Training in progress, step 500
Browse files- README.md +331 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_vocabulary
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_vocabulary
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.5122
|
| 19 |
+
- Qwk: 0.6327
|
| 20 |
+
- Mse: 0.5122
|
| 21 |
+
- Rmse: 0.7157
|
| 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 | 0.0202 | 2 | 4.6425 | -0.0016 | 4.6425 | 2.1546 |
|
| 53 |
+
| No log | 0.0404 | 4 | 3.5211 | 0.0424 | 3.5211 | 1.8765 |
|
| 54 |
+
| No log | 0.0606 | 6 | 2.1920 | 0.0890 | 2.1920 | 1.4805 |
|
| 55 |
+
| No log | 0.0808 | 8 | 0.9420 | 0.1994 | 0.9420 | 0.9705 |
|
| 56 |
+
| No log | 0.1010 | 10 | 0.8174 | 0.0527 | 0.8174 | 0.9041 |
|
| 57 |
+
| No log | 0.1212 | 12 | 0.9957 | -0.0033 | 0.9957 | 0.9979 |
|
| 58 |
+
| No log | 0.1414 | 14 | 0.9415 | 0.0827 | 0.9415 | 0.9703 |
|
| 59 |
+
| No log | 0.1616 | 16 | 0.8202 | 0.0897 | 0.8202 | 0.9056 |
|
| 60 |
+
| No log | 0.1818 | 18 | 0.7362 | 0.1023 | 0.7362 | 0.8580 |
|
| 61 |
+
| No log | 0.2020 | 20 | 0.6793 | 0.2131 | 0.6793 | 0.8242 |
|
| 62 |
+
| No log | 0.2222 | 22 | 0.6568 | 0.2051 | 0.6568 | 0.8104 |
|
| 63 |
+
| No log | 0.2424 | 24 | 0.6874 | 0.2212 | 0.6874 | 0.8291 |
|
| 64 |
+
| No log | 0.2626 | 26 | 0.7505 | 0.2945 | 0.7505 | 0.8663 |
|
| 65 |
+
| No log | 0.2828 | 28 | 0.7388 | 0.4198 | 0.7388 | 0.8595 |
|
| 66 |
+
| No log | 0.3030 | 30 | 0.6675 | 0.4752 | 0.6675 | 0.8170 |
|
| 67 |
+
| No log | 0.3232 | 32 | 0.6021 | 0.4902 | 0.6021 | 0.7760 |
|
| 68 |
+
| No log | 0.3434 | 34 | 0.5672 | 0.5322 | 0.5672 | 0.7531 |
|
| 69 |
+
| No log | 0.3636 | 36 | 0.5567 | 0.5938 | 0.5567 | 0.7462 |
|
| 70 |
+
| No log | 0.3838 | 38 | 0.5716 | 0.5911 | 0.5716 | 0.7560 |
|
| 71 |
+
| No log | 0.4040 | 40 | 0.5919 | 0.5992 | 0.5919 | 0.7693 |
|
| 72 |
+
| No log | 0.4242 | 42 | 0.5984 | 0.5898 | 0.5984 | 0.7736 |
|
| 73 |
+
| No log | 0.4444 | 44 | 0.5986 | 0.6073 | 0.5986 | 0.7737 |
|
| 74 |
+
| No log | 0.4646 | 46 | 0.7060 | 0.5036 | 0.7060 | 0.8403 |
|
| 75 |
+
| No log | 0.4848 | 48 | 0.7054 | 0.5038 | 0.7054 | 0.8399 |
|
| 76 |
+
| No log | 0.5051 | 50 | 0.5853 | 0.5572 | 0.5853 | 0.7650 |
|
| 77 |
+
| No log | 0.5253 | 52 | 0.5009 | 0.5916 | 0.5009 | 0.7077 |
|
| 78 |
+
| No log | 0.5455 | 54 | 0.4653 | 0.6264 | 0.4653 | 0.6822 |
|
| 79 |
+
| No log | 0.5657 | 56 | 0.4675 | 0.6185 | 0.4675 | 0.6837 |
|
| 80 |
+
| No log | 0.5859 | 58 | 0.5101 | 0.5389 | 0.5101 | 0.7142 |
|
| 81 |
+
| No log | 0.6061 | 60 | 0.4829 | 0.5809 | 0.4829 | 0.6949 |
|
| 82 |
+
| No log | 0.6263 | 62 | 0.4443 | 0.5819 | 0.4443 | 0.6665 |
|
| 83 |
+
