Training in progress, step 500
Browse files- README.md +320 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,320 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_TestTask2_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_TestTask2_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: 0.5070
|
| 19 |
+
- Qwk: 0.5876
|
| 20 |
+
- Mse: 0.5070
|
| 21 |
+
- Rmse: 0.7121
|
| 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 | 3.7204 | 0.0266 | 3.7204 | 1.9288 |
|
| 53 |
+
| No log | 0.0426 | 4 | 2.7978 | 0.0386 | 2.7978 | 1.6727 |
|
| 54 |
+
| No log | 0.0638 | 6 | 1.1891 | 0.1293 | 1.1891 | 1.0905 |
|
| 55 |
+
| No log | 0.0851 | 8 | 0.6163 | 0.3347 | 0.6163 | 0.7851 |
|
| 56 |
+
| No log | 0.1064 | 10 | 0.7672 | 0.1045 | 0.7672 | 0.8759 |
|
| 57 |
+
| No log | 0.1277 | 12 | 0.7503 | 0.1488 | 0.7503 | 0.8662 |
|
| 58 |
+
| No log | 0.1489 | 14 | 0.6529 | 0.2807 | 0.6529 | 0.8080 |
|
| 59 |
+
| No log | 0.1702 | 16 | 0.6211 | 0.4197 | 0.6211 | 0.7881 |
|
| 60 |
+
| No log | 0.1915 | 18 | 0.5747 | 0.4828 | 0.5747 | 0.7581 |
|
| 61 |
+
| No log | 0.2128 | 20 | 0.5579 | 0.4842 | 0.5579 | 0.7470 |
|
| 62 |
+
| No log | 0.2340 | 22 | 0.6349 | 0.4219 | 0.6349 | 0.7968 |
|
| 63 |
+
| No log | 0.2553 | 24 | 0.6046 | 0.3709 | 0.6046 | 0.7775 |
|
| 64 |
+
| No log | 0.2766 | 26 | 0.5573 | 0.4521 | 0.5573 | 0.7465 |
|
| 65 |
+
| No log | 0.2979 | 28 | 0.4811 | 0.5304 | 0.4811 | 0.6936 |
|
| 66 |
+
| No log | 0.3191 | 30 | 0.4795 | 0.5014 | 0.4795 | 0.6924 |
|
| 67 |
+
| No log | 0.3404 | 32 | 0.4736 | 0.5088 | 0.4736 | 0.6882 |
|
| 68 |
+
| No log | 0.3617 | 34 | 0.4783 | 0.5030 | 0.4783 | 0.6916 |
|
| 69 |
+
| No log | 0.3830 | 36 | 0.4733 | 0.4722 | 0.4733 | 0.6879 |
|
| 70 |
+
| No log | 0.4043 | 38 | 0.5547 | 0.3726 | 0.5547 | 0.7448 |
|
| 71 |
+
| No log | 0.4255 | 40 | 0.6035 | 0.3099 | 0.6035 | 0.7768 |
|
| 72 |
+
| No log | 0.4468 | 42 | 0.7365 | 0.1975 | 0.7365 | 0.8582 |
|
| 73 |
+
| No log | 0.4681 | 44 | 0.7888 | 0.1334 | 0.7888 | 0.8881 |
|
| 74 |
+
| No log | 0.4894 | 46 | 0.7687 | 0.1519 | 0.7687 | 0.8768 |
|
| 75 |
+
| No log | 0.5106 | 48 | 0.6884 | 0.2542 | 0.6884 | 0.8297 |
|
| 76 |
+
| No log | 0.5319 | 50 | 0.5303 | 0.3747 | 0.5303 | 0.7282 |
|
| 77 |
+
| No log | 0.5532 | 52 | 0.4630 | 0.5222 | 0.4630 | 0.6804 |
|
| 78 |
+
| No log | 0.5745 | 54 | 0.4749 | 0.5715 | 0.4749 | 0.6891 |
|
| 79 |
+
| No log | 0.5957 | 56 | 0.4511 | 0.5760 | 0.4511 | 0.6717 |
|
| 80 |
+
| No log | 0.6170 | 58 | 0.5164 | 0.5367 | 0.5164 | 0.7186 |
|
| 81 |
+
