0.7440 |
|
| 98 |
+
| No log | 0.9895 | 94 | 0.6057 | 0.5042 | 0.6057 | 0.7783 |
|
| 99 |
+
| No log | 1.0105 | 96 | 0.7273 | 0.5322 | 0.7273 | 0.8528 |
|
| 100 |
+
| No log | 1.0316 | 98 | 0.9281 | 0.4456 | 0.9281 | 0.9634 |
|
| 101 |
+
| No log | 1.0526 | 100 | 1.0470 | 0.4297 | 1.0470 | 1.0232 |
|
| 102 |
+
| No log | 1.0737 | 102 | 1.0144 | 0.4966 | 1.0144 | 1.0072 |
|
| 103 |
+
| No log | 1.0947 | 104 | 0.8072 | 0.4288 | 0.8072 | 0.8984 |
|
| 104 |
+
| No log | 1.1158 | 106 | 0.5471 | 0.5591 | 0.5471 | 0.7397 |
|
| 105 |
+
| No log | 1.1368 | 108 | 0.5090 | 0.5379 | 0.5090 | 0.7135 |
|
| 106 |
+
| No log | 1.1579 | 110 | 0.5480 | 0.5042 | 0.5480 | 0.7403 |
|
| 107 |
+
| No log | 1.1789 | 112 | 0.6091 | 0.4369 | 0.6091 | 0.7805 |
|
| 108 |
+
| No log | 1.2 | 114 | 0.5837 | 0.5562 | 0.5837 | 0.7640 |
|
| 109 |
+
| No log | 1.2211 | 116 | 0.5166 | 0.6797 | 0.5166 | 0.7188 |
|
| 110 |
+
| No log | 1.2421 | 118 | 0.6081 | 0.5255 | 0.6081 | 0.7798 |
|
| 111 |
+
| No log | 1.2632 | 120 | 0.6127 | 0.5692 | 0.6127 | 0.7827 |
|
| 112 |
+
| No log | 1.2842 | 122 | 0.5917 | 0.5195 | 0.5917 | 0.7692 |
|
| 113 |
+
| No log | 1.3053 | 124 | 0.5468 | 0.5426 | 0.5468 | 0.7394 |
|
| 114 |
+
| No log | 1.3263 | 126 | 0.5668 | 0.5920 | 0.5668 | 0.7529 |
|
| 115 |
+
| No log | 1.3474 | 128 | 0.7194 | 0.4268 | 0.7194 | 0.8482 |
|
| 116 |
+
| No log | 1.3684 | 130 | 0.7812 | 0.4703 | 0.7812 | 0.8838 |
|
| 117 |
+
| No log | 1.3895 | 132 | 0.6732 | 0.4438 | 0.6732 | 0.8205 |
|
| 118 |
+
| No log | 1.4105 | 134 | 0.5920 | 0.4961 | 0.5920 | 0.7694 |
|
| 119 |
+
| No log | 1.4316 | 136 | 0.5428 | 0.6135 | 0.5428 | 0.7367 |
|
| 120 |
+
| No log | 1.4526 | 138 | 0.5440 | 0.5799 | 0.5440 | 0.7376 |
|
| 121 |
+
| No log | 1.4737 | 140 | 0.5887 | 0.5812 | 0.5887 | 0.7673 |
|
| 122 |
+
| No log | 1.4947 | 142 | 0.6512 | 0.5935 | 0.6512 | 0.8069 |
|
| 123 |
+
| No log | 1.5158 | 144 | 0.6504 | 0.6104 | 0.6504 | 0.8065 |
|
| 124 |
+
| No log | 1.5368 | 146 | 0.6439 | 0.5545 | 0.6439 | 0.8024 |
|
| 125 |
+
| No log | 1.5579 | 148 | 0.6111 | 0.6149 | 0.6111 | 0.7817 |
|
| 126 |
+
| No log | 1.5789 | 150 | 0.5937 | 0.5692 | 0.5937 | 0.7705 |
|
| 127 |
+
