Training in progress, step 500
Browse files- README.md +337 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_run1_AugV5_k11_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_run1_AugV5_k11_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: 0.7216
|
| 19 |
+
- Qwk: 0.3324
|
| 20 |
+
- Mse: 0.7216
|
| 21 |
+
- Rmse: 0.8495
|
| 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 | 0.0364 | 2 | 2.5668 | -0.0262 | 2.5668 | 1.6021 |
|
| 53 |
+
| No log | 0.0727 | 4 | 1.6186 | 0.0789 | 1.6186 | 1.2723 |
|
| 54 |
+
| No log | 0.1091 | 6 | 0.8064 | 0.1770 | 0.8064 | 0.8980 |
|
| 55 |
+
| No log | 0.1455 | 8 | 0.9287 | -0.0963 | 0.9287 | 0.9637 |
|
| 56 |
+
| No log | 0.1818 | 10 | 0.9986 | 0.2142 | 0.9986 | 0.9993 |
|
| 57 |
+
| No log | 0.2182 | 12 | 1.0884 | 0.2121 | 1.0884 | 1.0433 |
|
| 58 |
+
| No log | 0.2545 | 14 | 1.1141 | 0.2121 | 1.1141 | 1.0555 |
|
| 59 |
+
| No log | 0.2909 | 16 | 1.1174 | 0.1723 | 1.1174 | 1.0571 |
|
| 60 |
+
| No log | 0.3273 | 18 | 0.9435 | 0.1183 | 0.9435 | 0.9714 |
|
| 61 |
+
| No log | 0.3636 | 20 | 0.8515 | -0.0054 | 0.8515 | 0.9228 |
|
| 62 |
+
| No log | 0.4 | 22 | 0.7603 | 0.1863 | 0.7603 | 0.8720 |
|
| 63 |
+
| No log | 0.4364 | 24 | 0.7092 | 0.2606 | 0.7092 | 0.8422 |
|
| 64 |
+
| No log | 0.4727 | 26 | 0.8626 | 0.0295 | 0.8626 | 0.9288 |
|
| 65 |
+
| No log | 0.5091 | 28 | 0.9564 | 0.0344 | 0.9564 | 0.9779 |
|
| 66 |
+
| No log | 0.5455 | 30 | 0.9297 | 0.0653 | 0.9297 | 0.9642 |
|
| 67 |
+
| No log | 0.5818 | 32 | 1.0498 | 0.2635 | 1.0498 | 1.0246 |
|
| 68 |
+
| No log | 0.6182 | 34 | 0.9536 | 0.3225 | 0.9536 | 0.9765 |
|
| 69 |
+
| No log | 0.6545 | 36 | 0.7721 | 0.3675 | 0.7721 | 0.8787 |
|
| 70 |
+
| No log | 0.6909 | 38 | 0.6464 | 0.2930 | 0.6464 | 0.8040 |
|
| 71 |
+
| No log | 0.7273 | 40 | 0.6907 | 0.1904 | 0.6907 | 0.8311 |
|
| 72 |
+
| No log | 0.7636 | 42 | 0.6339 | 0.2884 | 0.6339 | 0.7962 |
|
| 73 |
+
| No log | 0.8 | 44 | 0.6163 | 0.3789 | 0.6163 | 0.7851 |
|
| 74 |
+
| No log | 0.8364 | 46 | 0.7464 | 0.3359 | 0.7464 | 0.8639 |
|
| 75 |
+
| No log | 0.8727 | 48 | 0.9303 | 0.3945 | 0.9303 | 0.9645 |
|
| 76 |
+
| No log | 0.9091 | 50 | 1.0772 | 0.2280 | 1.0772 | 1.0379 |
|
| 77 |
+
| No log | 0.9455 | 52 | 1.0092 | 0.2271 | 1.0092 | 1.0046 |
|
| 78 |
+
| No log | 0.9818 | 54 | 0.7104 | 0.3155 | 0.7104 | 0.8429 |
|
| 79 |
+
| No log | 1.0182 | 56 | 0.6345 | 0.4289 | 0.6345 | 0.7965 |
|
| 80 |
+
| No log | 1.0545 | 58 | 0.6185 | 0.5131 | 0.6185 | 0.7864 |
|
| 81 |
+
| No log | 1.0909 | 60 | 0.8405 | 0.3503 | 0.8405 | 0.9168 |
|
| 82 |
+
| No log | 1.1273 | 62 | 1.0543 | 0.3572 | 1.0543 | 1.0268 |
|
| 83 |
+
| No log | 1.1636 | 64 | 0.9688 | 0.4051 | 0.9688 | 0.9843 |
