Training in progress, step 500
Browse files- README.md +363 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_TestTask4_grammar
|
| 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_TestTask4_grammar
|
| 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: 0.4946
|
| 19 |
+
- Qwk: 0.5245
|
| 20 |
+
- Mse: 0.4946
|
| 21 |
+
- Rmse: 0.7033
|
| 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 | 0.0187 | 2 | 4.6909 | 0.0067 | 4.6909 | 2.1658 |
|
| 53 |
+
| No log | 0.0374 | 4 | 3.3550 | 0.0504 | 3.3550 | 1.8317 |
|
| 54 |
+
| No log | 0.0561 | 6 | 1.8060 | 0.1151 | 1.8060 | 1.3439 |
|
| 55 |
+
| No log | 0.0748 | 8 | 0.9222 | 0.1800 | 0.9222 | 0.9603 |
|
| 56 |
+
| No log | 0.0935 | 10 | 0.8426 | 0.1258 | 0.8426 | 0.9180 |
|
| 57 |
+
| No log | 0.1121 | 12 | 0.8917 | 0.1169 | 0.8917 | 0.9443 |
|
| 58 |
+
| No log | 0.1308 | 14 | 1.0185 | 0.0879 | 1.0185 | 1.0092 |
|
| 59 |
+
| No log | 0.1495 | 16 | 1.0964 | 0.0863 | 1.0964 | 1.0471 |
|
| 60 |
+
| No log | 0.1682 | 18 | 0.9224 | 0.2409 | 0.9224 | 0.9604 |
|
| 61 |
+
| No log | 0.1869 | 20 | 0.8513 | 0.1995 | 0.8513 | 0.9227 |
|
| 62 |
+
| No log | 0.2056 | 22 | 0.7326 | 0.2205 | 0.7326 | 0.8559 |
|
| 63 |
+
| No log | 0.2243 | 24 | 0.6936 | 0.2493 | 0.6936 | 0.8328 |
|
| 64 |
+
| No log | 0.2430 | 26 | 0.6989 | 0.3637 | 0.6989 | 0.8360 |
|
| 65 |
+
| No log | 0.2617 | 28 | 0.7834 | 0.3652 | 0.7834 | 0.8851 |
|
| 66 |
+
| No log | 0.2804 | 30 | 0.6835 | 0.3956 | 0.6835 | 0.8267 |
|
| 67 |
+
| No log | 0.2991 | 32 | 0.6387 | 0.3739 | 0.6387 | 0.7992 |
|
| 68 |
+
| No log | 0.3178 | 34 | 0.7230 | 0.3301 | 0.7230 | 0.8503 |
|
| 69 |
+
| No log | 0.3364 | 36 | 0.7429 | 0.3196 | 0.7429 | 0.8619 |
|
| 70 |
+
| No log | 0.3551 | 38 | 0.6954 | 0.3338 | 0.6954 | 0.8339 |
|
| 71 |
+
| No log | 0.3738 | 40 | 0.6865 | 0.3419 | 0.6865 | 0.8286 |
|
| 72 |
+
| No log | 0.3925 | 42 | 0.6636 | 0.3361 | 0.6636 | 0.8146 |
|
| 73 |
+
| No log | 0.4112 | 44 | 0.6712 | 0.3367 | 0.6712 | 0.8193 |
|
| 74 |
+
| No log | 0.4299 | 46 | 0.7001 | 0.3346 | 0.7001 | 0.8367 |
|
| 75 |
+
| No log | 0.4486 | 48 | 0.7158 | 0.3153 | 0.7158 | 0.8461 |
|
| 76 |
+
| No log | 0.4673 | 50 | 0.6919 | 0.3314 | 0.6919 | 0.8318 |
|
| 77 |
+
| No log | 0.4860 | 52 | 0.6841 | 0.3344 | 0.6841 | 0.8271 |
|
| 78 |
+
| No log | 0.5047 | 54 | 0.6269 | 0.3067 | 0.6269 | 0.7917 |
|
| 79 |
+
| No log | 0.5234 | 56 | 0.6212 | 0.3513 | 0.6212 | 0.7881 |
|
| 80 |
+
| No log | 0.5421 | 58 | 0.6123 | 0.3793 | 0.6123 | 0.7825 |
|
| 81 |
+
| No log | 0.5607 | 60 | 0.5916 | 0.3094 | 0.5916 | 0.7692 |
|
| 82 |
+
| No log | 0.5794 | 62 | 0.6205 | 0.2840 | 0.6205 | 0.7877 |
|
| 83 |
+
| No log | 0.5981 | 64 | 0.5838 | 0.3333 | 0.5838 | 0.7641 |
|
| 84 |
+
| No log | 0.6168 | 66 | 0.5679 | 0.4087 | 0.5679 | 0.7536 |
|
| 85 |
+
| No log | 0.6355 | 68 | 0.5330 | 0.4381 | 0.5330 | 0.7301 |
|
| 86 |
+
| No log | 0.6542 | 70 | 0.5568 | 0.4050 | 0.5568 | 0.7462 |