| No log | 0.6465 | 64 | 0.4506 | 0.6129 | 0.4506 | 0.6712 |
|
| 84 |
+
| No log | 0.6667 | 66 | 0.5041 | 0.6263 | 0.5041 | 0.7100 |
|
| 85 |
+
| No log | 0.6869 | 68 | 0.7029 | 0.4867 | 0.7029 | 0.8384 |
|
| 86 |
+
| No log | 0.7071 | 70 | 0.8082 | 0.4482 | 0.8082 | 0.8990 |
|
| 87 |
+
| No log | 0.7273 | 72 | 0.7248 | 0.5148 | 0.7248 | 0.8513 |
|
| 88 |
+
| No log | 0.7475 | 74 | 0.5613 | 0.5877 | 0.5613 | 0.7492 |
|
| 89 |
+
| No log | 0.7677 | 76 | 0.4909 | 0.6374 | 0.4909 | 0.7007 |
|
| 90 |
+
| No log | 0.7879 | 78 | 0.4660 | 0.6514 | 0.4660 | 0.6827 |
|
| 91 |
+
| No log | 0.8081 | 80 | 0.4851 | 0.5882 | 0.4851 | 0.6965 |
|
| 92 |
+
| No log | 0.8283 | 82 | 0.4962 | 0.5610 | 0.4962 | 0.7044 |
|
| 93 |
+
| No log | 0.8485 | 84 | 0.4615 | 0.5557 | 0.4615 | 0.6793 |
|
| 94 |
+
| No log | 0.8687 | 86 | 0.4440 | 0.5635 | 0.4440 | 0.6663 |
|
| 95 |
+
| No log | 0.8889 | 88 | 0.4314 | 0.5894 | 0.4314 | 0.6568 |
|
| 96 |
+
| No log | 0.9091 | 90 | 0.4190 | 0.5780 | 0.4190 | 0.6473 |
|
| 97 |
+
| No log | 0.9293 | 92 | 0.4786 | 0.5599 | 0.4786 | 0.6918 |
|
| 98 |
+
| No log | 0.9495 | 94 | 0.6113 | 0.5707 | 0.6113 | 0.7818 |
|
| 99 |
+
| No log | 0.9697 | 96 | 0.5209 | 0.6093 | 0.5209 | 0.7217 |
|
| 100 |
+
| No log | 0.9899 | 98 | 0.4775 | 0.6045 | 0.4775 | 0.6910 |
|
| 101 |
+
| No log | 1.0101 | 100 | 0.4327 | 0.6471 | 0.4327 | 0.6578 |
|
| 102 |
+
| No log | 1.0303 | 102 | 0.4660 | 0.6414 | 0.4660 | 0.6827 |
|
| 103 |
+
| No log | 1.0505 | 104 | 0.6273 | 0.5745 | 0.6273 | 0.7920 |
|
| 104 |
+
| No log | 1.0707 | 106 | 0.6881 | 0.5560 | 0.6881 | 0.8295 |
|
| 105 |
+
| No log | 1.0909 | 108 | 0.5957 | 0.5972 | 0.5957 | 0.7718 |
|
| 106 |
+
| No log | 1.1111 | 110 | 0.4659 | 0.6273 | 0.4659 | 0.6826 |
|
| 107 |
+
| No log | 1.1313 | 112 | 0.4384 | 0.6824 | 0.4384 | 0.6621 |
|
| 108 |
+
| No log | 1.1515 | 114 | 0.4231 | 0.6581 | 0.4231 | 0.6505 |
|
| 109 |
+
| No log | 1.1717 | 116 | 0.4279 | 0.6091 | 0.4279 | 0.6541 |
|
| 110 |
+
| No log | 1.1919 | 118 | 0.5012 | 0.6160 | 0.5012 | 0.7079 |
|
| 111 |
+
| No log | 1.2121 | 120 | 0.5547 | 0.5870 | 0.5547 | 0.7448 |
|
| 112 |
+
| No log | 1.2323 | 122 | 0.5423 | 0.5928 | 0.5423 | 0.7364 |
|
| 113 |
+
| No log | 1.2525 | 124 | 0.5302 | 0.6137 | 0.5302 | 0.7282 |
|
| 114 |
+
| No log | 1.2727 | 126 | 0.5858 | 0.5847 | 0.5858 | 0.7654 |
|
| 115 |
+
| No log | 1.2929 | 128 | 0.4783 | 0.6016 | 0.4783 | 0.6916 |
|
| 116 |
+
| No log | 1.3131 | 130 | 0.4545 | 0.5997 | 0.4545 | 0.6742 |
|
| 117 |
+
| No log | 1.3333 | 132 | 0.4900 | 0.6533 | 0.4900 | 0.7000 |
|
| 118 |
+
| No log | 1.3535 | 134 | 0.5569 | 0.6246 | 0.5569 | 0.7463 |
|
| 119 |
+