| No log | 1.6 | 152 | 0.5521 | 0.5262 | 0.5521 | 0.7430 |
|
| 128 |
+
| No log | 1.6211 | 154 | 0.5278 | 0.5103 | 0.5278 | 0.7265 |
|
| 129 |
+
| No log | 1.6421 | 156 | 0.5604 | 0.5845 | 0.5604 | 0.7486 |
|
| 130 |
+
| No log | 1.6632 | 158 | 0.6952 | 0.4704 | 0.6952 | 0.8338 |
|
| 131 |
+
| No log | 1.6842 | 160 | 0.8742 | 0.4267 | 0.8742 | 0.9350 |
|
| 132 |
+
| No log | 1.7053 | 162 | 0.8607 | 0.4713 | 0.8607 | 0.9278 |
|
| 133 |
+
| No log | 1.7263 | 164 | 0.7574 | 0.5340 | 0.7574 | 0.8703 |
|
| 134 |
+
| No log | 1.7474 | 166 | 0.7011 | 0.4705 | 0.7011 | 0.8373 |
|
| 135 |
+
| No log | 1.7684 | 168 | 0.5775 | 0.4728 | 0.5775 | 0.7599 |
|
| 136 |
+
| No log | 1.7895 | 170 | 0.5100 | 0.6004 | 0.5100 | 0.7141 |
|
| 137 |
+
| No log | 1.8105 | 172 | 0.5005 | 0.5996 | 0.5005 | 0.7075 |
|
| 138 |
+
| No log | 1.8316 | 174 | 0.5291 | 0.6052 | 0.5291 | 0.7274 |
|
| 139 |
+
| No log | 1.8526 | 176 | 0.5790 | 0.6197 | 0.5790 | 0.7609 |
|
| 140 |
+
| No log | 1.8737 | 178 | 0.6124 | 0.5863 | 0.6124 | 0.7826 |
|
| 141 |
+
| No log | 1.8947 | 180 | 0.6354 | 0.5560 | 0.6354 | 0.7971 |
|
| 142 |
+
| No log | 1.9158 | 182 | 0.5914 | 0.5546 | 0.5914 | 0.7690 |
|
| 143 |
+
| No log | 1.9368 | 184 | 0.5475 | 0.5156 | 0.5475 | 0.7399 |
|
| 144 |
+
| No log | 1.9579 | 186 | 0.5245 | 0.5195 | 0.5245 | 0.7242 |
|
| 145 |
+
| No log | 1.9789 | 188 | 0.5189 | 0.6052 | 0.5189 | 0.7203 |
|
| 146 |
+
| No log | 2.0 | 190 | 0.5453 | 0.6028 | 0.5453 | 0.7384 |
|
| 147 |
+
| No log | 2.0211 | 192 | 0.6117 | 0.5334 | 0.6117 | 0.7821 |
|
| 148 |
+
| No log | 2.0421 | 194 | 0.7300 | 0.5146 | 0.7300 | 0.8544 |
|
| 149 |
+
| No log | 2.0632 | 196 | 0.6740 | 0.5555 | 0.6740 | 0.8210 |
|
| 150 |
+
| No log | 2.0842 | 198 | 0.5656 | 0.6653 | 0.5656 | 0.7521 |
|
| 151 |
+
| No log | 2.1053 | 200 | 0.5405 | 0.6006 | 0.5405 | 0.7352 |
|
| 152 |
+
| No log | 2.1263 | 202 | 0.5182 | 0.5853 | 0.5182 | 0.7198 |
|
| 153 |
+
| No log | 2.1474 | 204 | 0.6585 | 0.5295 | 0.6585 | 0.8115 |
|
| 154 |
+
| No log | 2.1684 | 206 | 0.8847 | 0.3945 | 0.8847 | 0.9406 |
|
| 155 |
+
| No log | 2.1895 | 208 | 0.8924 | 0.2977 | 0.8924 | 0.9447 |
|
| 156 |
+
| No log | 2.2105 | 210 | 0.8114 | 0.3137 | 0.8114 | 0.9008 |