| No log | 0.6383 | 60 | 0.7207 | 0.1337 | 0.7207 | 0.8490 |
|
| 82 |
+
| No log | 0.6596 | 62 | 0.7457 | 0.0698 | 0.7457 | 0.8635 |
|
| 83 |
+
| No log | 0.6809 | 64 | 0.5740 | 0.3800 | 0.5740 | 0.7576 |
|
| 84 |
+
| No log | 0.7021 | 66 | 0.4494 | 0.5451 | 0.4494 | 0.6704 |
|
| 85 |
+
| No log | 0.7234 | 68 | 0.4235 | 0.5805 | 0.4235 | 0.6508 |
|
| 86 |
+
| No log | 0.7447 | 70 | 0.4372 | 0.5801 | 0.4372 | 0.6612 |
|
| 87 |
+
| No log | 0.7660 | 72 | 0.4908 | 0.5666 | 0.4908 | 0.7006 |
|
| 88 |
+
| No log | 0.7872 | 74 | 0.5745 | 0.5636 | 0.5745 | 0.7579 |
|
| 89 |
+
| No log | 0.8085 | 76 | 0.7250 | 0.4962 | 0.7250 | 0.8515 |
|
| 90 |
+
| No log | 0.8298 | 78 | 0.7346 | 0.5022 | 0.7346 | 0.8571 |
|
| 91 |
+
| No log | 0.8511 | 80 | 0.5671 | 0.5375 | 0.5671 | 0.7530 |
|
| 92 |
+
| No log | 0.8723 | 82 | 0.4204 | 0.6118 | 0.4204 | 0.6484 |
|
| 93 |
+
| No log | 0.8936 | 84 | 0.4118 | 0.6546 | 0.4118 | 0.6417 |
|
| 94 |
+
| No log | 0.9149 | 86 | 0.4549 | 0.6058 | 0.4549 | 0.6745 |
|
| 95 |
+
| No log | 0.9362 | 88 | 0.5741 | 0.5467 | 0.5741 | 0.7577 |
|
| 96 |
+
| No log | 0.9574 | 90 | 0.6135 | 0.5415 | 0.6135 | 0.7833 |
|
| 97 |
+
| No log | 0.9787 | 92 | 0.5457 | 0.5764 | 0.5457 | 0.7387 |
|
| 98 |
+
| No log | 1.0 | 94 | 0.4709 | 0.6539 | 0.4709 | 0.6862 |
|
| 99 |
+
| No log | 1.0213 | 96 | 0.4406 | 0.6480 | 0.4406 | 0.6638 |
|
| 100 |
+
| No log | 1.0426 | 98 | 0.4732 | 0.6548 | 0.4732 | 0.6879 |
|
| 101 |
+
| No log | 1.0638 | 100 | 0.5617 | 0.5800 | 0.5617 | 0.7495 |
|
| 102 |
+
| No log | 1.0851 | 102 | 0.6388 | 0.5480 | 0.6388 | 0.7993 |
|
| 103 |
+
| No log | 1.1064 | 104 | 0.7549 | 0.4955 | 0.7549 | 0.8689 |
|
| 104 |
+
| No log | 1.1277 | 106 | 0.8081 | 0.4800 | 0.8081 | 0.8989 |
|
| 105 |
+
| No log | 1.1489 | 108 | 0.7216 | 0.4676 | 0.7216 | 0.8495 |
|
| 106 |
+
| No log | 1.1702 | 110 | 0.5091 | 0.5241 | 0.5091 | 0.7135 |
|
| 107 |
+
| No log | 1.1915 | 112 | 0.3850 | 0.6229 | 0.3850 | 0.6205 |
|
| 108 |
+
| No log | 1.2128 | 114 | 0.3878 | 0.6374 | 0.3878 | 0.6227 |
|
| 109 |
+
| No log | 1.2340 | 116 | 0.4004 | 0.5822 | 0.4004 | 0.6327 |
|
| 110 |
+
| No log | 1.2553 | 118 | 0.4842 | 0.4500 | 0.4842 | 0.6959 |
|
| 111 |
+
| No log | 1.2766 | 120 | 0.6117 | 0.3872 | 0.6117 | 0.7821 |
|
| 112 |
+
| No log | 1.2979 | 122 | 0.6379 | 0.3872 | 0.6379 | 0.7987 |
|
| 113 |
+
| No log | 1.3191 | 124 | 0.5915 | 0.4408 | 0.5915 | 0.7691 |
|
| 114 |
+
| No log | 1.3404 | 126 | 0.4770 | 0.5779 | 0.4770 | 0.6907 |
|
| 115 |
+
| No log | 1.3617 | 128 | 0.4692 | 0.6156 | 0.4692 | 0.6850 |