| No log | 1.3737 | 136 | 0.6941 | 0.5597 | 0.6941 | 0.8331 |
|
| 120 |
+
| No log | 1.3939 | 138 | 0.6269 | 0.5530 | 0.6269 | 0.7918 |
|
| 121 |
+
| No log | 1.4141 | 140 | 0.5370 | 0.6167 | 0.5370 | 0.7328 |
|
| 122 |
+
| No log | 1.4343 | 142 | 0.4683 | 0.6273 | 0.4683 | 0.6844 |
|
| 123 |
+
| No log | 1.4545 | 144 | 0.4653 | 0.6252 | 0.4653 | 0.6821 |
|
| 124 |
+
| No log | 1.4747 | 146 | 0.4532 | 0.6137 | 0.4532 | 0.6732 |
|
| 125 |
+
| No log | 1.4949 | 148 | 0.4565 | 0.6079 | 0.4565 | 0.6756 |
|
| 126 |
+
| No log | 1.5152 | 150 | 0.6492 | 0.5182 | 0.6492 | 0.8057 |
|
| 127 |
+
| No log | 1.5354 | 152 | 0.8368 | 0.3903 | 0.8368 | 0.9148 |
|
| 128 |
+
| No log | 1.5556 | 154 | 0.7759 | 0.4540 | 0.7759 | 0.8809 |
|
| 129 |
+
| No log | 1.5758 | 156 | 0.5920 | 0.5715 | 0.5920 | 0.7694 |
|
| 130 |
+
| No log | 1.5960 | 158 | 0.4664 | 0.5772 | 0.4664 | 0.6829 |
|
| 131 |
+
| No log | 1.6162 | 160 | 0.4405 | 0.6409 | 0.4405 | 0.6637 |
|
| 132 |
+
| No log | 1.6364 | 162 | 0.4782 | 0.6378 | 0.4782 | 0.6915 |
|
| 133 |
+
| No log | 1.6566 | 164 | 0.5797 | 0.5800 | 0.5797 | 0.7614 |
|
| 134 |
+
| No log | 1.6768 | 166 | 0.6372 | 0.5521 | 0.6372 | 0.7983 |
|
| 135 |
+
| No log | 1.6970 | 168 | 0.5039 | 0.6210 | 0.5039 | 0.7098 |
|
| 136 |
+
| No log | 1.7172 | 170 | 0.4606 | 0.6636 | 0.4606 | 0.6787 |
|
| 137 |
+
| No log | 1.7374 | 172 | 0.4801 | 0.6563 | 0.4801 | 0.6929 |
|
| 138 |
+
| No log | 1.7576 | 174 | 0.4554 | 0.6752 | 0.4554 | 0.6748 |
|
| 139 |
+
| No log | 1.7778 | 176 | 0.4792 | 0.6439 | 0.4792 | 0.6923 |
|
| 140 |
+
| No log | 1.7980 | 178 | 0.5210 | 0.6281 | 0.5210 | 0.7218 |
|
| 141 |
+
| No log | 1.8182 | 180 | 0.6026 | 0.5248 | 0.6026 | 0.7763 |
|
| 142 |
+
| No log | 1.8384 | 182 | 0.6646 | 0.4807 | 0.6646 | 0.8152 |
|
| 143 |
+
| No log | 1.8586 | 184 | 0.7238 | 0.4611 | 0.7238 | 0.8508 |
|
| 144 |
+
| No log | 1.8788 | 186 | 0.5563 | 0.5518 | 0.5563 | 0.7459 |
|
| 145 |
+
| No log | 1.8990 | 188 | 0.4310 | 0.6262 | 0.4310 | 0.6565 |
|
| 146 |
+
| No log | 1.9192 | 190 | 0.4659 | 0.6464 | 0.4659 | 0.6826 |
|
| 147 |
+
| No log | 1.9394 | 192 | 0.5744 | 0.5836 | 0.5744 | 0.7579 |
|
| 148 |
+
| No log | 1.9596 | 194 | 0.5957 | 0.5864 | 0.5957 | 0.7718 |
|
| 149 |
+
| No log | 1.9798 | 196 | 0.5255 | 0.6336 | 0.5255 | 0.7249 |
|
| 150 |
+
| No log | 2.0 | 198 | 0.5154 | 0.6167 | 0.5154 | 0.7179 |
|
| 151 |
+
| No log | 2.0202 | 200 | 0.5811 | 0.5599 | 0.5811 | 0.7623 |
|
| 152 |
+
| No log | 2.0404 | 202 | 0.6868 | 0.5241 | 0.6868 | 0.8287 |
|
| 153 |
+
| No log | 2.0606 | 204 | 0.6167 | 0.5619 | 0.6167 | 0.7853 |
|
| 154 |
+