|
| 157 |
+
| No log | 2.2316 | 212 | 0.6558 | 0.4349 | 0.6558 | 0.8098 |
|
| 158 |
+
| No log | 2.2526 | 214 | 0.6528 | 0.5443 | 0.6528 | 0.8079 |
|
| 159 |
+
| No log | 2.2737 | 216 | 0.8157 | 0.5126 | 0.8157 | 0.9032 |
|
| 160 |
+
| No log | 2.2947 | 218 | 0.8733 | 0.5126 | 0.8733 | 0.9345 |
|
| 161 |
+
| No log | 2.3158 | 220 | 0.7559 | 0.5446 | 0.7559 | 0.8694 |
|
| 162 |
+
| No log | 2.3368 | 222 | 0.6838 | 0.5416 | 0.6838 | 0.8269 |
|
| 163 |
+
| No log | 2.3579 | 224 | 0.6330 | 0.5042 | 0.6330 | 0.7956 |
|
| 164 |
+
| No log | 2.3789 | 226 | 0.5971 | 0.5086 | 0.5971 | 0.7727 |
|
| 165 |
+
| No log | 2.4 | 228 | 0.6095 | 0.4835 | 0.6095 | 0.7807 |
|
| 166 |
+
| No log | 2.4211 | 230 | 0.6604 | 0.4424 | 0.6604 | 0.8126 |
|
| 167 |
+
| No log | 2.4421 | 232 | 0.6840 | 0.4587 | 0.6840 | 0.8270 |
|
| 168 |
+
| No log | 2.4632 | 234 | 0.7361 | 0.4450 | 0.7361 | 0.8579 |
|
| 169 |
+
| No log | 2.4842 | 236 | 0.6888 | 0.5163 | 0.6888 | 0.8299 |
|
| 170 |
+
| No log | 2.5053 | 238 | 0.6811 | 0.4877 | 0.6811 | 0.8253 |
|
| 171 |
+
| No log | 2.5263 | 240 | 0.7307 | 0.4992 | 0.7307 | 0.8548 |
|
| 172 |
+
| No log | 2.5474 | 242 | 0.6436 | 0.4665 | 0.6436 | 0.8022 |
|
| 173 |
+
| No log | 2.5684 | 244 | 0.5723 | 0.5140 | 0.5723 | 0.7565 |
|
| 174 |
+
| No log | 2.5895 | 246 | 0.6145 | 0.5326 | 0.6145 | 0.7839 |
|
| 175 |
+
| No log | 2.6105 | 248 | 0.6905 | 0.4738 | 0.6905 | 0.8310 |
|
| 176 |
+
| No log | 2.6316 | 250 | 0.7957 | 0.4409 | 0.7957 | 0.8920 |
|
| 177 |
+
| No log | 2.6526 | 252 | 0.7441 | 0.4296 | 0.7441 | 0.8626 |
|
| 178 |
+
| No log | 2.6737 | 254 | 0.7819 | 0.4133 | 0.7819 | 0.8843 |
|
| 179 |
+
| No log | 2.6947 | 256 | 0.8500 | 0.4186 | 0.8500 | 0.9220 |
|
| 180 |
+
| No log | 2.7158 | 258 | 0.7822 | 0.4096 | 0.7822 | 0.8844 |
|
| 181 |
+
| No log | 2.7368 | 260 | 0.7412 | 0.4580 | 0.7412 | 0.8609 |
|
| 182 |
+
| No log | 2.7579 | 262 | 0.8842 | 0.4376 | 0.8842 | 0.9403 |
|
| 183 |
+
| No log | 2.7789 | 264 | 0.8263 | 0.4604 | 0.8263 | 0.9090 |
|
| 184 |
+
| No log | 2.8 | 266 | 0.7685 | 0.4536 | 0.7685 | 0.8767 |
|
| 185 |
+
| No log | 2.8211 | 268 | 0.7210 | 0.4400 | 0.7210 | 0.8491 |
|
| 186 |
+