|
| 116 |
+
| No log | 1.3830 | 130 | 0.6005 | 0.5766 | 0.6005 | 0.7749 |
|
| 117 |
+
| No log | 1.4043 | 132 | 0.4989 | 0.6088 | 0.4989 | 0.7063 |
|
| 118 |
+
| No log | 1.4255 | 134 | 0.4134 | 0.6009 | 0.4134 | 0.6429 |
|
| 119 |
+
| No log | 1.4468 | 136 | 0.4951 | 0.4797 | 0.4951 | 0.7036 |
|
| 120 |
+
| No log | 1.4681 | 138 | 0.5664 | 0.4048 | 0.5664 | 0.7526 |
|
| 121 |
+
| No log | 1.4894 | 140 | 0.5489 | 0.4106 | 0.5489 | 0.7409 |
|
| 122 |
+
| No log | 1.5106 | 142 | 0.4772 | 0.5133 | 0.4772 | 0.6908 |
|
| 123 |
+
| No log | 1.5319 | 144 | 0.4210 | 0.6038 | 0.4210 | 0.6488 |
|
| 124 |
+
| No log | 1.5532 | 146 | 0.4301 | 0.6022 | 0.4301 | 0.6558 |
|
| 125 |
+
| No log | 1.5745 | 148 | 0.4520 | 0.6337 | 0.4520 | 0.6723 |
|
| 126 |
+
| No log | 1.5957 | 150 | 0.5077 | 0.6346 | 0.5077 | 0.7125 |
|
| 127 |
+
| No log | 1.6170 | 152 | 0.5407 | 0.6305 | 0.5407 | 0.7353 |
|
| 128 |
+
| No log | 1.6383 | 154 | 0.5495 | 0.6117 | 0.5495 | 0.7413 |
|
| 129 |
+
| No log | 1.6596 | 156 | 0.4711 | 0.5976 | 0.4711 | 0.6863 |
|
| 130 |
+
| No log | 1.6809 | 158 | 0.4052 | 0.5863 | 0.4052 | 0.6365 |
|
| 131 |
+
| No log | 1.7021 | 160 | 0.3964 | 0.5967 | 0.3964 | 0.6296 |
|
| 132 |
+
| No log | 1.7234 | 162 | 0.4397 | 0.6067 | 0.4397 | 0.6631 |
|
| 133 |
+
| No log | 1.7447 | 164 | 0.4495 | 0.6002 | 0.4495 | 0.6705 |
|
| 134 |
+
| No log | 1.7660 | 166 | 0.4127 | 0.6097 | 0.4127 | 0.6424 |
|
| 135 |
+
| No log | 1.7872 | 168 | 0.4227 | 0.6381 | 0.4227 | 0.6502 |
|
| 136 |
+
| No log | 1.8085 | 170 | 0.4330 | 0.6120 | 0.4330 | 0.6580 |
|
| 137 |
+
| No log | 1.8298 | 172 | 0.4648 | 0.6096 | 0.4648 | 0.6817 |
|
| 138 |
+
| No log | 1.8511 | 174 | 0.6112 | 0.5718 | 0.6112 | 0.7818 |
|
| 139 |
+
| No log | 1.8723 | 176 | 0.7205 | 0.5159 | 0.7205 | 0.8488 |
|
| 140 |
+
| No log | 1.8936 | 178 | 0.8977 | 0.4292 | 0.8977 | 0.9475 |
|
| 141 |
+
| No log | 1.9149 | 180 | 0.9416 | 0.4144 | 0.9416 | 0.9704 |
|
| 142 |
+
| No log | 1.9362 | 182 | 0.8258 | 0.4938 | 0.8258 | 0.9088 |
|
| 143 |
+
| No log | 1.9574 | 184 | 0.6293 | 0.5676 | 0.6293 | 0.7933 |
|
| 144 |
+
| No log | 1.9787 | 186 | 0.4060 | 0.6315 | 0.4060 | 0.6372 |
|
| 145 |
+
| No log | 2.0 | 188 | 0.3900 | 0.6812 | 0.3900 | 0.6245 |
|
| 146 |
+
| No log | 2.0213 | 190 | 0.3909 | 0.6389 | 0.3909 | 0.6252 |
|
| 147 |
+
| No log | 2.0426 | 192 | 0.5262 | 0.5417 | 0.5262 | 0.7254 |
|
| 148 |
+
| No log | 2.0638 | 194 | 0.4990 | 0.5546 | 0.4990 | 0.7064 |
|
| 149 |
+