|
| 84 |
+
| No log | 1.2 | 66 | 0.7046 | 0.4451 | 0.7046 | 0.8394 |
|
| 85 |
+
| No log | 1.2364 | 68 | 0.6039 | 0.4595 | 0.6039 | 0.7771 |
|
| 86 |
+
| No log | 1.2727 | 70 | 0.7212 | 0.4003 | 0.7212 | 0.8493 |
|
| 87 |
+
| No log | 1.3091 | 72 | 0.6175 | 0.3383 | 0.6175 | 0.7858 |
|
| 88 |
+
| No log | 1.3455 | 74 | 0.5764 | 0.4419 | 0.5764 | 0.7592 |
|
| 89 |
+
| No log | 1.3818 | 76 | 0.7278 | 0.3819 | 0.7278 | 0.8531 |
|
| 90 |
+
| No log | 1.4182 | 78 | 0.8167 | 0.3473 | 0.8167 | 0.9037 |
|
| 91 |
+
| No log | 1.4545 | 80 | 0.8011 | 0.3825 | 0.8011 | 0.8950 |
|
| 92 |
+
| No log | 1.4909 | 82 | 0.6381 | 0.4662 | 0.6381 | 0.7988 |
|
| 93 |
+
| No log | 1.5273 | 84 | 0.6224 | 0.2476 | 0.6224 | 0.7889 |
|
| 94 |
+
| No log | 1.5636 | 86 | 0.6353 | 0.2476 | 0.6353 | 0.7970 |
|
| 95 |
+
| No log | 1.6 | 88 | 0.7101 | 0.3819 | 0.7101 | 0.8427 |
|
| 96 |
+
| No log | 1.6364 | 90 | 1.0804 | 0.3292 | 1.0804 | 1.0394 |
|
| 97 |
+
| No log | 1.6727 | 92 | 1.1114 | 0.3175 | 1.1114 | 1.0542 |
|
| 98 |
+
| No log | 1.7091 | 94 | 0.7990 | 0.3810 | 0.7990 | 0.8939 |
|
| 99 |
+
| No log | 1.7455 | 96 | 0.6547 | 0.5508 | 0.6547 | 0.8091 |
|
| 100 |
+
| No log | 1.7818 | 98 | 0.5964 | 0.5201 | 0.5964 | 0.7723 |
|
| 101 |
+
| No log | 1.8182 | 100 | 0.7306 | 0.4511 | 0.7306 | 0.8547 |
|
| 102 |
+
| No log | 1.8545 | 102 | 0.8064 | 0.3849 | 0.8064 | 0.8980 |
|
| 103 |
+
| No log | 1.8909 | 104 | 0.6583 | 0.4862 | 0.6583 | 0.8113 |
|
| 104 |
+
| No log | 1.9273 | 106 | 0.5405 | 0.5876 | 0.5405 | 0.7352 |
|
| 105 |
+
| No log | 1.9636 | 108 | 0.5616 | 0.4731 | 0.5616 | 0.7494 |
|
| 106 |
+
| No log | 2.0 | 110 | 0.6952 | 0.4404 | 0.6952 | 0.8338 |
|
| 107 |
+
| No log | 2.0364 | 112 | 0.6749 | 0.4404 | 0.6749 | 0.8215 |
|
| 108 |
+
| No log | 2.0727 | 114 | 0.5775 | 0.5139 | 0.5775 | 0.7599 |
|
| 109 |
+
| No log | 2.1091 | 116 | 0.5123 | 0.5836 | 0.5123 | 0.7157 |
|
| 110 |
+
| No log | 2.1455 | 118 | 0.5329 | 0.5327 | 0.5329 | 0.7300 |
|
| 111 |
+
| No log | 2.1818 | 120 | 0.5067 | 0.6201 | 0.5067 | 0.7119 |
|
| 112 |
+
| No log | 2.2182 | 122 | 0.4733 | 0.5899 | 0.4733 | 0.6879 |
|
| 113 |
+
| No log | 2.2545 | 124 | 0.4633 | 0.5899 | 0.4633 | 0.6806 |
|
| 114 |
+
| No log | 2.2909 | 126 | 0.4874 | 0.5980 | 0.4874 | 0.6981 |
|
| 115 |
+
| No log | 2.3273 | 128 | 0.6341 | 0.5803 | 0.6341 | 0.7963 |
|
| 116 |
+
| No log | 2.3636 | 130 | 0.9349 | 0.3939 | 0.9349 | 0.9669 |
|
| 117 |
+
| No log | 2.4 | 132 | 0.9988 | 0.3886 | 0.9988 | 0.9994 |
|
| 118 |
+
| No log | 2.4364 | 134 | 0.7376 | 0.4852 | 0.7376 | 0.8589 |
|
| 119 |
+
| No log | 2.4727 | 136 | 0.6218 | 0.4295 | 0.6218 | 0.7885 |
|
| 120 |
+