|
| 87 |
+
| No log | 0.6729 | 72 | 0.5778 | 0.4466 | 0.5778 | 0.7601 |
|
| 88 |
+
| No log | 0.6916 | 74 | 0.7796 | 0.3016 | 0.7796 | 0.8830 |
|
| 89 |
+
| No log | 0.7103 | 76 | 0.8055 | 0.2610 | 0.8055 | 0.8975 |
|
| 90 |
+
| No log | 0.7290 | 78 | 0.8392 | 0.1976 | 0.8392 | 0.9161 |
|
| 91 |
+
| No log | 0.7477 | 80 | 0.8873 | 0.1131 | 0.8873 | 0.9419 |
|
| 92 |
+
| No log | 0.7664 | 82 | 0.9376 | 0.1404 | 0.9376 | 0.9683 |
|
| 93 |
+
| No log | 0.7850 | 84 | 1.0218 | 0.1780 | 1.0218 | 1.0109 |
|
| 94 |
+
| No log | 0.8037 | 86 | 0.9614 | 0.1926 | 0.9614 | 0.9805 |
|
| 95 |
+
| No log | 0.8224 | 88 | 0.7407 | 0.4210 | 0.7407 | 0.8606 |
|
| 96 |
+
| No log | 0.8411 | 90 | 0.5650 | 0.4620 | 0.5650 | 0.7516 |
|
| 97 |
+
| No log | 0.8598 | 92 | 0.5112 | 0.4219 | 0.5112 | 0.7150 |
|
| 98 |
+
| No log | 0.8785 | 94 | 0.5244 | 0.3832 | 0.5244 | 0.7241 |
|
| 99 |
+
| No log | 0.8972 | 96 | 0.5448 | 0.3759 | 0.5448 | 0.7381 |
|
| 100 |
+
| No log | 0.9159 | 98 | 0.5472 | 0.3533 | 0.5472 | 0.7397 |
|
| 101 |
+
| No log | 0.9346 | 100 | 0.5826 | 0.3699 | 0.5826 | 0.7633 |
|
| 102 |
+
| No log | 0.9533 | 102 | 0.6793 | 0.4322 | 0.6793 | 0.8242 |
|
| 103 |
+
| No log | 0.9720 | 104 | 0.7808 | 0.4309 | 0.7808 | 0.8836 |
|
| 104 |
+
| No log | 0.9907 | 106 | 0.7082 | 0.4691 | 0.7082 | 0.8415 |
|
| 105 |
+
| No log | 1.0093 | 108 | 0.6321 | 0.4551 | 0.6321 | 0.7950 |
|
| 106 |
+
| No log | 1.0280 | 110 | 0.5119 | 0.4712 | 0.5119 | 0.7154 |
|
| 107 |
+
| No log | 1.0467 | 112 | 0.4803 | 0.4973 | 0.4803 | 0.6931 |
|
| 108 |
+
| No log | 1.0654 | 114 | 0.4714 | 0.5047 | 0.4714 | 0.6866 |
|
| 109 |
+
| No log | 1.0841 | 116 | 0.4958 | 0.5252 | 0.4958 | 0.7042 |
|
| 110 |
+
| No log | 1.1028 | 118 | 0.6300 | 0.5123 | 0.6300 | 0.7937 |
|
| 111 |
+
| No log | 1.1215 | 120 | 0.6902 | 0.5153 | 0.6902 | 0.8308 |
|
| 112 |
+
| No log | 1.1402 | 122 | 0.6344 | 0.5549 | 0.6344 | 0.7965 |
|
| 113 |
+
| No log | 1.1589 | 124 | 0.5181 | 0.6337 | 0.5181 | 0.7198 |
|
| 114 |
+
| No log | 1.1776 | 126 | 0.5060 | 0.6224 | 0.5060 | 0.7113 |
|
| 115 |
+
| No log | 1.1963 | 128 | 0.5268 | 0.6368 | 0.5268 | 0.7258 |
|
| 116 |
+
| No log | 1.2150 | 130 | 0.5112 | 0.6431 | 0.5112 | 0.7150 |
|
| 117 |
+
| No log | 1.2336 | 132 | 0.4970 | 0.6516 | 0.4970 | 0.7049 |
|
| 118 |
+
| No log | 1.2523 | 134 | 0.4880 | 0.6287 | 0.4880 | 0.6986 |
|
| 119 |
+
| No log | 1.2710 | 136 | 0.5088 | 0.6221 | 0.5088 | 0.7133 |
|
| 120 |
+
| No log | 1.2897 | 138 | 0.5693 | 0.5806 | 0.5693 | 0.7545 |
|
| 121 |
+
| No log | 1.3084 | 140 | 0.6024 | 0.5615 | 0.6024 | 0.7762 |
|
| 122 |
+
| No log | 1.3271 | 142 | 0.6086 | 0.5236 | 0.6086 | 0.7801 |
|
| 123 |
+
| No log | 1.3458 | 144 | 0.4797 | 0.5731 | 0.4797 | 0.6926 |
|
| 124 |
+
| No log | 1.3645 | 146 | 0.4482 | 0.5821 | 0.4482 | 0.6695 |
|
| 125 |
+
| No log | 1.3832 | 148 | 0.4818 | 0.5926 | 0.4818 | 0.6941 |
|
| 126 |
+