| No log | 2.8421 | 270 | 0.6655 | 0.4916 | 0.6655 | 0.8158 |
|
| 187 |
+
| No log | 2.8632 | 272 | 0.7550 | 0.4462 | 0.7550 | 0.8689 |
|
| 188 |
+
| No log | 2.8842 | 274 | 0.9170 | 0.4118 | 0.9170 | 0.9576 |
|
| 189 |
+
| No log | 2.9053 | 276 | 0.8120 | 0.4378 | 0.8120 | 0.9011 |
|
| 190 |
+
| No log | 2.9263 | 278 | 0.6768 | 0.5243 | 0.6768 | 0.8227 |
|
| 191 |
+
| No log | 2.9474 | 280 | 0.6640 | 0.5455 | 0.6640 | 0.8149 |
|
| 192 |
+
| No log | 2.9684 | 282 | 0.6908 | 0.4438 | 0.6908 | 0.8311 |
|
| 193 |
+
| No log | 2.9895 | 284 | 0.7249 | 0.3582 | 0.7249 | 0.8514 |
|
| 194 |
+
| No log | 3.0105 | 286 | 0.8802 | 0.3499 | 0.8802 | 0.9382 |
|
| 195 |
+
| No log | 3.0316 | 288 | 0.9180 | 0.3290 | 0.9180 | 0.9581 |
|
| 196 |
+
| No log | 3.0526 | 290 | 0.9864 | 0.4077 | 0.9864 | 0.9932 |
|
| 197 |
+
| No log | 3.0737 | 292 | 0.8252 | 0.3988 | 0.8252 | 0.9084 |
|
| 198 |
+
| No log | 3.0947 | 294 | 0.6790 | 0.3934 | 0.6790 | 0.8240 |
|
| 199 |
+
| No log | 3.1158 | 296 | 0.7364 | 0.4438 | 0.7364 | 0.8581 |
|
| 200 |
+
| No log | 3.1368 | 298 | 0.8636 | 0.3559 | 0.8636 | 0.9293 |
|
| 201 |
+
| No log | 3.1579 | 300 | 0.7871 | 0.3618 | 0.7871 | 0.8872 |
|
| 202 |
+
| No log | 3.1789 | 302 | 0.6323 | 0.4329 | 0.6323 | 0.7952 |
|
| 203 |
+
| No log | 3.2 | 304 | 0.6051 | 0.4430 | 0.6051 | 0.7779 |
|
| 204 |
+
| No log | 3.2211 | 306 | 0.6901 | 0.4592 | 0.6901 | 0.8308 |
|
| 205 |
+
| No log | 3.2421 | 308 | 0.8866 | 0.3928 | 0.8866 | 0.9416 |
|
| 206 |
+
| No log | 3.2632 | 310 | 0.9454 | 0.4021 | 0.9454 | 0.9723 |
|
| 207 |
+
| No log | 3.2842 | 312 | 0.7849 | 0.4250 | 0.7849 | 0.8860 |
|
| 208 |
+
| No log | 3.3053 | 314 | 0.7698 | 0.4396 | 0.7698 | 0.8774 |
|
| 209 |
+
| No log | 3.3263 | 316 | 0.7612 | 0.4396 | 0.7612 | 0.8725 |
|
| 210 |
+
| No log | 3.3474 | 318 | 0.8248 | 0.3868 | 0.8248 | 0.9082 |
|
| 211 |
+
| No log | 3.3684 | 320 | 0.8950 | 0.3697 | 0.8950 | 0.9460 |
|
| 212 |
+
| No log | 3.3895 | 322 | 0.7824 | 0.3868 | 0.7824 | 0.8845 |
|
| 213 |
+
| No log | 3.4105 | 324 | 0.6532 | 0.4014 | 0.6532 | 0.8082 |
|
| 214 |
+
| No log | 3.4316 | 326 | 0.6122 | 0.4479 | 0.6122 | 0.7824 |
|
| 215 |
+
| No log | 3.4526 | 328 | 0.6043 | 0.4491 | 0.6043 | 0.7774 |