| No log | 2.0851 | 196 | 0.4023 | 0.5996 | 0.4023 | 0.6343 |
|
| 150 |
+
| No log | 2.1064 | 198 | 0.3880 | 0.6344 | 0.3880 | 0.6229 |
|
| 151 |
+
| No log | 2.1277 | 200 | 0.3915 | 0.6028 | 0.3915 | 0.6257 |
|
| 152 |
+
| No log | 2.1489 | 202 | 0.4802 | 0.5639 | 0.4802 | 0.6930 |
|
| 153 |
+
| No log | 2.1702 | 204 | 0.5257 | 0.5819 | 0.5257 | 0.7251 |
|
| 154 |
+
| No log | 2.1915 | 206 | 0.4264 | 0.5904 | 0.4264 | 0.6530 |
|
| 155 |
+
| No log | 2.2128 | 208 | 0.4337 | 0.6301 | 0.4337 | 0.6586 |
|
| 156 |
+
| No log | 2.2340 | 210 | 0.6026 | 0.5633 | 0.6026 | 0.7763 |
|
| 157 |
+
| No log | 2.2553 | 212 | 0.8583 | 0.4885 | 0.8583 | 0.9264 |
|
| 158 |
+
| No log | 2.2766 | 214 | 0.8020 | 0.5266 | 0.8020 | 0.8955 |
|
| 159 |
+
| No log | 2.2979 | 216 | 0.5803 | 0.6053 | 0.5803 | 0.7618 |
|
| 160 |
+
| No log | 2.3191 | 218 | 0.4590 | 0.6534 | 0.4590 | 0.6775 |
|
| 161 |
+
| No log | 2.3404 | 220 | 0.4656 | 0.6592 | 0.4656 | 0.6823 |
|
| 162 |
+
| No log | 2.3617 | 222 | 0.5785 | 0.5673 | 0.5785 | 0.7606 |
|
| 163 |
+
| No log | 2.3830 | 224 | 0.6688 | 0.4474 | 0.6688 | 0.8178 |
|
| 164 |
+
| No log | 2.4043 | 226 | 0.6556 | 0.4453 | 0.6556 | 0.8097 |
|
| 165 |
+
| No log | 2.4255 | 228 | 0.5727 | 0.4596 | 0.5727 | 0.7568 |
|
| 166 |
+
| No log | 2.4468 | 230 | 0.4235 | 0.5907 | 0.4235 | 0.6508 |
|
| 167 |
+
| No log | 2.4681 | 232 | 0.4018 | 0.6144 | 0.4018 | 0.6339 |
|
| 168 |
+
| No log | 2.4894 | 234 | 0.4174 | 0.6132 | 0.4174 | 0.6461 |
|
| 169 |
+
| No log | 2.5106 | 236 | 0.3963 | 0.6664 | 0.3963 | 0.6295 |
|
| 170 |
+
| No log | 2.5319 | 238 | 0.5067 | 0.6360 | 0.5067 | 0.7119 |
|
| 171 |
+
| No log | 2.5532 | 240 | 0.6720 | 0.5078 | 0.6720 | 0.8198 |
|
| 172 |
+
| No log | 2.5745 | 242 | 0.7034 | 0.5072 | 0.7034 | 0.8387 |
|
| 173 |
+
| No log | 2.5957 | 244 | 0.5401 | 0.5908 | 0.5401 | 0.7349 |
|
| 174 |
+
| No log | 2.6170 | 246 | 0.3934 | 0.6430 | 0.3934 | 0.6272 |
|
| 175 |
+
| No log | 2.6383 | 248 | 0.3923 | 0.6427 | 0.3923 | 0.6264 |
|
| 176 |
+
| No log | 2.6596 | 250 | 0.4575 | 0.6287 | 0.4575 | 0.6764 |
|
| 177 |
+
| No log | 2.6809 | 252 | 0.4848 | 0.6046 | 0.4848 | 0.6963 |
|
| 178 |
+
| No log | 2.7021 | 254 | 0.5784 | 0.6014 | 0.5784 | 0.7605 |
|
| 179 |
+
| No log | 2.7234 | 256 | 0.6490 | 0.5743 | 0.6490 | 0.8056 |
|
| 180 |
+
| No log | 2.7447 | 258 | 0.7010 | 0.5466 | 0.7010 | 0.8372 |
|
| 181 |
+
| No log | 2.7660 | 260 | 0.6070 | 0.5923 | 0.6070 | 0.7791 |
|
| 182 |
+
| No log | 2.7872 | 262 | 0.4685 | 0.6435 | 0.4685 | 0.6845 |
|
| 183 |
+