| No log | 1.4019 | 150 | 0.4787 | 0.5917 | 0.4787 | 0.6918 |
|
| 127 |
+
| No log | 1.4206 | 152 | 0.4551 | 0.5398 | 0.4551 | 0.6746 |
|
| 128 |
+
| No log | 1.4393 | 154 | 0.5331 | 0.4403 | 0.5331 | 0.7301 |
|
| 129 |
+
| No log | 1.4579 | 156 | 0.6580 | 0.4073 | 0.6580 | 0.8112 |
|
| 130 |
+
| No log | 1.4766 | 158 | 0.7586 | 0.3895 | 0.7586 | 0.8710 |
|
| 131 |
+
| No log | 1.4953 | 160 | 0.7507 | 0.4276 | 0.7507 | 0.8664 |
|
| 132 |
+
| No log | 1.5140 | 162 | 0.6379 | 0.4460 | 0.6379 | 0.7987 |
|
| 133 |
+
| No log | 1.5327 | 164 | 0.5549 | 0.4837 | 0.5549 | 0.7449 |
|
| 134 |
+
| No log | 1.5514 | 166 | 0.4786 | 0.6031 | 0.4786 | 0.6918 |
|
| 135 |
+
| No log | 1.5701 | 168 | 0.4632 | 0.6238 | 0.4632 | 0.6806 |
|
| 136 |
+
| No log | 1.5888 | 170 | 0.4807 | 0.6470 | 0.4807 | 0.6933 |
|
| 137 |
+
| No log | 1.6075 | 172 | 0.4879 | 0.6186 | 0.4879 | 0.6985 |
|
| 138 |
+
| No log | 1.6262 | 174 | 0.6092 | 0.5360 | 0.6092 | 0.7805 |
|
| 139 |
+
| No log | 1.6449 | 176 | 0.7225 | 0.3810 | 0.7225 | 0.8500 |
|
| 140 |
+
| No log | 1.6636 | 178 | 0.7457 | 0.3395 | 0.7457 | 0.8635 |
|
| 141 |
+
| No log | 1.6822 | 180 | 0.6915 | 0.4367 | 0.6915 | 0.8316 |
|
| 142 |
+
| No log | 1.7009 | 182 | 0.5971 | 0.5079 | 0.5971 | 0.7727 |
|
| 143 |
+
| No log | 1.7196 | 184 | 0.4874 | 0.5671 | 0.4874 | 0.6981 |
|
| 144 |
+
| No log | 1.7383 | 186 | 0.4545 | 0.5565 | 0.4545 | 0.6742 |
|
| 145 |
+
| No log | 1.7570 | 188 | 0.4996 | 0.5464 | 0.4996 | 0.7068 |
|
| 146 |
+
| No log | 1.7757 | 190 | 0.4844 | 0.5489 | 0.4844 | 0.6960 |
|
| 147 |
+
| No log | 1.7944 | 192 | 0.4610 | 0.5210 | 0.4610 | 0.6789 |
|
| 148 |
+
| No log | 1.8131 | 194 | 0.4881 | 0.5564 | 0.4881 | 0.6986 |
|
| 149 |
+
| No log | 1.8318 | 196 | 0.5238 | 0.5738 | 0.5238 | 0.7238 |
|
| 150 |
+
| No log | 1.8505 | 198 | 0.5021 | 0.5872 | 0.5021 | 0.7086 |
|
| 151 |
+
| No log | 1.8692 | 200 | 0.4610 | 0.5851 | 0.4610 | 0.6790 |
|
| 152 |
+
| No log | 1.8879 | 202 | 0.5161 | 0.5477 | 0.5161 | 0.7184 |
|
| 153 |
+
| No log | 1.9065 | 204 | 0.4841 | 0.5699 | 0.4841 | 0.6958 |
|
| 154 |
+
| No log | 1.9252 | 206 | 0.4415 | 0.6101 | 0.4415 | 0.6644 |
|
| 155 |
+
| No log | 1.9439 | 208 | 0.5044 | 0.5768 | 0.5044 | 0.7102 |
|
| 156 |
+
| No log | 1.9626 | 210 | 0.5646 | 0.5234 | 0.5646 | 0.7514 |
|
| 157 |
+
| No log | 1.9813 | 212 | 0.5393 | 0.5046 | 0.5393 | 0.7344 |
|
| 158 |
+
| No log | 2.0 | 214 | 0.4874 | 0.4772 | 0.4874 | 0.6982 |
|
| 159 |
+
| No log | 2.0187 | 216 | 0.4948 | 0.4653 | 0.4948 | 0.7034 |
|
| 160 |
+
| No log | 2.0374 | 218 | 0.5073 | 0.4489 | 0.5073 | 0.7122 |
|
| 161 |
+
| No log | 2.0561 | 220 | 0.5328 | 0.3936 | 0.5328 | 0.7299 |
|
| 162 |
+
| No log | 2.0748 | 222 | 0.5639 | 0.3794 | 0.5639 | 0.7509 |
|
| 163 |
+
| No log | 2.0935 | 224 | 0.5730 | 0.3673 | 0.5730 | 0.7570 |
|
| 164 |
+
| No log | 2.1121 | 226 | 0.5888 | 0.3276 | 0.5888 | 0.7673 |
|
| 165 |
+
| No log | 2.1308 | 228 | 0.5698 | 0.3870 | 0.5698 | 0.7548 |