| No log | 2.5091 | 138 | 0.6910 | 0.4457 | 0.6910 | 0.8312 |
|
| 121 |
+
| No log | 2.5455 | 140 | 0.7062 | 0.4385 | 0.7062 | 0.8403 |
|
| 122 |
+
| No log | 2.5818 | 142 | 0.6127 | 0.4819 | 0.6127 | 0.7827 |
|
| 123 |
+
| No log | 2.6182 | 144 | 0.6693 | 0.4512 | 0.6693 | 0.8181 |
|
| 124 |
+
| No log | 2.6545 | 146 | 0.6879 | 0.4275 | 0.6879 | 0.8294 |
|
| 125 |
+
| No log | 2.6909 | 148 | 0.6747 | 0.4349 | 0.6747 | 0.8214 |
|
| 126 |
+
| No log | 2.7273 | 150 | 0.5633 | 0.5140 | 0.5633 | 0.7505 |
|
| 127 |
+
| No log | 2.7636 | 152 | 0.4731 | 0.6443 | 0.4731 | 0.6878 |
|
| 128 |
+
| No log | 2.8 | 154 | 0.4769 | 0.6241 | 0.4769 | 0.6906 |
|
| 129 |
+
| No log | 2.8364 | 156 | 0.5431 | 0.5357 | 0.5431 | 0.7369 |
|
| 130 |
+
| No log | 2.8727 | 158 | 0.7679 | 0.5190 | 0.7679 | 0.8763 |
|
| 131 |
+
| No log | 2.9091 | 160 | 0.9716 | 0.4297 | 0.9716 | 0.9857 |
|
| 132 |
+
| No log | 2.9455 | 162 | 0.8349 | 0.3753 | 0.8349 | 0.9137 |
|
| 133 |
+
| No log | 2.9818 | 164 | 0.6645 | 0.5292 | 0.6645 | 0.8152 |
|
| 134 |
+
| No log | 3.0182 | 166 | 0.6017 | 0.4997 | 0.6017 | 0.7757 |
|
| 135 |
+
| No log | 3.0545 | 168 | 0.6169 | 0.4664 | 0.6169 | 0.7854 |
|
| 136 |
+
| No log | 3.0909 | 170 | 0.6719 | 0.4438 | 0.6719 | 0.8197 |
|
| 137 |
+
| No log | 3.1273 | 172 | 0.5408 | 0.5158 | 0.5408 | 0.7354 |
|
| 138 |
+
| No log | 3.1636 | 174 | 0.4687 | 0.5104 | 0.4687 | 0.6846 |
|
| 139 |
+
| No log | 3.2 | 176 | 0.4838 | 0.5403 | 0.4838 | 0.6955 |
|
| 140 |
+
| No log | 3.2364 | 178 | 0.6183 | 0.4930 | 0.6183 | 0.7863 |
|
| 141 |
+
| No log | 3.2727 | 180 | 0.6507 | 0.4930 | 0.6507 | 0.8066 |
|
| 142 |
+
| No log | 3.3091 | 182 | 0.7969 | 0.3593 | 0.7969 | 0.8927 |
|
| 143 |
+
| No log | 3.3455 | 184 | 0.7316 | 0.4277 | 0.7316 | 0.8553 |
|
| 144 |
+
| No log | 3.3818 | 186 | 0.6744 | 0.4404 | 0.6744 | 0.8212 |
|
| 145 |
+
| No log | 3.4182 | 188 | 0.6077 | 0.4329 | 0.6077 | 0.7795 |
|
| 146 |
+
| No log | 3.4545 | 190 | 0.6733 | 0.4175 | 0.6733 | 0.8206 |
|
| 147 |
+
| No log | 3.4909 | 192 | 0.6654 | 0.4521 | 0.6654 | 0.8157 |
|
| 148 |
+
| No log | 3.5273 | 194 | 0.5251 | 0.5516 | 0.5251 | 0.7246 |
|
| 149 |
+
| No log | 3.5636 | 196 | 0.4870 | 0.5904 | 0.4870 | 0.6979 |
|
| 150 |
+
| No log | 3.6 | 198 | 0.5362 | 0.5627 | 0.5362 | 0.7323 |
|
| 151 |
+
| No log | 3.6364 | 200 | 0.4710 | 0.6053 | 0.4710 | 0.6863 |
|
| 152 |
+
| No log | 3.6727 | 202 | 0.6025 | 0.5101 | 0.6025 | 0.7762 |
|
| 153 |
+
| No log | 3.7091 | 204 | 0.7373 | 0.4652 | 0.7373 | 0.8587 |
|
| 154 |
+
| No log | 3.7455 | 206 | 0.6025 | 0.5045 | 0.6025 | 0.7762 |
|
| 155 |
+
| No log | 3.7818 | 208 | 0.5025 | 0.5289 | 0.5025 | 0.7089 |
|
| 156 |
+