|
| 216 |
+
| No log | 3.4737 | 330 | 0.7139 | 0.4228 | 0.7139 | 0.8450 |
|
| 217 |
+
| No log | 3.4947 | 332 | 0.8486 | 0.4149 | 0.8486 | 0.9212 |
|
| 218 |
+
| No log | 3.5158 | 334 | 0.8826 | 0.4091 | 0.8826 | 0.9395 |
|
| 219 |
+
| No log | 3.5368 | 336 | 0.7521 | 0.4364 | 0.7521 | 0.8672 |
|
| 220 |
+
| No log | 3.5579 | 338 | 0.6172 | 0.4123 | 0.6172 | 0.7856 |
|
| 221 |
+
| No log | 3.5789 | 340 | 0.5840 | 0.3894 | 0.5840 | 0.7642 |
|
| 222 |
+
| No log | 3.6 | 342 | 0.5994 | 0.3471 | 0.5994 | 0.7742 |
|
| 223 |
+
| No log | 3.6211 | 344 | 0.7126 | 0.3913 | 0.7126 | 0.8442 |
|
| 224 |
+
| No log | 3.6421 | 346 | 1.0080 | 0.3587 | 1.0080 | 1.0040 |
|
| 225 |
+
| No log | 3.6632 | 348 | 1.2029 | 0.3375 | 1.2029 | 1.0968 |
|
| 226 |
+
| No log | 3.6842 | 350 | 1.0850 | 0.3802 | 1.0850 | 1.0416 |
|
| 227 |
+
| No log | 3.7053 | 352 | 0.7979 | 0.4444 | 0.7979 | 0.8933 |
|
| 228 |
+
| No log | 3.7263 | 354 | 0.6039 | 0.3157 | 0.6039 | 0.7771 |
|
| 229 |
+
| No log | 3.7474 | 356 | 0.5297 | 0.4929 | 0.5297 | 0.7278 |
|
| 230 |
+
| No log | 3.7684 | 358 | 0.5307 | 0.5460 | 0.5307 | 0.7285 |
|
| 231 |
+
| No log | 3.7895 | 360 | 0.5688 | 0.5373 | 0.5688 | 0.7542 |
|
| 232 |
+
| No log | 3.8105 | 362 | 0.6340 | 0.4436 | 0.6340 | 0.7963 |
|
| 233 |
+
| No log | 3.8316 | 364 | 0.8068 | 0.4288 | 0.8068 | 0.8982 |
|
| 234 |
+
| No log | 3.8526 | 366 | 0.9895 | 0.3869 | 0.9895 | 0.9947 |
|
| 235 |
+
| No log | 3.8737 | 368 | 0.9366 | 0.3481 | 0.9366 | 0.9678 |
|
| 236 |
+
| No log | 3.8947 | 370 | 0.8875 | 0.3481 | 0.8875 | 0.9421 |
|
| 237 |
+
| No log | 3.9158 | 372 | 0.7824 | 0.3606 | 0.7824 | 0.8845 |
|
| 238 |
+
| No log | 3.9368 | 374 | 0.6491 | 0.3869 | 0.6491 | 0.8057 |
|
| 239 |
+
| No log | 3.9579 | 376 | 0.5338 | 0.4964 | 0.5338 | 0.7306 |
|
| 240 |
+
| No log | 3.9789 | 378 | 0.4938 | 0.5095 | 0.4938 | 0.7027 |
|
| 241 |
+
| No log | 4.0 | 380 | 0.4852 | 0.5604 | 0.4852 | 0.6966 |
|
| 242 |
+
| No log | 4.0211 | 382 | 0.5076 | 0.6040 | 0.5076 | 0.7125 |
|
| 243 |
+
| No log | 4.0421 | 384 | 0.5356 | 0.5877 | 0.5356 | 0.7318 |
|
| 244 |
+
| No log | 4.0632 | 386 | 0.5486 | 0.5709 | 0.5486 | 0.7407 |
|
| 245 |
+