|
| 166 |
+
| No log | 2.1495 | 230 | 0.5221 | 0.4694 | 0.5221 | 0.7226 |
|
| 167 |
+
| No log | 2.1682 | 232 | 0.4869 | 0.5875 | 0.4869 | 0.6978 |
|
| 168 |
+
| No log | 2.1869 | 234 | 0.4779 | 0.6017 | 0.4779 | 0.6913 |
|
| 169 |
+
| No log | 2.2056 | 236 | 0.4587 | 0.6373 | 0.4587 | 0.6773 |
|
| 170 |
+
| No log | 2.2243 | 238 | 0.4770 | 0.6463 | 0.4770 | 0.6906 |
|
| 171 |
+
| No log | 2.2430 | 240 | 0.5380 | 0.5828 | 0.5380 | 0.7335 |
|
| 172 |
+
| No log | 2.2617 | 242 | 0.5793 | 0.5720 | 0.5793 | 0.7611 |
|
| 173 |
+
| No log | 2.2804 | 244 | 0.5067 | 0.5982 | 0.5067 | 0.7118 |
|
| 174 |
+
| No log | 2.2991 | 246 | 0.4665 | 0.5676 | 0.4665 | 0.6830 |
|
| 175 |
+
| No log | 2.3178 | 248 | 0.4592 | 0.5578 | 0.4592 | 0.6777 |
|
| 176 |
+
| No log | 2.3364 | 250 | 0.4638 | 0.5404 | 0.4638 | 0.6810 |
|
| 177 |
+
| No log | 2.3551 | 252 | 0.5172 | 0.5472 | 0.5172 | 0.7191 |
|
| 178 |
+
| No log | 2.3738 | 254 | 0.6020 | 0.4921 | 0.6020 | 0.7759 |
|
| 179 |
+
| No log | 2.3925 | 256 | 0.6448 | 0.4939 | 0.6448 | 0.8030 |
|
| 180 |
+
| No log | 2.4112 | 258 | 0.5623 | 0.5591 | 0.5623 | 0.7499 |
|
| 181 |
+
| No log | 2.4299 | 260 | 0.4486 | 0.6020 | 0.4486 | 0.6698 |
|
| 182 |
+
| No log | 2.4486 | 262 | 0.4297 | 0.5698 | 0.4297 | 0.6555 |
|
| 183 |
+
| No log | 2.4673 | 264 | 0.4221 | 0.6116 | 0.4221 | 0.6497 |
|
| 184 |
+
| No log | 2.4860 | 266 | 0.4321 | 0.6420 | 0.4321 | 0.6573 |
|
| 185 |
+
| No log | 2.5047 | 268 | 0.5164 | 0.6357 | 0.5164 | 0.7186 |
|
| 186 |
+
| No log | 2.5234 | 270 | 0.5749 | 0.5900 | 0.5749 | 0.7582 |
|
| 187 |
+
| No log | 2.5421 | 272 | 0.4987 | 0.6262 | 0.4987 | 0.7062 |
|
| 188 |
+
| No log | 2.5607 | 274 | 0.4699 | 0.6288 | 0.4699 | 0.6855 |
|
| 189 |
+
| No log | 2.5794 | 276 | 0.5253 | 0.6040 | 0.5253 | 0.7248 |
|
| 190 |
+
| No log | 2.5981 | 278 | 0.5125 | 0.5980 | 0.5125 | 0.7159 |
|
| 191 |
+
| No log | 2.6168 | 280 | 0.4667 | 0.6513 | 0.4667 | 0.6832 |
|
| 192 |
+
| No log | 2.6355 | 282 | 0.4391 | 0.6185 | 0.4391 | 0.6627 |
|
| 193 |
+
| No log | 2.6542 | 284 | 0.4485 | 0.6706 | 0.4485 | 0.6697 |
|
| 194 |
+
| No log | 2.6729 | 286 | 0.5413 | 0.6169 | 0.5413 | 0.7358 |
|
| 195 |
+
| No log | 2.6916 | 288 | 0.7172 | 0.5152 | 0.7172 | 0.8469 |
|
| 196 |
+
| No log | 2.7103 | 290 | 0.7016 | 0.5329 | 0.7016 | 0.8376 |
|
| 197 |
+
| No log | 2.7290 | 292 | 0.5335 | 0.6034 | 0.5335 | 0.7304 |
|
| 198 |
+
| No log | 2.7477 | 294 | 0.4575 | 0.6415 | 0.4575 | 0.6764 |
|
| 199 |
+
| No log | 2.7664 | 296 | 0.4277 | 0.6038 | 0.4277 | 0.6540 |
|
| 200 |
+
| No log | 2.7850 | 298 | 0.4262 | 0.6193 | 0.4262 | 0.6528 |
|
| 201 |
+
| No log | 2.8037 | 300 | 0.4214 | 0.6108 | 0.4214 | 0.6492 |
|
| 202 |
+
| No log | 2.8224 | 302 | 0.4229 | 0.6507 | 0.4229 | 0.6503 |
|
| 203 |
+
| No log | 2.8411 | 304 | 0.4155 | 0.6093 | 0.4155 | 0.6446 |
|
| 204 |
+
| No log | 2.8598 | 306 | 0.4679 | 0.6349 | 0.4679 | 0.6840 |
|