| No log | 3.8182 | 210 | 0.4745 | 0.6037 | 0.4745 | 0.6888 |
|
| 157 |
+
| No log | 3.8545 | 212 | 0.4815 | 0.5955 | 0.4815 | 0.6939 |
|
| 158 |
+
| No log | 3.8909 | 214 | 0.5284 | 0.5498 | 0.5284 | 0.7269 |
|
| 159 |
+
| No log | 3.9273 | 216 | 0.6638 | 0.4493 | 0.6638 | 0.8148 |
|
| 160 |
+
| No log | 3.9636 | 218 | 0.9092 | 0.3632 | 0.9092 | 0.9535 |
|
| 161 |
+
| No log | 4.0 | 220 | 0.8585 | 0.3431 | 0.8585 | 0.9265 |
|
| 162 |
+
| No log | 4.0364 | 222 | 0.6861 | 0.3538 | 0.6861 | 0.8283 |
|
| 163 |
+
| No log | 4.0727 | 224 | 0.6867 | 0.3538 | 0.6867 | 0.8287 |
|
| 164 |
+
| No log | 4.1091 | 226 | 0.8179 | 0.2876 | 0.8179 | 0.9044 |
|
| 165 |
+
| No log | 4.1455 | 228 | 0.8508 | 0.3059 | 0.8508 | 0.9224 |
|
| 166 |
+
| No log | 4.1818 | 230 | 0.8845 | 0.3010 | 0.8845 | 0.9405 |
|
| 167 |
+
| No log | 4.2182 | 232 | 0.8435 | 0.3650 | 0.8435 | 0.9184 |
|
| 168 |
+
| No log | 4.2545 | 234 | 0.7567 | 0.4096 | 0.7567 | 0.8699 |
|
| 169 |
+
| No log | 4.2909 | 236 | 0.6673 | 0.4064 | 0.6673 | 0.8169 |
|
| 170 |
+
| No log | 4.3273 | 238 | 0.5692 | 0.4582 | 0.5692 | 0.7545 |
|
| 171 |
+
| No log | 4.3636 | 240 | 0.5634 | 0.4167 | 0.5634 | 0.7506 |
|
| 172 |
+
| No log | 4.4 | 242 | 0.5669 | 0.4664 | 0.5669 | 0.7529 |
|
| 173 |
+
| No log | 4.4364 | 244 | 0.5830 | 0.4947 | 0.5830 | 0.7635 |
|
| 174 |
+
| No log | 4.4727 | 246 | 0.6223 | 0.4992 | 0.6223 | 0.7889 |
|
| 175 |
+
| No log | 4.5091 | 248 | 0.7348 | 0.4526 | 0.7348 | 0.8572 |
|
| 176 |
+
| No log | 4.5455 | 250 | 0.7955 | 0.4639 | 0.7955 | 0.8919 |
|
| 177 |
+
| No log | 4.5818 | 252 | 0.7059 | 0.4124 | 0.7059 | 0.8402 |
|
| 178 |
+
| No log | 4.6182 | 254 | 0.6313 | 0.4133 | 0.6313 | 0.7945 |
|
| 179 |
+
| No log | 4.6545 | 256 | 0.5783 | 0.4175 | 0.5783 | 0.7605 |
|
| 180 |
+
| No log | 4.6909 | 258 | 0.6250 | 0.3782 | 0.6250 | 0.7906 |
|
| 181 |
+
| No log | 4.7273 | 260 | 0.6551 | 0.4186 | 0.6551 | 0.8094 |
|
| 182 |
+
| No log | 4.7636 | 262 | 0.7316 | 0.4465 | 0.7316 | 0.8554 |
|
| 183 |
+
| No log | 4.8 | 264 | 0.7313 | 0.4409 | 0.7313 | 0.8552 |
|
| 184 |
+
| No log | 4.8364 | 266 | 0.6554 | 0.4085 | 0.6554 | 0.8095 |
|
| 185 |
+
| No log | 4.8727 | 268 | 0.6357 | 0.4153 | 0.6357 | 0.7973 |
|
| 186 |
+
| No log | 4.9091 | 270 | 0.5635 | 0.4502 | 0.5635 | 0.7507 |
|
| 187 |
+
| No log | 4.9455 | 272 | 0.5644 | 0.4502 | 0.5644 | 0.7512 |
|
| 188 |
+
| No log | 4.9818 | 274 | 0.6429 | 0.4114 | 0.6429 | 0.8018 |
|
| 189 |
+
| No log | 5.0182 | 276 | 0.5799 | 0.4887 | 0.5799 | 0.7615 |
|
| 190 |
+
| No log | 5.0545 | 278 | 0.4983 | 0.5934 | 0.4983 | 0.7059 |
|
| 191 |
+
| No log | 5.0909 | 280 | 0.4301 | 0.6843 | 0.4301 | 0.6558 |
|
| 192 |