| No log | 4.0842 | 388 | 0.5335 | 0.6200 | 0.5335 | 0.7304 |
|
| 246 |
+
| No log | 4.1053 | 390 | 0.5097 | 0.6419 | 0.5097 | 0.7139 |
|
| 247 |
+
| No log | 4.1263 | 392 | 0.4801 | 0.6492 | 0.4801 | 0.6929 |
|
| 248 |
+
| No log | 4.1474 | 394 | 0.4680 | 0.6060 | 0.4680 | 0.6841 |
|
| 249 |
+
| No log | 4.1684 | 396 | 0.4778 | 0.5819 | 0.4778 | 0.6912 |
|
| 250 |
+
| No log | 4.1895 | 398 | 0.5403 | 0.4745 | 0.5403 | 0.7351 |
|
| 251 |
+
| No log | 4.2105 | 400 | 0.5762 | 0.4521 | 0.5762 | 0.7590 |
|
| 252 |
+
| No log | 4.2316 | 402 | 0.6229 | 0.5103 | 0.6229 | 0.7892 |
|
| 253 |
+
| No log | 4.2526 | 404 | 0.5363 | 0.6293 | 0.5363 | 0.7323 |
|
| 254 |
+
| No log | 4.2737 | 406 | 0.4846 | 0.5934 | 0.4846 | 0.6961 |
|
| 255 |
+
| No log | 4.2947 | 408 | 0.4614 | 0.5671 | 0.4614 | 0.6792 |
|
| 256 |
+
| No log | 4.3158 | 410 | 0.4684 | 0.5289 | 0.4684 | 0.6844 |
|
| 257 |
+
| No log | 4.3368 | 412 | 0.4534 | 0.5631 | 0.4534 | 0.6734 |
|
| 258 |
+
| No log | 4.3579 | 414 | 0.4597 | 0.5631 | 0.4597 | 0.6780 |
|
| 259 |
+
| No log | 4.3789 | 416 | 0.4793 | 0.6087 | 0.4793 | 0.6923 |
|
| 260 |
+
| No log | 4.4 | 418 | 0.4660 | 0.6087 | 0.4660 | 0.6827 |
|
| 261 |
+
| No log | 4.4211 | 420 | 0.4350 | 0.6010 | 0.4350 | 0.6596 |
|
| 262 |
+
| No log | 4.4421 | 422 | 0.4415 | 0.5860 | 0.4415 | 0.6644 |
|
| 263 |
+
| No log | 4.4632 | 424 | 0.4417 | 0.6228 | 0.4417 | 0.6646 |
|
| 264 |
+
| No log | 4.4842 | 426 | 0.4644 | 0.6087 | 0.4644 | 0.6814 |
|
| 265 |
+
| No log | 4.5053 | 428 | 0.5250 | 0.6109 | 0.5250 | 0.7246 |
|
| 266 |
+
| No log | 4.5263 | 430 | 0.5344 | 0.5586 | 0.5344 | 0.7310 |
|
| 267 |
+
| No log | 4.5474 | 432 | 0.5401 | 0.4979 | 0.5401 | 0.7349 |
|
| 268 |
+
| No log | 4.5684 | 434 | 0.5062 | 0.5597 | 0.5062 | 0.7115 |
|
| 269 |
+
| No log | 4.5895 | 436 | 0.5115 | 0.5036 | 0.5115 | 0.7152 |
|
| 270 |
+
| No log | 4.6105 | 438 | 0.5372 | 0.5639 | 0.5372 | 0.7330 |
|
| 271 |
+
| No log | 4.6316 | 440 | 0.6197 | 0.4795 | 0.6197 | 0.7872 |
|
| 272 |
+
| No log | 4.6526 | 442 | 0.6326 | 0.52 | 0.6326 | 0.7954 |
|
| 273 |
+
| No log | 4.6737 | 444 | 0.5431 | 0.6096 | 0.5431 | 0.7370 |
|
| 274 |
+
| No log | 4.6947 | 446 | 0.4845 | 0.5345 | 0.4845 | 0.6960 |