| No log | 2.0808 | 206 | 0.4414 | 0.7001 | 0.4414 | 0.6644 |
|
| 155 |
+
| No log | 2.1010 | 208 | 0.4241 | 0.7258 | 0.4241 | 0.6512 |
|
| 156 |
+
| No log | 2.1212 | 210 | 0.5128 | 0.6553 | 0.5128 | 0.7161 |
|
| 157 |
+
| No log | 2.1414 | 212 | 0.7633 | 0.5285 | 0.7633 | 0.8736 |
|
| 158 |
+
| No log | 2.1616 | 214 | 0.7805 | 0.5364 | 0.7805 | 0.8834 |
|
| 159 |
+
| No log | 2.1818 | 216 | 0.6143 | 0.5962 | 0.6143 | 0.7838 |
|
| 160 |
+
| No log | 2.2020 | 218 | 0.4738 | 0.7078 | 0.4738 | 0.6883 |
|
| 161 |
+
| No log | 2.2222 | 220 | 0.4811 | 0.6576 | 0.4811 | 0.6936 |
|
| 162 |
+
| No log | 2.2424 | 222 | 0.4788 | 0.6576 | 0.4788 | 0.6919 |
|
| 163 |
+
| No log | 2.2626 | 224 | 0.5424 | 0.6320 | 0.5424 | 0.7364 |
|
| 164 |
+
| No log | 2.2828 | 226 | 0.5690 | 0.6031 | 0.5690 | 0.7543 |
|
| 165 |
+
| No log | 2.3030 | 228 | 0.5594 | 0.6390 | 0.5594 | 0.7480 |
|
| 166 |
+
| No log | 2.3232 | 230 | 0.5012 | 0.6828 | 0.5012 | 0.7080 |
|
| 167 |
+
| No log | 2.3434 | 232 | 0.4376 | 0.6912 | 0.4376 | 0.6615 |
|
| 168 |
+
| No log | 2.3636 | 234 | 0.4209 | 0.6885 | 0.4209 | 0.6488 |
|
| 169 |
+
| No log | 2.3838 | 236 | 0.4412 | 0.6679 | 0.4412 | 0.6642 |
|
| 170 |
+
| No log | 2.4040 | 238 | 0.6753 | 0.4904 | 0.6753 | 0.8218 |
|
| 171 |
+
| No log | 2.4242 | 240 | 0.8822 | 0.3803 | 0.8822 | 0.9393 |
|
| 172 |
+
| No log | 2.4444 | 242 | 0.8198 | 0.4415 | 0.8198 | 0.9054 |
|
| 173 |
+
| No log | 2.4646 | 244 | 0.7410 | 0.4814 | 0.7410 | 0.8608 |
|
| 174 |
+
| No log | 2.4848 | 246 | 0.6392 | 0.5406 | 0.6392 | 0.7995 |
|
| 175 |
+
| No log | 2.5051 | 248 | 0.4713 | 0.6135 | 0.4713 | 0.6865 |
|
| 176 |
+
| No log | 2.5253 | 250 | 0.4495 | 0.6600 | 0.4495 | 0.6704 |
|
| 177 |
+
| No log | 2.5455 | 252 | 0.4332 | 0.6803 | 0.4332 | 0.6582 |
|
| 178 |
+
| No log | 2.5657 | 254 | 0.4518 | 0.6980 | 0.4518 | 0.6721 |
|
| 179 |
+
| No log | 2.5859 | 256 | 0.5212 | 0.6659 | 0.5212 | 0.7219 |
|
| 180 |
+
| No log | 2.6061 | 258 | 0.7160 | 0.5233 | 0.7160 | 0.8462 |
|
| 181 |
+
| No log | 2.6263 | 260 | 0.7221 | 0.4580 | 0.7221 | 0.8497 |
|
| 182 |
+
| No log | 2.6465 | 262 | 0.5726 | 0.4901 | 0.5726 | 0.7567 |
|
| 183 |
+
| No log | 2.6667 | 264 | 0.4629 | 0.5599 | 0.4629 | 0.6803 |
|
| 184 |
+
| No log | 2.6869 | 266 | 0.4259 | 0.6264 | 0.4259 | 0.6526 |
|
| 185 |
+
| No log | 2.7071 | 268 | 0.4130 | 0.6564 | 0.4130 | 0.6426 |
|
| 186 |
+
| No log | 2.7273 | 270 | 0.4060 | 0.6488 | 0.4060 | 0.6372 |
|
| 187 |
+
| No log | 2.7475 | 272 | 0.4092 | 0.6694 | 0.4092 | 0.6397 |
|
| 188 |
+
| No log | 2.7677 | 274 | 0.4230 | 0.7175 | 0.4230 | 0.6504 |
|
| 189 |
+
| No log | 2.7879 | 276 | 0.5503 | 0.5953 | 0.5503 | 0.7418 |