| No log | 2.8085 | 264 | 0.4882 | 0.6391 | 0.4882 | 0.6987 |
|
| 184 |
+
| No log | 2.8298 | 266 | 0.6881 | 0.5382 | 0.6881 | 0.8295 |
|
| 185 |
+
| No log | 2.8511 | 268 | 0.7501 | 0.5211 | 0.7501 | 0.8661 |
|
| 186 |
+
| No log | 2.8723 | 270 | 0.5829 | 0.5716 | 0.5829 | 0.7635 |
|
| 187 |
+
| No log | 2.8936 | 272 | 0.3984 | 0.6438 | 0.3984 | 0.6312 |
|
| 188 |
+
| No log | 2.9149 | 274 | 0.3876 | 0.6469 | 0.3876 | 0.6226 |
|
| 189 |
+
| No log | 2.9362 | 276 | 0.3767 | 0.6742 | 0.3767 | 0.6137 |
|
| 190 |
+
| No log | 2.9574 | 278 | 0.4345 | 0.6367 | 0.4345 | 0.6591 |
|
| 191 |
+
| No log | 2.9787 | 280 | 0.7209 | 0.4572 | 0.7209 | 0.8491 |
|
| 192 |
+
| No log | 3.0 | 282 | 0.9757 | 0.3512 | 0.9757 | 0.9878 |
|
| 193 |
+
| No log | 3.0213 | 284 | 0.9757 | 0.3336 | 0.9757 | 0.9878 |
|
| 194 |
+
| No log | 3.0426 | 286 | 0.8074 | 0.3235 | 0.8074 | 0.8985 |
|
| 195 |
+
| No log | 3.0638 | 288 | 0.6072 | 0.4569 | 0.6072 | 0.7793 |
|
| 196 |
+
| No log | 3.0851 | 290 | 0.4221 | 0.5614 | 0.4221 | 0.6497 |
|
| 197 |
+
| No log | 3.1064 | 292 | 0.3809 | 0.6887 | 0.3809 | 0.6172 |
|
| 198 |
+
| No log | 3.1277 | 294 | 0.4099 | 0.6366 | 0.4099 | 0.6403 |
|
| 199 |
+
| No log | 3.1489 | 296 | 0.5706 | 0.5777 | 0.5706 | 0.7554 |
|
| 200 |
+
| No log | 3.1702 | 298 | 0.6450 | 0.5658 | 0.6450 | 0.8031 |
|
| 201 |
+
| No log | 3.1915 | 300 | 0.6043 | 0.5731 | 0.6043 | 0.7774 |
|
| 202 |
+
| No log | 3.2128 | 302 | 0.4893 | 0.6319 | 0.4893 | 0.6995 |
|
| 203 |
+
| No log | 3.2340 | 304 | 0.5062 | 0.6347 | 0.5062 | 0.7115 |
|
| 204 |
+
| No log | 3.2553 | 306 | 0.5452 | 0.6328 | 0.5452 | 0.7384 |
|
| 205 |
+
| No log | 3.2766 | 308 | 0.5000 | 0.6523 | 0.5000 | 0.7071 |
|
| 206 |
+
| No log | 3.2979 | 310 | 0.4749 | 0.6185 | 0.4749 | 0.6891 |
|
| 207 |
+
| No log | 3.3191 | 312 | 0.4188 | 0.6313 | 0.4188 | 0.6472 |
|
| 208 |
+
| No log | 3.3404 | 314 | 0.4317 | 0.6197 | 0.4317 | 0.6570 |
|
| 209 |
+
| No log | 3.3617 | 316 | 0.5480 | 0.5608 | 0.5480 | 0.7402 |
|
| 210 |
+
| No log | 3.3830 | 318 | 0.5784 | 0.5679 | 0.5784 | 0.7605 |
|
| 211 |
+
| No log | 3.4043 | 320 | 0.5196 | 0.6015 | 0.5196 | 0.7209 |
|
| 212 |
+
| No log | 3.4255 | 322 | 0.5270 | 0.6028 | 0.5270 | 0.7259 |
|
| 213 |
+
| No log | 3.4468 | 324 | 0.5854 | 0.5824 | 0.5854 | 0.7651 |
|
| 214 |
+
| No log | 3.4681 | 326 | 0.5958 | 0.5722 | 0.5958 | 0.7719 |
|
| 215 |
+
| No log | 3.4894 | 328 | 0.6262 | 0.5791 | 0.6262 | 0.7913 |
|
| 216 |
+
| No log | 3.5106 | 330 | 0.5834 | 0.5904 | 0.5834 | 0.7638 |
|
| 217 |
+