| 205 |
+
| No log | 2.8785 | 308 | 0.4657 | 0.6356 | 0.4657 | 0.6824 |
|
| 206 |
+
| No log | 2.8972 | 310 | 0.4787 | 0.6208 | 0.4787 | 0.6919 |
|
| 207 |
+
| No log | 2.9159 | 312 | 0.5411 | 0.6151 | 0.5411 | 0.7356 |
|
| 208 |
+
| No log | 2.9346 | 314 | 0.4876 | 0.6108 | 0.4876 | 0.6983 |
|
| 209 |
+
| No log | 2.9533 | 316 | 0.4206 | 0.6204 | 0.4206 | 0.6485 |
|
| 210 |
+
| No log | 2.9720 | 318 | 0.4224 | 0.6200 | 0.4224 | 0.6499 |
|
| 211 |
+
| No log | 2.9907 | 320 | 0.4367 | 0.6026 | 0.4367 | 0.6608 |
|
| 212 |
+
| No log | 3.0093 | 322 | 0.5085 | 0.5390 | 0.5085 | 0.7131 |
|
| 213 |
+
| No log | 3.0280 | 324 | 0.5996 | 0.5456 | 0.5996 | 0.7743 |
|
| 214 |
+
| No log | 3.0467 | 326 | 0.5840 | 0.5655 | 0.5840 | 0.7642 |
|
| 215 |
+
| No log | 3.0654 | 328 | 0.5168 | 0.6144 | 0.5168 | 0.7189 |
|
| 216 |
+
| No log | 3.0841 | 330 | 0.4641 | 0.6322 | 0.4641 | 0.6813 |
|
| 217 |
+
| No log | 3.1028 | 332 | 0.4594 | 0.6770 | 0.4594 | 0.6778 |
|
| 218 |
+
| No log | 3.1215 | 334 | 0.4794 | 0.6916 | 0.4794 | 0.6924 |
|
| 219 |
+
| No log | 3.1402 | 336 | 0.5288 | 0.6577 | 0.5288 | 0.7272 |
|
| 220 |
+
| No log | 3.1589 | 338 | 0.5831 | 0.6389 | 0.5831 | 0.7636 |
|
| 221 |
+
| No log | 3.1776 | 340 | 0.5270 | 0.6524 | 0.5270 | 0.7260 |
|
| 222 |
+
| No log | 3.1963 | 342 | 0.4278 | 0.6609 | 0.4278 | 0.6541 |
|
| 223 |
+
| No log | 3.2150 | 344 | 0.4226 | 0.6493 | 0.4226 | 0.6501 |
|
| 224 |
+
| No log | 3.2336 | 346 | 0.4175 | 0.6672 | 0.4175 | 0.6461 |
|
| 225 |
+
| No log | 3.2523 | 348 | 0.4628 | 0.6565 | 0.4628 | 0.6803 |
|
| 226 |
+
| No log | 3.2710 | 350 | 0.4828 | 0.6549 | 0.4828 | 0.6948 |
|
| 227 |
+
| No log | 3.2897 | 352 | 0.4547 | 0.6548 | 0.4547 | 0.6743 |
|
| 228 |
+
| No log | 3.3084 | 354 | 0.4429 | 0.6153 | 0.4429 | 0.6655 |
|
| 229 |
+
| No log | 3.3271 | 356 | 0.4685 | 0.5639 | 0.4685 | 0.6845 |
|
| 230 |
+
| No log | 3.3458 | 358 | 0.4661 | 0.5507 | 0.4661 | 0.6827 |
|
| 231 |
+
| No log | 3.3645 | 360 | 0.4614 | 0.5829 | 0.4614 | 0.6792 |
|
| 232 |
+
| No log | 3.3832 | 362 | 0.4663 | 0.5402 | 0.4663 | 0.6829 |
|
| 233 |
+
| No log | 3.4019 | 364 | 0.4685 | 0.5632 | 0.4685 | 0.6844 |
|
| 234 |
+
| No log | 3.4206 | 366 | 0.4967 | 0.6130 | 0.4967 | 0.7048 |
|
| 235 |
+
| No log | 3.4393 | 368 | 0.5437 | 0.6385 | 0.5437 | 0.7373 |
|
| 236 |
+
| No log | 3.4579 | 370 | 0.6294 | 0.5986 | 0.6294 | 0.7934 |
|
| 237 |
+
| No log | 3.4766 | 372 | 0.6688 | 0.5647 | 0.6688 | 0.8178 |
|
| 238 |
+
| No log | 3.4953 | 374 | 0.5939 | 0.6051 | 0.5939 | 0.7706 |
|
| 239 |
+
| No log | 3.5140 | 376 | 0.5189 | 0.6785 | 0.5189 | 0.7204 |
|
| 240 |
+
| No log | 3.5327 | 378 | 0.4826 | 0.6946 | 0.4826 | 0.6947 |
|
| 241 |
+
| No log | 3.5514 | 380 | 0.5590 | 0.6266 | 0.5590 | 0.7476 |
|
| 242 |
+
| No log | 3.5701 | 382 | 0.6080 | 0.6000 | 0.6080 | 0.7797 |
|
| 243 |
+
| No log | 3.5888 | 384 | 0.4495 | 0.6764 | 0.4495 | 0.6705 |
|
| 244 |
+