+
| No log | 5.1273 | 282 | 0.4387 | 0.6964 | 0.4387 | 0.6623 |
|
| 193 |
+
| No log | 5.1636 | 284 | 0.4644 | 0.5980 | 0.4644 | 0.6815 |
|
| 194 |
+
| No log | 5.2 | 286 | 0.6387 | 0.3913 | 0.6387 | 0.7992 |
|
| 195 |
+
| No log | 5.2364 | 288 | 0.7878 | 0.4156 | 0.7878 | 0.8876 |
|
| 196 |
+
| No log | 5.2727 | 290 | 0.6647 | 0.4462 | 0.6647 | 0.8153 |
|
| 197 |
+
| No log | 5.3091 | 292 | 0.4729 | 0.6201 | 0.4729 | 0.6877 |
|
| 198 |
+
| No log | 5.3455 | 294 | 0.4454 | 0.6620 | 0.4454 | 0.6674 |
|
| 199 |
+
| No log | 5.3818 | 296 | 0.5446 | 0.5040 | 0.5446 | 0.7380 |
|
| 200 |
+
| No log | 5.4182 | 298 | 0.8751 | 0.4060 | 0.8751 | 0.9354 |
|
| 201 |
+
| No log | 5.4545 | 300 | 1.0284 | 0.4105 | 1.0284 | 1.0141 |
|
| 202 |
+
| No log | 5.4909 | 302 | 0.9559 | 0.4083 | 0.9559 | 0.9777 |
|
| 203 |
+
| No log | 5.5273 | 304 | 0.6580 | 0.4992 | 0.6580 | 0.8112 |
|
| 204 |
+
| No log | 5.5636 | 306 | 0.4731 | 0.6408 | 0.4731 | 0.6878 |
|
| 205 |
+
| No log | 5.6 | 308 | 0.4777 | 0.5995 | 0.4777 | 0.6912 |
|
| 206 |
+
| No log | 5.6364 | 310 | 0.6012 | 0.5760 | 0.6012 | 0.7754 |
|
| 207 |
+
| No log | 5.6727 | 312 | 0.8549 | 0.4491 | 0.8549 | 0.9246 |
|
| 208 |
+
| No log | 5.7091 | 314 | 0.8647 | 0.4491 | 0.8647 | 0.9299 |
|
| 209 |
+
| No log | 5.7455 | 316 | 0.6772 | 0.4867 | 0.6772 | 0.8229 |
|
| 210 |
+
| No log | 5.7818 | 318 | 0.5447 | 0.5591 | 0.5447 | 0.7380 |
|
| 211 |
+
| No log | 5.8182 | 320 | 0.5739 | 0.5308 | 0.5739 | 0.7576 |
|
| 212 |
+
| No log | 5.8545 | 322 | 0.6214 | 0.4755 | 0.6214 | 0.7883 |
|
| 213 |
+
| No log | 5.8909 | 324 | 0.6335 | 0.4223 | 0.6335 | 0.7960 |
|
| 214 |
+
| No log | 5.9273 | 326 | 0.6209 | 0.4275 | 0.6209 | 0.7879 |
|
| 215 |
+
| No log | 5.9636 | 328 | 0.6749 | 0.4502 | 0.6749 | 0.8215 |
|
| 216 |
+
| No log | 6.0 | 330 | 0.6873 | 0.4502 | 0.6873 | 0.8290 |
|
| 217 |
+
| No log | 6.0364 | 332 | 0.7380 | 0.4161 | 0.7380 | 0.8590 |
|
| 218 |
+
| No log | 6.0727 | 334 | 0.6566 | 0.4438 | 0.6566 | 0.8103 |
|
| 219 |
+
| No log | 6.1091 | 336 | 0.5265 | 0.5736 | 0.5265 | 0.7256 |
|
| 220 |
+
| No log | 6.1455 | 338 | 0.4922 | 0.6067 | 0.4922 | 0.7016 |
|
| 221 |
+
| No log | 6.1818 | 340 | 0.5095 | 0.5867 | 0.5095 | 0.7138 |
|
| 222 |
+
| No log | 6.2182 | 342 | 0.5544 | 0.5063 | 0.5544 | 0.7446 |
|
| 223 |
+
| No log | 6.2545 | 344 | 0.5864 | 0.4502 | 0.5864 | 0.7658 |
|
| 224 |
+
| No log | 6.2909 | 346 | 0.6216 | 0.4502 | 0.6216 | 0.7884 |
|
| 225 |
+
| No log | 6.3273 | 348 | 0.5656 | 0.4582 | 0.5656 | 0.7521 |
|
| 226 |
+
| No log | 6.3636 | 350 | 0.5583 | 0.4582 | 0.5583 | 0.7472 |
|
| 227 |
+
| No log | 6.4 | 352 | 0.5887 | 0.4587 | 0.5887 | 0.7673 |
|
| 228 |