|
| 190 |
+
| No log | 2.8081 | 278 | 0.6174 | 0.5455 | 0.6174 | 0.7857 |
|
| 191 |
+
| No log | 2.8283 | 280 | 0.5289 | 0.6188 | 0.5289 | 0.7273 |
|
| 192 |
+
| No log | 2.8485 | 282 | 0.4348 | 0.6377 | 0.4348 | 0.6594 |
|
| 193 |
+
| No log | 2.8687 | 284 | 0.4178 | 0.6303 | 0.4178 | 0.6464 |
|
| 194 |
+
| No log | 2.8889 | 286 | 0.4285 | 0.5560 | 0.4285 | 0.6546 |
|
| 195 |
+
| No log | 2.9091 | 288 | 0.4839 | 0.4733 | 0.4839 | 0.6956 |
|
| 196 |
+
| No log | 2.9293 | 290 | 0.5337 | 0.4651 | 0.5337 | 0.7305 |
|
| 197 |
+
| No log | 2.9495 | 292 | 0.5038 | 0.5155 | 0.5038 | 0.7098 |
|
| 198 |
+
| No log | 2.9697 | 294 | 0.4717 | 0.5880 | 0.4717 | 0.6868 |
|
| 199 |
+
| No log | 2.9899 | 296 | 0.4817 | 0.6284 | 0.4817 | 0.6940 |
|
| 200 |
+
| No log | 3.0101 | 298 | 0.4936 | 0.6336 | 0.4936 | 0.7025 |
|
| 201 |
+
| No log | 3.0303 | 300 | 0.4310 | 0.6946 | 0.4310 | 0.6565 |
|
| 202 |
+
| No log | 3.0505 | 302 | 0.4184 | 0.7028 | 0.4184 | 0.6468 |
|
| 203 |
+
| No log | 3.0707 | 304 | 0.4944 | 0.6255 | 0.4944 | 0.7032 |
|
| 204 |
+
| No log | 3.0909 | 306 | 0.5080 | 0.6313 | 0.5080 | 0.7128 |
|
| 205 |
+
| No log | 3.1111 | 308 | 0.4478 | 0.6972 | 0.4478 | 0.6692 |
|
| 206 |
+
| No log | 3.1313 | 310 | 0.4734 | 0.6913 | 0.4734 | 0.6881 |
|
| 207 |
+
| No log | 3.1515 | 312 | 0.5411 | 0.6360 | 0.5411 | 0.7356 |
|
| 208 |
+
| No log | 3.1717 | 314 | 0.5459 | 0.6367 | 0.5459 | 0.7388 |
|
| 209 |
+
| No log | 3.1919 | 316 | 0.5335 | 0.6552 | 0.5335 | 0.7304 |
|
| 210 |
+
| No log | 3.2121 | 318 | 0.4951 | 0.6289 | 0.4951 | 0.7036 |
|
| 211 |
+
| No log | 3.2323 | 320 | 0.5534 | 0.6154 | 0.5534 | 0.7439 |
|
| 212 |
+
| No log | 3.2525 | 322 | 0.5340 | 0.6382 | 0.5340 | 0.7308 |
|
| 213 |
+
| No log | 3.2727 | 324 | 0.4645 | 0.6822 | 0.4645 | 0.6816 |
|
| 214 |
+
| No log | 3.2929 | 326 | 0.5300 | 0.6255 | 0.5300 | 0.7280 |
|
| 215 |
+
| No log | 3.3131 | 328 | 0.5323 | 0.6188 | 0.5323 | 0.7296 |
|
| 216 |
+
| No log | 3.3333 | 330 | 0.4859 | 0.6475 | 0.4859 | 0.6971 |
|
| 217 |
+
| No log | 3.3535 | 332 | 0.8037 | 0.5090 | 0.8037 | 0.8965 |
|
| 218 |
+
| No log | 3.3737 | 334 | 1.0383 | 0.4066 | 1.0383 | 1.0190 |
|
| 219 |
+
| No log | 3.3939 | 336 | 0.9358 | 0.4225 | 0.9358 | 0.9674 |
|
| 220 |
+
| No log | 3.4141 | 338 | 0.6982 | 0.5351 | 0.6982 | 0.8356 |
|
| 221 |
+
| No log | 3.4343 | 340 | 0.4546 | 0.6613 | 0.4546 | 0.6742 |
|
| 222 |
+
| No log | 3.4545 | 342 | 0.4228 | 0.6513 | 0.4228 | 0.6503 |
|
| 223 |
+
| No log | 3.4747 | 344 | 0.4159 | 0.6534 | 0.4159 | 0.6449 |
|
| 224 |
+
| No log | 3.4949 | 346 | 0.4126 | 0.6701 | 0.4126 | 0.6423 |
|
| 225 |
+