| No log | 3.6075 | 386 | 0.4134 | 0.6896 | 0.4134 | 0.6430 |
|
| 245 |
+
| No log | 3.6262 | 388 | 0.4689 | 0.6340 | 0.4689 | 0.6847 |
|
| 246 |
+
| No log | 3.6449 | 390 | 0.4628 | 0.6472 | 0.4628 | 0.6803 |
|
| 247 |
+
| No log | 3.6636 | 392 | 0.4298 | 0.6543 | 0.4298 | 0.6556 |
|
| 248 |
+
| No log | 3.6822 | 394 | 0.4038 | 0.6282 | 0.4038 | 0.6355 |
|
| 249 |
+
| No log | 3.7009 | 396 | 0.4084 | 0.6316 | 0.4084 | 0.6390 |
|
| 250 |
+
| No log | 3.7196 | 398 | 0.4341 | 0.6564 | 0.4341 | 0.6589 |
|
| 251 |
+
| No log | 3.7383 | 400 | 0.4665 | 0.6413 | 0.4665 | 0.6830 |
|
| 252 |
+
| No log | 3.7570 | 402 | 0.5091 | 0.6188 | 0.5091 | 0.7135 |
|
| 253 |
+
| No log | 3.7757 | 404 | 0.5099 | 0.6542 | 0.5099 | 0.7141 |
|
| 254 |
+
| No log | 3.7944 | 406 | 0.5958 | 0.6279 | 0.5958 | 0.7719 |
|
| 255 |
+
| No log | 3.8131 | 408 | 0.6455 | 0.6095 | 0.6455 | 0.8034 |
|
| 256 |
+
| No log | 3.8318 | 410 | 0.5262 | 0.6232 | 0.5262 | 0.7254 |
|
| 257 |
+
| No log | 3.8505 | 412 | 0.4311 | 0.6495 | 0.4311 | 0.6566 |
|
| 258 |
+
| No log | 3.8692 | 414 | 0.4412 | 0.6336 | 0.4412 | 0.6642 |
|
| 259 |
+
| No log | 3.8879 | 416 | 0.4283 | 0.6049 | 0.4283 | 0.6544 |
|
| 260 |
+
| No log | 3.9065 | 418 | 0.4452 | 0.5769 | 0.4452 | 0.6672 |
|
| 261 |
+
| No log | 3.9252 | 420 | 0.4954 | 0.5872 | 0.4954 | 0.7039 |
|
| 262 |
+
| No log | 3.9439 | 422 | 0.5485 | 0.5954 | 0.5485 | 0.7406 |
|
| 263 |
+
| No log | 3.9626 | 424 | 0.5847 | 0.6058 | 0.5847 | 0.7646 |
|
| 264 |
+
| No log | 3.9813 | 426 | 0.4560 | 0.6836 | 0.4560 | 0.6753 |
|
| 265 |
+
| No log | 4.0 | 428 | 0.4409 | 0.6695 | 0.4409 | 0.6640 |
|
| 266 |
+
| No log | 4.0187 | 430 | 0.5017 | 0.6337 | 0.5017 | 0.7083 |
|
| 267 |
+
| No log | 4.0374 | 432 | 0.5970 | 0.6133 | 0.5970 | 0.7726 |
|
| 268 |
+
| No log | 4.0561 | 434 | 0.6838 | 0.5644 | 0.6838 | 0.8269 |
|
| 269 |
+
| No log | 4.0748 | 436 | 0.6351 | 0.5812 | 0.6351 | 0.7969 |
|
| 270 |
+
| No log | 4.0935 | 438 | 0.4993 | 0.6536 | 0.4993 | 0.7066 |
|
| 271 |
+
| No log | 4.1121 | 440 | 0.4587 | 0.6345 | 0.4587 | 0.6773 |
|
| 272 |
+
| No log | 4.1308 | 442 | 0.4994 | 0.6431 | 0.4994 | 0.7067 |
|
| 273 |
+
| No log | 4.1495 | 444 | 0.6705 | 0.6142 | 0.6705 | 0.8188 |
|
| 274 |
+
| No log | 4.1682 | 446 | 0.7197 | 0.6162 | 0.7197 | 0.8484 |
|
| 275 |
+
| No log | 4.1869 | 448 | 0.5529 | 0.6450 | 0.5529 | 0.7435 |
|
| 276 |
+
| No log | 4.2056 | 450 | 0.4448 | 0.6703 | 0.4448 | 0.6669 |
|
| 277 |
+
| No log | 4.2243 | 452 | 0.4174 | 0.6355 | 0.4174 | 0.6461 |
|
| 278 |
+
| No log | 4.2430 | 454 | 0.4297 | 0.6438 | 0.4297 | 0.6555 |
|
| 279 |
+
| No log | 4.2617 | 456 | 0.5314 | 0.6442 | 0.5314 | 0.7290 |
|
| 280 |
+
| No log | 4.2804 | 458 | 0.5980 | 0.5995 | 0.5980 | 0.7733 |
|
| 281 |
+
| No log | 4.2991 | 460 | 0.5239 | 0.6088 | 0.5239 | 0.7238 |
|
| 282 |
+
| No log | 4.3178 | 462 | 0.4698 | 0.6219 | 0.4698 | 0.6854 |
|
| 283 |
+