+
| No log | 6.4364 | 354 | 0.6389 | 0.4870 | 0.6389 | 0.7993 |
|
| 229 |
+
| No log | 6.4727 | 356 | 0.7503 | 0.4640 | 0.7503 | 0.8662 |
|
| 230 |
+
| No log | 6.5091 | 358 | 0.6832 | 0.5504 | 0.6832 | 0.8266 |
|
| 231 |
+
| No log | 6.5455 | 360 | 0.5235 | 0.5259 | 0.5235 | 0.7235 |
|
| 232 |
+
| No log | 6.5818 | 362 | 0.4206 | 0.6705 | 0.4206 | 0.6486 |
|
| 233 |
+
| No log | 6.6182 | 364 | 0.4173 | 0.6852 | 0.4173 | 0.6460 |
|
| 234 |
+
| No log | 6.6545 | 366 | 0.4190 | 0.7066 | 0.4190 | 0.6473 |
|
| 235 |
+
| No log | 6.6909 | 368 | 0.4278 | 0.6082 | 0.4278 | 0.6541 |
|
| 236 |
+
| No log | 6.7273 | 370 | 0.5136 | 0.5379 | 0.5136 | 0.7166 |
|
| 237 |
+
| No log | 6.7636 | 372 | 0.5574 | 0.4827 | 0.5574 | 0.7466 |
|
| 238 |
+
| No log | 6.8 | 374 | 0.5194 | 0.5252 | 0.5194 | 0.7207 |
|
| 239 |
+
| No log | 6.8364 | 376 | 0.5117 | 0.5349 | 0.5117 | 0.7154 |
|
| 240 |
+
| No log | 6.8727 | 378 | 0.5059 | 0.5290 | 0.5059 | 0.7112 |
|
| 241 |
+
| No log | 6.9091 | 380 | 0.5271 | 0.5252 | 0.5271 | 0.7260 |
|
| 242 |
+
| No log | 6.9455 | 382 | 0.6224 | 0.3847 | 0.6224 | 0.7890 |
|
| 243 |
+
| No log | 6.9818 | 384 | 0.7053 | 0.3613 | 0.7053 | 0.8398 |
|
| 244 |
+
| No log | 7.0182 | 386 | 0.6516 | 0.3973 | 0.6516 | 0.8072 |
|
| 245 |
+
| No log | 7.0545 | 388 | 0.4918 | 0.5965 | 0.4918 | 0.7013 |
|
| 246 |
+
| No log | 7.0909 | 390 | 0.4306 | 0.6530 | 0.4306 | 0.6562 |
|
| 247 |
+
| No log | 7.1273 | 392 | 0.4309 | 0.6530 | 0.4309 | 0.6564 |
|
| 248 |
+
| No log | 7.1636 | 394 | 0.4415 | 0.6488 | 0.4415 | 0.6644 |
|
| 249 |
+
| No log | 7.2 | 396 | 0.4942 | 0.5965 | 0.4942 | 0.7030 |
|
| 250 |
+
| No log | 7.2364 | 398 | 0.5148 | 0.5639 | 0.5148 | 0.7175 |
|
| 251 |
+
| No log | 7.2727 | 400 | 0.5343 | 0.5544 | 0.5343 | 0.7309 |
|
| 252 |
+
| No log | 7.3091 | 402 | 0.4889 | 0.6381 | 0.4889 | 0.6992 |
|
| 253 |
+
| No log | 7.3455 | 404 | 0.5215 | 0.5544 | 0.5215 | 0.7221 |
|
| 254 |
+
| No log | 7.3818 | 406 | 0.5400 | 0.5310 | 0.5400 | 0.7349 |
|
| 255 |
+
| No log | 7.4182 | 408 | 0.5882 | 0.4664 | 0.5882 | 0.7669 |
|
| 256 |
+
| No log | 7.4545 | 410 | 0.5511 | 0.4663 | 0.5511 | 0.7423 |
|
| 257 |
+
| No log | 7.4909 | 412 | 0.5680 | 0.4663 | 0.5680 | 0.7536 |
|
| 258 |
+
| No log | 7.5273 | 414 | 0.6335 | 0.4197 | 0.6335 | 0.7959 |
|
| 259 |
+
| No log | 7.5636 | 416 | 0.6344 | 0.4199 | 0.6344 | 0.7965 |
|
| 260 |
+
| No log | 7.6 | 418 | 0.5794 | 0.4911 | 0.5794 | 0.7612 |
|
| 261 |
+
| No log | 7.6364 | 420 | 0.5151 | 0.5736 | 0.5151 | 0.7177 |
|
| 262 |
+
| No log | 7.6727 | 422 | 0.5526 | 0.5291 | 0.5526 | 0.7434 |
|
| 263 |
+
| No log | 7.7091 | 424 | 0.6979 | 0.4952 | 0.6979 | 0.8354 |
|