|
| 275 |
+
| No log | 4.7158 | 448 | 0.4512 | 0.5648 | 0.4512 | 0.6718 |
|
| 276 |
+
| No log | 4.7368 | 450 | 0.4333 | 0.5648 | 0.4333 | 0.6583 |
|
| 277 |
+
| No log | 4.7579 | 452 | 0.4276 | 0.6307 | 0.4276 | 0.6539 |
|
| 278 |
+
| No log | 4.7789 | 454 | 0.4539 | 0.6187 | 0.4539 | 0.6737 |
|
| 279 |
+
| No log | 4.8 | 456 | 0.4717 | 0.6087 | 0.4717 | 0.6868 |
|
| 280 |
+
| No log | 4.8211 | 458 | 0.4746 | 0.6187 | 0.4746 | 0.6889 |
|
| 281 |
+
| No log | 4.8421 | 460 | 0.4990 | 0.5692 | 0.4990 | 0.7064 |
|
| 282 |
+
| No log | 4.8632 | 462 | 0.4903 | 0.5692 | 0.4903 | 0.7002 |
|
| 283 |
+
| No log | 4.8842 | 464 | 0.4601 | 0.5980 | 0.4601 | 0.6783 |
|
| 284 |
+
| No log | 4.9053 | 466 | 0.4494 | 0.5897 | 0.4494 | 0.6704 |
|
| 285 |
+
| No log | 4.9263 | 468 | 0.4804 | 0.5617 | 0.4804 | 0.6931 |
|
| 286 |
+
| No log | 4.9474 | 470 | 0.5055 | 0.5639 | 0.5055 | 0.7110 |
|
| 287 |
+
| No log | 4.9684 | 472 | 0.5630 | 0.5293 | 0.5630 | 0.7503 |
|
| 288 |
+
| No log | 4.9895 | 474 | 0.5401 | 0.5510 | 0.5401 | 0.7349 |
|
| 289 |
+
| No log | 5.0105 | 476 | 0.5519 | 0.5471 | 0.5519 | 0.7429 |
|
| 290 |
+
| No log | 5.0316 | 478 | 0.5332 | 0.5735 | 0.5332 | 0.7302 |
|
| 291 |
+
| No log | 5.0526 | 480 | 0.5166 | 0.5261 | 0.5166 | 0.7188 |
|
| 292 |
+
| No log | 5.0737 | 482 | 0.4571 | 0.6214 | 0.4571 | 0.6761 |
|
| 293 |
+
| No log | 5.0947 | 484 | 0.4499 | 0.6215 | 0.4499 | 0.6707 |
|
| 294 |
+
| No log | 5.1158 | 486 | 0.4558 | 0.6215 | 0.4558 | 0.6751 |
|
| 295 |
+
| No log | 5.1368 | 488 | 0.4551 | 0.6833 | 0.4551 | 0.6746 |
|
| 296 |
+
| No log | 5.1579 | 490 | 0.4513 | 0.5980 | 0.4513 | 0.6718 |
|
| 297 |
+
| No log | 5.1789 | 492 | 0.4749 | 0.5411 | 0.4749 | 0.6891 |
|
| 298 |
+
| No log | 5.2 | 494 | 0.5059 | 0.5368 | 0.5059 | 0.7112 |
|
| 299 |
+
| No log | 5.2211 | 496 | 0.4926 | 0.5957 | 0.4926 | 0.7018 |
|
| 300 |
+
| No log | 5.2421 | 498 | 0.4413 | 0.6339 | 0.4413 | 0.6643 |
|
| 301 |
+
| 0.3127 | 5.2632 | 500 | 0.4456 | 0.6087 | 0.4456 | 0.6676 |
|
| 302 |
+
| 0.3127 | 5.2842 | 502 | 0.4528 | 0.6292 | 0.4528 | 0.6729 |
|
| 303 |
+
| 0.3127 | 5.3053 | 504 | 0.4519 | 0.6542 | 0.4519 | 0.6722 |
|
| 304 |
+