| No log | 3.5152 | 348 | 0.4794 | 0.6609 | 0.4794 | 0.6924 |
|
| 226 |
+
| No log | 3.5354 | 350 | 0.6280 | 0.6011 | 0.6280 | 0.7925 |
|
| 227 |
+
| No log | 3.5556 | 352 | 0.6433 | 0.6017 | 0.6433 | 0.8021 |
|
| 228 |
+
| No log | 3.5758 | 354 | 0.6046 | 0.6257 | 0.6046 | 0.7776 |
|
| 229 |
+
| No log | 3.5960 | 356 | 0.5843 | 0.6432 | 0.5843 | 0.7644 |
|
| 230 |
+
| No log | 3.6162 | 358 | 0.6137 | 0.6347 | 0.6137 | 0.7834 |
|
| 231 |
+
| No log | 3.6364 | 360 | 0.5384 | 0.6956 | 0.5384 | 0.7338 |
|
| 232 |
+
| No log | 3.6566 | 362 | 0.4696 | 0.6935 | 0.4696 | 0.6852 |
|
| 233 |
+
| No log | 3.6768 | 364 | 0.4149 | 0.6971 | 0.4149 | 0.6441 |
|
| 234 |
+
| No log | 3.6970 | 366 | 0.3950 | 0.6830 | 0.3950 | 0.6285 |
|
| 235 |
+
| No log | 3.7172 | 368 | 0.4067 | 0.6970 | 0.4067 | 0.6377 |
|
| 236 |
+
| No log | 3.7374 | 370 | 0.4379 | 0.6542 | 0.4379 | 0.6617 |
|
| 237 |
+
| No log | 3.7576 | 372 | 0.4702 | 0.6351 | 0.4702 | 0.6857 |
|
| 238 |
+
| No log | 3.7778 | 374 | 0.5298 | 0.6325 | 0.5298 | 0.7279 |
|
| 239 |
+
| No log | 3.7980 | 376 | 0.4978 | 0.6568 | 0.4978 | 0.7055 |
|
| 240 |
+
| No log | 3.8182 | 378 | 0.4240 | 0.7229 | 0.4240 | 0.6512 |
|
| 241 |
+
| No log | 3.8384 | 380 | 0.4542 | 0.7255 | 0.4542 | 0.6739 |
|
| 242 |
+
| No log | 3.8586 | 382 | 0.4801 | 0.7224 | 0.4801 | 0.6929 |
|
| 243 |
+
| No log | 3.8788 | 384 | 0.6541 | 0.5992 | 0.6541 | 0.8088 |
|
| 244 |
+
| No log | 3.8990 | 386 | 0.8113 | 0.5203 | 0.8113 | 0.9007 |
|
| 245 |
+
| No log | 3.9192 | 388 | 0.8043 | 0.4722 | 0.8043 | 0.8969 |
|
| 246 |
+
| No log | 3.9394 | 390 | 0.6871 | 0.5415 | 0.6871 | 0.8289 |
|
| 247 |
+
| No log | 3.9596 | 392 | 0.5006 | 0.6487 | 0.5006 | 0.7075 |
|
| 248 |
+
| No log | 3.9798 | 394 | 0.4014 | 0.6952 | 0.4014 | 0.6336 |
|
| 249 |
+
| No log | 4.0 | 396 | 0.3954 | 0.7081 | 0.3954 | 0.6288 |
|
| 250 |
+
| No log | 4.0202 | 398 | 0.3888 | 0.7006 | 0.3888 | 0.6235 |
|
| 251 |
+
| No log | 4.0404 | 400 | 0.3961 | 0.6757 | 0.3961 | 0.6294 |
|
| 252 |
+
| No log | 4.0606 | 402 | 0.4855 | 0.6713 | 0.4855 | 0.6968 |
|
| 253 |
+
| No log | 4.0808 | 404 | 0.6802 | 0.5927 | 0.6802 | 0.8247 |
|
| 254 |
+
| No log | 4.1010 | 406 | 0.7531 | 0.5652 | 0.7531 | 0.8678 |
|
| 255 |
+
| No log | 4.1212 | 408 | 0.7370 | 0.5833 | 0.7370 | 0.8585 |
|
| 256 |
+
| No log | 4.1414 | 410 | 0.5869 | 0.6642 | 0.5869 | 0.7661 |
|
| 257 |
+
| No log | 4.1616 | 412 | 0.4251 | 0.7180 | 0.4251 | 0.6520 |
|
| 258 |
+
| No log | 4.1818 | 414 | 0.4382 | 0.6799 | 0.4382 | 0.6620 |
|
| 259 |
+
| No log | 4.2020 | 416 | 0.4375 | 0.6904 | 0.4375 | 0.6615 |
|
| 260 |
+
| No log | 4.2222 | 418 | 0.4337 | 0.7220 | 0.4337 | 0.6586 |