| 264 |
+
| No log | 7.7455 | 426 | 0.7130 | 0.4821 | 0.7130 | 0.8444 |
|
| 265 |
+
| No log | 7.7818 | 428 | 0.6275 | 0.5206 | 0.6275 | 0.7921 |
|
| 266 |
+
| No log | 7.8182 | 430 | 0.6034 | 0.5237 | 0.6034 | 0.7768 |
|
| 267 |
+
| No log | 7.8545 | 432 | 0.5546 | 0.5104 | 0.5546 | 0.7447 |
|
| 268 |
+
| No log | 7.8909 | 434 | 0.5048 | 0.5801 | 0.5048 | 0.7105 |
|
| 269 |
+
| No log | 7.9273 | 436 | 0.5099 | 0.5614 | 0.5099 | 0.7141 |
|
| 270 |
+
| No log | 7.9636 | 438 | 0.5492 | 0.5677 | 0.5492 | 0.7411 |
|
| 271 |
+
| No log | 8.0 | 440 | 0.6436 | 0.5155 | 0.6436 | 0.8022 |
|
| 272 |
+
| No log | 8.0364 | 442 | 0.7266 | 0.4287 | 0.7266 | 0.8524 |
|
| 273 |
+
| No log | 8.0727 | 444 | 0.7239 | 0.4287 | 0.7239 | 0.8508 |
|
| 274 |
+
| No log | 8.1091 | 446 | 0.6601 | 0.4400 | 0.6601 | 0.8124 |
|
| 275 |
+
| No log | 8.1455 | 448 | 0.5609 | 0.4898 | 0.5609 | 0.7489 |
|
| 276 |
+
| No log | 8.1818 | 450 | 0.5157 | 0.5237 | 0.5157 | 0.7181 |
|
| 277 |
+
| No log | 8.2182 | 452 | 0.5393 | 0.4835 | 0.5393 | 0.7343 |
|
| 278 |
+
| No log | 8.2545 | 454 | 0.5881 | 0.4197 | 0.5881 | 0.7669 |
|
| 279 |
+
| No log | 8.2909 | 456 | 0.6213 | 0.3981 | 0.6213 | 0.7882 |
|
| 280 |
+
| No log | 8.3273 | 458 | 0.6695 | 0.4203 | 0.6695 | 0.8182 |
|
| 281 |
+
| No log | 8.3636 | 460 | 0.6572 | 0.3803 | 0.6572 | 0.8107 |
|
| 282 |
+
| No log | 8.4 | 462 | 0.6935 | 0.3803 | 0.6935 | 0.8327 |
|
| 283 |
+
| No log | 8.4364 | 464 | 0.6351 | 0.4197 | 0.6351 | 0.7969 |
|
| 284 |
+
| No log | 8.4727 | 466 | 0.5970 | 0.4749 | 0.5970 | 0.7726 |
|
| 285 |
+
| No log | 8.5091 | 468 | 0.5612 | 0.5158 | 0.5612 | 0.7492 |
|
| 286 |
+
| No log | 8.5455 | 470 | 0.5630 | 0.5158 | 0.5630 | 0.7504 |
|
| 287 |
+
| No log | 8.5818 | 472 | 0.6129 | 0.5219 | 0.6129 | 0.7829 |
|
| 288 |
+
| No log | 8.6182 | 474 | 0.7454 | 0.4114 | 0.7454 | 0.8634 |
|
| 289 |
+
| No log | 8.6545 | 476 | 0.7433 | 0.4287 | 0.7433 | 0.8621 |
|
| 290 |
+
| No log | 8.6909 | 478 | 0.5910 | 0.5131 | 0.5910 | 0.7687 |
|
| 291 |
+
| No log | 8.7273 | 480 | 0.4848 | 0.5195 | 0.4848 | 0.6963 |
|
| 292 |
+
| No log | 8.7636 | 482 | 0.4674 | 0.6096 | 0.4674 | 0.6837 |
|
| 293 |
+
| No log | 8.8 | 484 | 0.4707 | 0.6082 | 0.4707 | 0.6861 |
|
| 294 |
+
| No log | 8.8364 | 486 | 0.5143 | 0.5403 | 0.5143 | 0.7172 |
|
| 295 |
+
| No log | 8.8727 | 488 | 0.5962 | 0.4745 | 0.5962 | 0.7721 |
|
| 296 |
+
| No log | 8.9091 | 490 | 0.6067 | 0.4272 | 0.6067 | 0.7789 |
|
| 297 |
+
| No log | 8.9455 | 492 | 0.5353 | 0.5310 | 0.5353 | 0.7316 |
|
| 298 |
+
| No log | 8.9818 | 494 | 0.5247 | 0.5252 | 0.5247 | 0.7244 |
|
| 299 |
+
| No log | 9.0182 | 496 | 0.5983 | 0.4812 | 0.5983 | 0.7735 |
|