| No log | 3.5319 | 332 | 0.4924 | 0.5941 | 0.4924 | 0.7017 |
|
| 218 |
+
| No log | 3.5532 | 334 | 0.4483 | 0.6107 | 0.4483 | 0.6696 |
|
| 219 |
+
| No log | 3.5745 | 336 | 0.4482 | 0.6009 | 0.4482 | 0.6695 |
|
| 220 |
+
| No log | 3.5957 | 338 | 0.4460 | 0.5957 | 0.4460 | 0.6678 |
|
| 221 |
+
| No log | 3.6170 | 340 | 0.4058 | 0.6208 | 0.4058 | 0.6370 |
|
| 222 |
+
| No log | 3.6383 | 342 | 0.4136 | 0.6332 | 0.4136 | 0.6432 |
|
| 223 |
+
| No log | 3.6596 | 344 | 0.4863 | 0.5878 | 0.4863 | 0.6974 |
|
| 224 |
+
| No log | 3.6809 | 346 | 0.9114 | 0.4930 | 0.9114 | 0.9547 |
|
| 225 |
+
| No log | 3.7021 | 348 | 1.1743 | 0.4017 | 1.1743 | 1.0837 |
|
| 226 |
+
| No log | 3.7234 | 350 | 0.9683 | 0.4817 | 0.9683 | 0.9840 |
|
| 227 |
+
| No log | 3.7447 | 352 | 0.5474 | 0.6104 | 0.5474 | 0.7399 |
|
| 228 |
+
| No log | 3.7660 | 354 | 0.4390 | 0.6722 | 0.4390 | 0.6626 |
|
| 229 |
+
| No log | 3.7872 | 356 | 0.4385 | 0.6759 | 0.4385 | 0.6622 |
|
| 230 |
+
| No log | 3.8085 | 358 | 0.5006 | 0.6037 | 0.5006 | 0.7075 |
|
| 231 |
+
| No log | 3.8298 | 360 | 0.6809 | 0.5460 | 0.6809 | 0.8252 |
|
| 232 |
+
| No log | 3.8511 | 362 | 0.6863 | 0.5423 | 0.6863 | 0.8284 |
|
| 233 |
+
| No log | 3.8723 | 364 | 0.5955 | 0.5838 | 0.5955 | 0.7717 |
|
| 234 |
+
| No log | 3.8936 | 366 | 0.5050 | 0.6169 | 0.5050 | 0.7106 |
|
| 235 |
+
| No log | 3.9149 | 368 | 0.5167 | 0.5967 | 0.5167 | 0.7188 |
|
| 236 |
+
| No log | 3.9362 | 370 | 0.4835 | 0.6109 | 0.4835 | 0.6953 |
|
| 237 |
+
| No log | 3.9574 | 372 | 0.6771 | 0.5413 | 0.6771 | 0.8229 |
|
| 238 |
+
| No log | 3.9787 | 374 | 1.0150 | 0.4424 | 1.0150 | 1.0075 |
|
| 239 |
+
| No log | 4.0 | 376 | 1.1965 | 0.3479 | 1.1965 | 1.0939 |
|
| 240 |
+
| No log | 4.0213 | 378 | 1.1475 | 0.3705 | 1.1475 | 1.0712 |
|
| 241 |
+
| No log | 4.0426 | 380 | 0.7832 | 0.5001 | 0.7832 | 0.8850 |
|
| 242 |
+
| No log | 4.0638 | 382 | 0.4177 | 0.6508 | 0.4177 | 0.6463 |
|
| 243 |
+
| No log | 4.0851 | 384 | 0.4121 | 0.6304 | 0.4121 | 0.6420 |
|
| 244 |
+
| No log | 4.1064 | 386 | 0.3978 | 0.6453 | 0.3978 | 0.6307 |
|
| 245 |
+
| No log | 4.1277 | 388 | 0.4994 | 0.5804 | 0.4994 | 0.7067 |
|
| 246 |
+
| No log | 4.1489 | 390 | 0.6198 | 0.5233 | 0.6198 | 0.7873 |
|
| 247 |
+
| No log | 4.1702 | 392 | 0.7567 | 0.4539 | 0.7567 | 0.8699 |
|
| 248 |
+
| No log | 4.1915 | 394 | 0.6999 | 0.4617 | 0.6999 | 0.8366 |
|
| 249 |
+
| No log | 4.2128 | 396 | 0.5602 | 0.5433 | 0.5602 | 0.7485 |
|
| 250 |
+
| No log | 4.2340 | 398 | 0.4428 | 0.6687 | 0.4428 | 0.6654 |
|
| 251 |
+