| No log | 4.3364 | 464 | 0.4848 | 0.6170 | 0.4848 | 0.6963 |
|
| 284 |
+
| No log | 4.3551 | 466 | 0.4880 | 0.5750 | 0.4880 | 0.6986 |
|
| 285 |
+
| No log | 4.3738 | 468 | 0.5079 | 0.6204 | 0.5079 | 0.7127 |
|
| 286 |
+
| No log | 4.3925 | 470 | 0.5434 | 0.5999 | 0.5434 | 0.7371 |
|
| 287 |
+
| No log | 4.4112 | 472 | 0.4981 | 0.6239 | 0.4981 | 0.7058 |
|
| 288 |
+
| No log | 4.4299 | 474 | 0.4921 | 0.6309 | 0.4921 | 0.7015 |
|
| 289 |
+
| No log | 4.4486 | 476 | 0.4660 | 0.6424 | 0.4660 | 0.6826 |
|
| 290 |
+
| No log | 4.4673 | 478 | 0.4366 | 0.6050 | 0.4366 | 0.6607 |
|
| 291 |
+
| No log | 4.4860 | 480 | 0.4717 | 0.6322 | 0.4717 | 0.6868 |
|
| 292 |
+
| No log | 4.5047 | 482 | 0.5668 | 0.6115 | 0.5668 | 0.7529 |
|
| 293 |
+
| No log | 4.5234 | 484 | 0.5440 | 0.6297 | 0.5440 | 0.7376 |
|
| 294 |
+
| No log | 4.5421 | 486 | 0.4823 | 0.5895 | 0.4823 | 0.6945 |
|
| 295 |
+
| No log | 4.5607 | 488 | 0.4709 | 0.6113 | 0.4709 | 0.6862 |
|
| 296 |
+
| No log | 4.5794 | 490 | 0.4921 | 0.6169 | 0.4921 | 0.7015 |
|
| 297 |
+
| No log | 4.5981 | 492 | 0.5569 | 0.6156 | 0.5569 | 0.7462 |
|
| 298 |
+
| No log | 4.6168 | 494 | 0.5460 | 0.6325 | 0.5460 | 0.7389 |
|
| 299 |
+
| No log | 4.6355 | 496 | 0.5375 | 0.6419 | 0.5375 | 0.7332 |
|
| 300 |
+
| No log | 4.6542 | 498 | 0.4752 | 0.6239 | 0.4752 | 0.6893 |
|
| 301 |
+
| 0.5152 | 4.6729 | 500 | 0.4713 | 0.6180 | 0.4713 | 0.6865 |
|
| 302 |
+
| 0.5152 | 4.6916 | 502 | 0.5551 | 0.6099 | 0.5551 | 0.7450 |
|
| 303 |
+
| 0.5152 | 4.7103 | 504 | 0.6524 | 0.6019 | 0.6524 | 0.8077 |
|
| 304 |
+
| 0.5152 | 4.7290 | 506 | 0.5678 | 0.6216 | 0.5678 | 0.7535 |
|
| 305 |
+
| 0.5152 | 4.7477 | 508 | 0.4535 | 0.6230 | 0.4535 | 0.6734 |
|
| 306 |
+
| 0.5152 | 4.7664 | 510 | 0.4542 | 0.6517 | 0.4542 | 0.6739 |
|
| 307 |
+
| 0.5152 | 4.7850 | 512 | 0.5111 | 0.6368 | 0.5111 | 0.7149 |
|
| 308 |
+
| 0.5152 | 4.8037 | 514 | 0.4801 | 0.6459 | 0.4801 | 0.6929 |
|
| 309 |
+
| 0.5152 | 4.8224 | 516 | 0.4818 | 0.6476 | 0.4818 | 0.6941 |
|
| 310 |
+
| 0.5152 | 4.8411 | 518 | 0.5343 | 0.6469 | 0.5343 | 0.7309 |
|
| 311 |
+
| 0.5152 | 4.8598 | 520 | 0.4977 | 0.6306 | 0.4977 | 0.7055 |
|
| 312 |
+
| 0.5152 | 4.8785 | 522 | 0.5100 | 0.6358 | 0.5100 | 0.7141 |
|
| 313 |
+
| 0.5152 | 4.8972 | 524 | 0.6145 | 0.6005 | 0.6145 | 0.7839 |
|
| 314 |
+
| 0.5152 | 4.9159 | 526 | 0.6761 | 0.5857 | 0.6761 | 0.8222 |
|
| 315 |
+
| 0.5152 | 4.9346 | 528 | 0.5247 | 0.6878 | 0.5247 | 0.7243 |
|
| 316 |
+
| 0.5152 | 4.9533 | 530 | 0.4911 | 0.6990 | 0.4911 | 0.7008 |
|
| 317 |
+
| 0.5152 | 4.9720 | 532 | 0.4745 | 0.6669 | 0.4745 | 0.6888 |
|
| 318 |
+
| 0.5152 | 4.9907 | 534 | 0.4599 | 0.6855 | 0.4599 | 0.6781 |
|
| 319 |
+
| 0.5152 | 5.0093 | 536 | 0.6473 | 0.6019 | 0.6473 | 0.8046 |
|
| 320 |
+
| 0.5152 | 5.0280 | 538 | 0.7257 | 0.5849 | 0.7257 | 0.8519 |
|
| 321 |
+
| 0.5152 | 5.0467 | 540 | 0.5479 | 0.6201 | 0.5479 | 0.7402 |
|
| 322 |
+
| 0.5152 | 5.0654 | 542 | 0.4119 | 0.6353 | 0.4119 | 0.6418 |