| 300 |
+
| No log | 9.0545 | 498 | 0.7388 | 0.4409 | 0.7388 | 0.8595 |
|
| 301 |
+
| 0.3455 | 9.0909 | 500 | 0.8149 | 0.4116 | 0.8149 | 0.9027 |
|
| 302 |
+
| 0.3455 | 9.1273 | 502 | 0.7963 | 0.4116 | 0.7963 | 0.8923 |
|
| 303 |
+
| 0.3455 | 9.1636 | 504 | 0.6542 | 0.4799 | 0.6542 | 0.8088 |
|
| 304 |
+
| 0.3455 | 9.2 | 506 | 0.5202 | 0.5989 | 0.5202 | 0.7213 |
|
| 305 |
+
| 0.3455 | 9.2364 | 508 | 0.4756 | 0.6293 | 0.4756 | 0.6896 |
|
| 306 |
+
| 0.3455 | 9.2727 | 510 | 0.4745 | 0.6516 | 0.4745 | 0.6888 |
|
| 307 |
+
| 0.3455 | 9.3091 | 512 | 0.4909 | 0.6060 | 0.4909 | 0.7007 |
|
| 308 |
+
| 0.3455 | 9.3455 | 514 | 0.5913 | 0.4764 | 0.5913 | 0.7690 |
|
| 309 |
+
| 0.3455 | 9.3818 | 516 | 0.7396 | 0.4472 | 0.7396 | 0.8600 |
|
| 310 |
+
| 0.3455 | 9.4182 | 518 | 0.7620 | 0.3963 | 0.7620 | 0.8730 |
|
| 311 |
+
| 0.3455 | 9.4545 | 520 | 0.6329 | 0.4606 | 0.6329 | 0.7955 |
|
| 312 |
+
| 0.3455 | 9.4909 | 522 | 0.4946 | 0.6060 | 0.4946 | 0.7033 |
|
| 313 |
+
| 0.3455 | 9.5273 | 524 | 0.4637 | 0.6296 | 0.4637 | 0.6810 |
|
| 314 |
+
| 0.3455 | 9.5636 | 526 | 0.4603 | 0.6054 | 0.4603 | 0.6785 |
|
| 315 |
+
| 0.3455 | 9.6 | 528 | 0.5111 | 0.5560 | 0.5111 | 0.7149 |
|
| 316 |
+
| 0.3455 | 9.6364 | 530 | 0.7104 | 0.3887 | 0.7104 | 0.8429 |
|
| 317 |
+
| 0.3455 | 9.6727 | 532 | 0.8059 | 0.3643 | 0.8059 | 0.8977 |
|
| 318 |
+
| 0.3455 | 9.7091 | 534 | 0.8649 | 0.3590 | 0.8649 | 0.9300 |
|
| 319 |
+
| 0.3455 | 9.7455 | 536 | 0.7245 | 0.3183 | 0.7245 | 0.8512 |
|
| 320 |
+
| 0.3455 | 9.7818 | 538 | 0.6918 | 0.4133 | 0.6918 | 0.8317 |
|
| 321 |
+
| 0.3455 | 9.8182 | 540 | 0.7140 | 0.4098 | 0.7140 | 0.8450 |
|
| 322 |
+
| 0.3455 | 9.8545 | 542 | 0.6959 | 0.4222 | 0.6959 | 0.8342 |
|
| 323 |
+
| 0.3455 | 9.8909 | 544 | 0.6289 | 0.4404 | 0.6289 | 0.7931 |
|
| 324 |
+
| 0.3455 | 9.9273 | 546 | 0.5962 | 0.4916 | 0.5962 | 0.7721 |
|
| 325 |
+
| 0.3455 | 9.9636 | 548 | 0.6374 | 0.4104 | 0.6374 | 0.7984 |
|
| 326 |
+
| 0.3455 | 10.0 | 550 | 0.7817 | 0.3593 | 0.7817 | 0.8841 |
|
| 327 |
+
| 0.3455 | 10.0364 | 552 | 0.8402 | 0.3484 | 0.8402 | 0.9166 |
|
| 328 |
+
| 0.3455 | 10.0727 | 554 | 0.8402 | 0.3484 | 0.8402 | 0.9166 |
|
| 329 |
+
| 0.3455 | 10.1091 | 556 | 0.7216 | 0.3324 | 0.7216 | 0.8495 |
|
| 330 |
+
|
| 331 |
+
|
| 332 |
+
### Framework versions
|
| 333 |
+
|
| 334 |
+
- Transformers 4.44.2
|
| 335 |
+
- Pytorch 2.4.0+cu118
|
| 336 |
+
- Datasets 2.21.0
|
| 337 |
+
- 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:d9fb1a90716ddd906c0da39dabef54d3d6c008f14605a6fbbe8fcd7f33ad022a
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e37e1ac19bc530334262b7d4a7813334b904af79810a0db9ee01aacfb45a18e
|
| 3 |
+
size 5304
|