| No log | 4.2553 | 400 | 0.4561 | 0.6579 | 0.4561 | 0.6754 |
|
| 252 |
+
| No log | 4.2766 | 402 | 0.6089 | 0.5550 | 0.6089 | 0.7803 |
|
| 253 |
+
| No log | 4.2979 | 404 | 0.8888 | 0.4757 | 0.8888 | 0.9427 |
|
| 254 |
+
| No log | 4.3191 | 406 | 0.8513 | 0.4902 | 0.8513 | 0.9227 |
|
| 255 |
+
| No log | 4.3404 | 408 | 0.5936 | 0.5876 | 0.5936 | 0.7705 |
|
| 256 |
+
| No log | 4.3617 | 410 | 0.5613 | 0.5794 | 0.5613 | 0.7492 |
|
| 257 |
+
| No log | 4.3830 | 412 | 0.5650 | 0.5845 | 0.5650 | 0.7516 |
|
| 258 |
+
| No log | 4.4043 | 414 | 0.5855 | 0.5845 | 0.5855 | 0.7652 |
|
| 259 |
+
| No log | 4.4255 | 416 | 0.6368 | 0.5635 | 0.6368 | 0.7980 |
|
| 260 |
+
| No log | 4.4468 | 418 | 0.6365 | 0.5506 | 0.6365 | 0.7978 |
|
| 261 |
+
| No log | 4.4681 | 420 | 0.5937 | 0.5576 | 0.5937 | 0.7705 |
|
| 262 |
+
| No log | 4.4894 | 422 | 0.5550 | 0.5844 | 0.5550 | 0.7450 |
|
| 263 |
+
| No log | 4.5106 | 424 | 0.5010 | 0.5932 | 0.5010 | 0.7078 |
|
| 264 |
+
| No log | 4.5319 | 426 | 0.4179 | 0.6356 | 0.4179 | 0.6465 |
|
| 265 |
+
| No log | 4.5532 | 428 | 0.4123 | 0.6324 | 0.4123 | 0.6421 |
|
| 266 |
+
| No log | 4.5745 | 430 | 0.3973 | 0.6516 | 0.3973 | 0.6303 |
|
| 267 |
+
| No log | 4.5957 | 432 | 0.3915 | 0.6600 | 0.3915 | 0.6257 |
|
| 268 |
+
| No log | 4.6170 | 434 | 0.4191 | 0.6556 | 0.4191 | 0.6474 |
|
| 269 |
+
| No log | 4.6383 | 436 | 0.5400 | 0.6279 | 0.5400 | 0.7349 |
|
| 270 |
+
| No log | 4.6596 | 438 | 0.6609 | 0.5741 | 0.6609 | 0.8129 |
|
| 271 |
+
| No log | 4.6809 | 440 | 0.5804 | 0.5946 | 0.5804 | 0.7619 |
|
| 272 |
+
| No log | 4.7021 | 442 | 0.5201 | 0.6101 | 0.5201 | 0.7212 |
|
| 273 |
+
| No log | 4.7234 | 444 | 0.4941 | 0.6107 | 0.4941 | 0.7029 |
|
| 274 |
+
| No log | 4.7447 | 446 | 0.4553 | 0.6128 | 0.4553 | 0.6748 |
|
| 275 |
+
| No log | 4.7660 | 448 | 0.4660 | 0.6108 | 0.4660 | 0.6826 |
|
| 276 |
+
| No log | 4.7872 | 450 | 0.6607 | 0.5189 | 0.6607 | 0.8128 |
|
| 277 |
+
| No log | 4.8085 | 452 | 0.7207 | 0.4971 | 0.7207 | 0.8490 |
|
| 278 |
+
| No log | 4.8298 | 454 | 0.5490 | 0.5595 | 0.5490 | 0.7409 |
|
| 279 |
+
| No log | 4.8511 | 456 | 0.4781 | 0.6159 | 0.4781 | 0.6914 |
|
| 280 |
+
| No log | 4.8723 | 458 | 0.5468 | 0.5884 | 0.5468 | 0.7395 |
|
| 281 |
+
| No log | 4.8936 | 460 | 0.7172 | 0.5488 | 0.7172 | 0.8469 |
|
| 282 |
+
| No log | 4.9149 | 462 | 0.9136 | 0.5218 | 0.9136 | 0.9558 |
|
| 283 |
+
| No log | 4.9362 | 464 | 0.7909 | 0.5461 | 0.7909 | 0.8893 |
|
| 284 |
+
| No log | 4.9574 | 466 | 0.5527 | 0.6065 | 0.5527 | 0.7435 |
|
| 285 |