|
| 261 |
+
| No log | 4.2424 | 420 | 0.5478 | 0.6365 | 0.5478 | 0.7401 |
|
| 262 |
+
| No log | 4.2626 | 422 | 0.6164 | 0.5760 | 0.6164 | 0.7851 |
|
| 263 |
+
| No log | 4.2828 | 424 | 0.5083 | 0.6794 | 0.5083 | 0.7130 |
|
| 264 |
+
| No log | 4.3030 | 426 | 0.4537 | 0.7117 | 0.4537 | 0.6736 |
|
| 265 |
+
| No log | 4.3232 | 428 | 0.4351 | 0.7133 | 0.4351 | 0.6596 |
|
| 266 |
+
| No log | 4.3434 | 430 | 0.4543 | 0.7124 | 0.4543 | 0.6740 |
|
| 267 |
+
| No log | 4.3636 | 432 | 0.5776 | 0.6197 | 0.5776 | 0.7600 |
|
| 268 |
+
| No log | 4.3838 | 434 | 0.7524 | 0.5262 | 0.7524 | 0.8674 |
|
| 269 |
+
| No log | 4.4040 | 436 | 0.7590 | 0.5032 | 0.7590 | 0.8712 |
|
| 270 |
+
| No log | 4.4242 | 438 | 0.6817 | 0.5460 | 0.6817 | 0.8257 |
|
| 271 |
+
| No log | 4.4444 | 440 | 0.6062 | 0.5985 | 0.6062 | 0.7786 |
|
| 272 |
+
| No log | 4.4646 | 442 | 0.5581 | 0.6562 | 0.5581 | 0.7471 |
|
| 273 |
+
| No log | 4.4848 | 444 | 0.5730 | 0.6754 | 0.5730 | 0.7569 |
|
| 274 |
+
| No log | 4.5051 | 446 | 0.6333 | 0.6874 | 0.6333 | 0.7958 |
|
| 275 |
+
| No log | 4.5253 | 448 | 0.6988 | 0.6098 | 0.6988 | 0.8359 |
|
| 276 |
+
| No log | 4.5455 | 450 | 0.6742 | 0.6180 | 0.6742 | 0.8211 |
|
| 277 |
+
| No log | 4.5657 | 452 | 0.5538 | 0.6498 | 0.5538 | 0.7442 |
|
| 278 |
+
| No log | 4.5859 | 454 | 0.4457 | 0.6213 | 0.4457 | 0.6676 |
|
| 279 |
+
| No log | 4.6061 | 456 | 0.4182 | 0.6250 | 0.4182 | 0.6467 |
|
| 280 |
+
| No log | 4.6263 | 458 | 0.4380 | 0.6350 | 0.4380 | 0.6619 |
|
| 281 |
+
| No log | 4.6465 | 460 | 0.5240 | 0.6251 | 0.5240 | 0.7239 |
|
| 282 |
+
| No log | 4.6667 | 462 | 0.5389 | 0.6459 | 0.5389 | 0.7341 |
|
| 283 |
+
| No log | 4.6869 | 464 | 0.5117 | 0.6927 | 0.5117 | 0.7154 |
|
| 284 |
+
| No log | 4.7071 | 466 | 0.5187 | 0.7049 | 0.5187 | 0.7202 |
|
| 285 |
+
| No log | 4.7273 | 468 | 0.4985 | 0.7188 | 0.4985 | 0.7060 |
|
| 286 |
+
| No log | 4.7475 | 470 | 0.4804 | 0.6795 | 0.4804 | 0.6931 |
|
| 287 |
+
| No log | 4.7677 | 472 | 0.5161 | 0.6677 | 0.5161 | 0.7184 |
|
| 288 |
+
| No log | 4.7879 | 474 | 0.6234 | 0.5944 | 0.6234 | 0.7896 |
|
| 289 |
+
| No log | 4.8081 | 476 | 0.6180 | 0.6254 | 0.6180 | 0.7861 |
|
| 290 |
+
| No log | 4.8283 | 478 | 0.5394 | 0.6633 | 0.5394 | 0.7344 |
|
| 291 |
+
| No log | 4.8485 | 480 | 0.5032 | 0.7041 | 0.5032 | 0.7094 |
|
| 292 |
+
| No log | 4.8687 | 482 | 0.4854 | 0.7186 | 0.4854 | 0.6967 |
|
| 293 |
+
| No log | 4.8889 | 484 | 0.5197 | 0.6469 | 0.5197 | 0.7209 |
|
| 294 |
+
| No log | 4.9091 | 486 | 0.6987 | 0.5691 | 0.6987 | 0.8359 |
|
| 295 |
+
| No log | 4.9293 | 488 | 0.8566 | 0.4831 | 0.8566 | 0.9255 |
|