|
| 323 |
+
| 0.5152 | 5.0841 | 544 | 0.4255 | 0.6308 | 0.4255 | 0.6523 |
|
| 324 |
+
| 0.5152 | 5.1028 | 546 | 0.4255 | 0.6243 | 0.4255 | 0.6523 |
|
| 325 |
+
| 0.5152 | 5.1215 | 548 | 0.4230 | 0.6337 | 0.4230 | 0.6504 |
|
| 326 |
+
| 0.5152 | 5.1402 | 550 | 0.4778 | 0.6636 | 0.4778 | 0.6912 |
|
| 327 |
+
| 0.5152 | 5.1589 | 552 | 0.5074 | 0.6614 | 0.5074 | 0.7123 |
|
| 328 |
+
| 0.5152 | 5.1776 | 554 | 0.5727 | 0.6121 | 0.5727 | 0.7568 |
|
| 329 |
+
| 0.5152 | 5.1963 | 556 | 0.6526 | 0.5814 | 0.6526 | 0.8078 |
|
| 330 |
+
| 0.5152 | 5.2150 | 558 | 0.6055 | 0.6377 | 0.6055 | 0.7781 |
|
| 331 |
+
| 0.5152 | 5.2336 | 560 | 0.6056 | 0.6369 | 0.6056 | 0.7782 |
|
| 332 |
+
| 0.5152 | 5.2523 | 562 | 0.7271 | 0.6123 | 0.7271 | 0.8527 |
|
| 333 |
+
| 0.5152 | 5.2710 | 564 | 0.7510 | 0.5707 | 0.7510 | 0.8666 |
|
| 334 |
+
| 0.5152 | 5.2897 | 566 | 0.6316 | 0.5895 | 0.6316 | 0.7947 |
|
| 335 |
+
| 0.5152 | 5.3084 | 568 | 0.4594 | 0.6470 | 0.4594 | 0.6778 |
|
| 336 |
+
| 0.5152 | 5.3271 | 570 | 0.4248 | 0.6600 | 0.4248 | 0.6518 |
|
| 337 |
+
| 0.5152 | 5.3458 | 572 | 0.4238 | 0.6409 | 0.4238 | 0.6510 |
|
| 338 |
+
| 0.5152 | 5.3645 | 574 | 0.4787 | 0.6259 | 0.4787 | 0.6919 |
|
| 339 |
+
| 0.5152 | 5.3832 | 576 | 0.5882 | 0.5796 | 0.5882 | 0.7669 |
|
| 340 |
+
| 0.5152 | 5.4019 | 578 | 0.5628 | 0.5983 | 0.5628 | 0.7502 |
|
| 341 |
+
| 0.5152 | 5.4206 | 580 | 0.4385 | 0.6573 | 0.4385 | 0.6622 |
|
| 342 |
+
| 0.5152 | 5.4393 | 582 | 0.4253 | 0.6364 | 0.4253 | 0.6521 |
|
| 343 |
+
| 0.5152 | 5.4579 | 584 | 0.4358 | 0.6150 | 0.4358 | 0.6602 |
|
| 344 |
+
| 0.5152 | 5.4766 | 586 | 0.4464 | 0.6277 | 0.4464 | 0.6682 |
|
| 345 |
+
| 0.5152 | 5.4953 | 588 | 0.4953 | 0.6450 | 0.4953 | 0.7037 |
|
| 346 |
+
| 0.5152 | 5.5140 | 590 | 0.6014 | 0.6147 | 0.6014 | 0.7755 |
|
| 347 |
+
| 0.5152 | 5.5327 | 592 | 0.6139 | 0.6052 | 0.6139 | 0.7835 |
|
| 348 |
+
| 0.5152 | 5.5514 | 594 | 0.5179 | 0.6410 | 0.5179 | 0.7196 |
|
| 349 |
+
| 0.5152 | 5.5701 | 596 | 0.4847 | 0.6447 | 0.4847 | 0.6962 |
|
| 350 |
+
| 0.5152 | 5.5888 | 598 | 0.5227 | 0.6324 | 0.5227 | 0.7230 |
|
| 351 |
+
| 0.5152 | 5.6075 | 600 | 0.6672 | 0.5594 | 0.6672 | 0.8168 |
|
| 352 |
+
| 0.5152 | 5.6262 | 602 | 0.6386 | 0.5335 | 0.6386 | 0.7991 |
|
| 353 |
+
| 0.5152 | 5.6449 | 604 | 0.5325 | 0.5382 | 0.5325 | 0.7297 |
|
| 354 |
+
| 0.5152 | 5.6636 | 606 | 0.5288 | 0.5100 | 0.5288 | 0.7272 |
|
| 355 |
+
| 0.5152 | 5.6822 | 608 | 0.4946 | 0.5245 | 0.4946 | 0.7033 |
|
| 356 |
+
|
| 357 |
+
|
| 358 |
+
### Framework versions
|
| 359 |
+
|
| 360 |
+
- Transformers 4.44.2
|
| 361 |
+
- Pytorch 2.4.0+cu118
|
| 362 |
+
- Datasets 2.21.0
|
| 363 |
+
- 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:d5bdb8eb1118ea501fd96d85fb76f576648160842321fb38dec01d5948590682
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3143b3d0fcaee9433ff9ce009139087d22ab8e250d782ec19c6a5b1557a0f267
|
| 3 |
+
size 5240
|