+
| No log | 4.9787 | 468 | 0.4749 | 0.6783 | 0.4749 | 0.6891 |
|
| 286 |
+
| No log | 5.0 | 470 | 0.4396 | 0.6697 | 0.4396 | 0.6630 |
|
| 287 |
+
| No log | 5.0213 | 472 | 0.4674 | 0.6136 | 0.4674 | 0.6837 |
|
| 288 |
+
| No log | 5.0426 | 474 | 0.5394 | 0.5657 | 0.5394 | 0.7344 |
|
| 289 |
+
| No log | 5.0638 | 476 | 0.5719 | 0.5637 | 0.5719 | 0.7562 |
|
| 290 |
+
| No log | 5.0851 | 478 | 0.6999 | 0.4875 | 0.6999 | 0.8366 |
|
| 291 |
+
| No log | 5.1064 | 480 | 0.7262 | 0.4688 | 0.7262 | 0.8522 |
|
| 292 |
+
| No log | 5.1277 | 482 | 0.5434 | 0.5454 | 0.5434 | 0.7372 |
|
| 293 |
+
| No log | 5.1489 | 484 | 0.4380 | 0.5854 | 0.4380 | 0.6618 |
|
| 294 |
+
| No log | 5.1702 | 486 | 0.4557 | 0.5793 | 0.4557 | 0.6751 |
|
| 295 |
+
| No log | 5.1915 | 488 | 0.4962 | 0.5939 | 0.4962 | 0.7044 |
|
| 296 |
+
| No log | 5.2128 | 490 | 0.6189 | 0.5817 | 0.6189 | 0.7867 |
|
| 297 |
+
| No log | 5.2340 | 492 | 0.7316 | 0.5527 | 0.7316 | 0.8553 |
|
| 298 |
+
| No log | 5.2553 | 494 | 0.5721 | 0.5868 | 0.5721 | 0.7564 |
|
| 299 |
+
| No log | 5.2766 | 496 | 0.4371 | 0.6044 | 0.4371 | 0.6611 |
|
| 300 |
+
| No log | 5.2979 | 498 | 0.4523 | 0.6291 | 0.4523 | 0.6726 |
|
| 301 |
+
| 0.4506 | 5.3191 | 500 | 0.6134 | 0.6164 | 0.6134 | 0.7832 |
|
| 302 |
+
| 0.4506 | 5.3404 | 502 | 0.8066 | 0.5371 | 0.8066 | 0.8981 |
|
| 303 |
+
| 0.4506 | 5.3617 | 504 | 0.8625 | 0.5321 | 0.8625 | 0.9287 |
|
| 304 |
+
| 0.4506 | 5.3830 | 506 | 0.6721 | 0.5875 | 0.6721 | 0.8198 |
|
| 305 |
+
| 0.4506 | 5.4043 | 508 | 0.4693 | 0.6603 | 0.4693 | 0.6850 |
|
| 306 |
+
| 0.4506 | 5.4255 | 510 | 0.4408 | 0.6665 | 0.4408 | 0.6639 |
|
| 307 |
+
| 0.4506 | 5.4468 | 512 | 0.4699 | 0.6469 | 0.4699 | 0.6855 |
|
| 308 |
+
| 0.4506 | 5.4681 | 514 | 0.7045 | 0.5493 | 0.7045 | 0.8394 |
|
| 309 |
+
| 0.4506 | 5.4894 | 516 | 1.0678 | 0.4213 | 1.0678 | 1.0333 |
|
| 310 |
+
| 0.4506 | 5.5106 | 518 | 1.0414 | 0.4122 | 1.0414 | 1.0205 |
|
| 311 |
+
| 0.4506 | 5.5319 | 520 | 0.7861 | 0.4759 | 0.7861 | 0.8866 |
|
| 312 |
+
| 0.4506 | 5.5532 | 522 | 0.5070 | 0.5876 | 0.5070 | 0.7121 |
|
| 313 |
+
|
| 314 |
+
|
| 315 |
+
### Framework versions
|
| 316 |
+
|
| 317 |
+
- Transformers 4.44.2
|
| 318 |
+
- Pytorch 2.4.0+cu118
|
| 319 |
+
- Datasets 2.21.0
|
| 320 |
+
- 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 sha256:15bb433f706326d4a94ec54700f3639cf1fd67d3a63c74f0c6b4d8f9bcbe218c
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a81cb5b4b2befd3054998faa1b538fba8aa29a04bf090aee79d7c1053cf58b2
|
| 3 |
+
size 5240
|