| 0.3127 | 5.3263 | 506 | 0.4849 | 0.6430 | 0.4849 | 0.6963 |
|
| 305 |
+
| 0.3127 | 5.3474 | 508 | 0.4938 | 0.6010 | 0.4938 | 0.7027 |
|
| 306 |
+
| 0.3127 | 5.3684 | 510 | 0.4815 | 0.6355 | 0.4815 | 0.6939 |
|
| 307 |
+
| 0.3127 | 5.3895 | 512 | 0.4570 | 0.6458 | 0.4570 | 0.6760 |
|
| 308 |
+
| 0.3127 | 5.4105 | 514 | 0.4560 | 0.6289 | 0.4560 | 0.6753 |
|
| 309 |
+
| 0.3127 | 5.4316 | 516 | 0.4629 | 0.6346 | 0.4629 | 0.6804 |
|
| 310 |
+
| 0.3127 | 5.4526 | 518 | 0.5063 | 0.5524 | 0.5063 | 0.7116 |
|
| 311 |
+
| 0.3127 | 5.4737 | 520 | 0.5293 | 0.5524 | 0.5293 | 0.7276 |
|
| 312 |
+
| 0.3127 | 5.4947 | 522 | 0.4961 | 0.5871 | 0.4961 | 0.7043 |
|
| 313 |
+
| 0.3127 | 5.5158 | 524 | 0.4721 | 0.6423 | 0.4721 | 0.6871 |
|
| 314 |
+
| 0.3127 | 5.5368 | 526 | 0.4660 | 0.6423 | 0.4660 | 0.6826 |
|
| 315 |
+
| 0.3127 | 5.5579 | 528 | 0.4769 | 0.6239 | 0.4769 | 0.6906 |
|
| 316 |
+
| 0.3127 | 5.5789 | 530 | 0.5229 | 0.6248 | 0.5229 | 0.7231 |
|
| 317 |
+
| 0.3127 | 5.6 | 532 | 0.5575 | 0.5716 | 0.5575 | 0.7466 |
|
| 318 |
+
| 0.3127 | 5.6211 | 534 | 0.5318 | 0.6325 | 0.5318 | 0.7293 |
|
| 319 |
+
| 0.3127 | 5.6421 | 536 | 0.4878 | 0.6251 | 0.4878 | 0.6984 |
|
| 320 |
+
| 0.3127 | 5.6632 | 538 | 0.4693 | 0.5697 | 0.4693 | 0.6850 |
|
| 321 |
+
| 0.3127 | 5.6842 | 540 | 0.4518 | 0.6298 | 0.4518 | 0.6722 |
|
| 322 |
+
| 0.3127 | 5.7053 | 542 | 0.4469 | 0.6265 | 0.4469 | 0.6685 |
|
| 323 |
+
| 0.3127 | 5.7263 | 544 | 0.4555 | 0.5923 | 0.4555 | 0.6749 |
|
| 324 |
+
| 0.3127 | 5.7474 | 546 | 0.4992 | 0.5817 | 0.4992 | 0.7065 |
|
| 325 |
+
| 0.3127 | 5.7684 | 548 | 0.6304 | 0.4536 | 0.6304 | 0.7940 |
|
| 326 |
+
| 0.3127 | 5.7895 | 550 | 0.8616 | 0.4213 | 0.8616 | 0.9282 |
|
| 327 |
+
| 0.3127 | 5.8105 | 552 | 0.9024 | 0.4213 | 0.9024 | 0.9499 |
|
| 328 |
+
|
| 329 |
+
|
| 330 |
+
### Framework versions
|
| 331 |
+
|
| 332 |
+
- Transformers 4.44.2
|
| 333 |
+
- Pytorch 2.4.0+cu118
|
| 334 |
+
- Datasets 2.21.0
|
| 335 |
+
- 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:ca5519b37a816483072696a40c31e3a2ecf539e0c83b93356ae266ec9f8d5230
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e77a7afee0fc92b83e6721a5d6e83f09233bbb061b71d805fa89cbc219dd045
|
| 3 |
+
size 5304
|