| 296 |
+
| No log | 4.9495 | 490 | 0.7736 | 0.5194 | 0.7736 | 0.8796 |
|
| 297 |
+
| No log | 4.9697 | 492 | 0.5160 | 0.5824 | 0.5160 | 0.7183 |
|
| 298 |
+
| No log | 4.9899 | 494 | 0.4634 | 0.6021 | 0.4634 | 0.6808 |
|
| 299 |
+
| No log | 5.0101 | 496 | 0.4314 | 0.6340 | 0.4314 | 0.6568 |
|
| 300 |
+
| No log | 5.0303 | 498 | 0.4743 | 0.6609 | 0.4743 | 0.6887 |
|
| 301 |
+
| 0.5311 | 5.0505 | 500 | 0.6548 | 0.6347 | 0.6548 | 0.8092 |
|
| 302 |
+
| 0.5311 | 5.0707 | 502 | 0.9260 | 0.5815 | 0.9260 | 0.9623 |
|
| 303 |
+
| 0.5311 | 5.0909 | 504 | 0.8772 | 0.5922 | 0.8772 | 0.9366 |
|
| 304 |
+
| 0.5311 | 5.1111 | 506 | 0.7710 | 0.6230 | 0.7710 | 0.8781 |
|
| 305 |
+
| 0.5311 | 5.1313 | 508 | 0.6076 | 0.6666 | 0.6076 | 0.7795 |
|
| 306 |
+
| 0.5311 | 5.1515 | 510 | 0.5119 | 0.6977 | 0.5119 | 0.7155 |
|
| 307 |
+
| 0.5311 | 5.1717 | 512 | 0.5983 | 0.6629 | 0.5983 | 0.7735 |
|
| 308 |
+
| 0.5311 | 5.1919 | 514 | 0.5607 | 0.6643 | 0.5607 | 0.7488 |
|
| 309 |
+
| 0.5311 | 5.2121 | 516 | 0.4336 | 0.6699 | 0.4336 | 0.6585 |
|
| 310 |
+
| 0.5311 | 5.2323 | 518 | 0.4463 | 0.6578 | 0.4463 | 0.6681 |
|
| 311 |
+
| 0.5311 | 5.2525 | 520 | 0.5635 | 0.5910 | 0.5635 | 0.7507 |
|
| 312 |
+
| 0.5311 | 5.2727 | 522 | 0.6719 | 0.5514 | 0.6719 | 0.8197 |
|
| 313 |
+
| 0.5311 | 5.2929 | 524 | 0.6379 | 0.6048 | 0.6379 | 0.7987 |
|
| 314 |
+
| 0.5311 | 5.3131 | 526 | 0.5615 | 0.6597 | 0.5615 | 0.7493 |
|
| 315 |
+
| 0.5311 | 5.3333 | 528 | 0.4546 | 0.7072 | 0.4546 | 0.6742 |
|
| 316 |
+
| 0.5311 | 5.3535 | 530 | 0.4233 | 0.6703 | 0.4233 | 0.6506 |
|
| 317 |
+
| 0.5311 | 5.3737 | 532 | 0.3957 | 0.6873 | 0.3957 | 0.6291 |
|
| 318 |
+
| 0.5311 | 5.3939 | 534 | 0.4237 | 0.6549 | 0.4237 | 0.6509 |
|
| 319 |
+
| 0.5311 | 5.4141 | 536 | 0.5246 | 0.6222 | 0.5246 | 0.7243 |
|
| 320 |
+
| 0.5311 | 5.4343 | 538 | 0.6562 | 0.5383 | 0.6562 | 0.8100 |
|
| 321 |
+
| 0.5311 | 5.4545 | 540 | 0.6706 | 0.5183 | 0.6706 | 0.8189 |
|
| 322 |
+
| 0.5311 | 5.4747 | 542 | 0.5935 | 0.5883 | 0.5935 | 0.7704 |
|
| 323 |
+
| 0.5311 | 5.4949 | 544 | 0.5122 | 0.6327 | 0.5122 | 0.7157 |
|
| 324 |
+
|
| 325 |
+
|
| 326 |
+
### Framework versions
|
| 327 |
+
|
| 328 |
+
- Transformers 4.44.2
|
| 329 |
+
- Pytorch 2.4.0+cu118
|
| 330 |
+
- Datasets 2.21.0
|
| 331 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv02",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 64000
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9da9b87ebdf7a2030b9dbce6fd2f04e2c537a9c079a6e31d9e9f936d4f396cc
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3045777f174b633b308019f69e60bf09b3002b3b17430d34ce4ccbc2fefb45c3
|
| 3 |
+
size 5240
|