Training in progress, step 500
Browse files- README.md +314 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k1_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_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k1_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: 0.4065
|
| 19 |
+
- Qwk: 0.5784
|
| 20 |
+
- Mse: 0.4065
|
| 21 |
+
- Rmse: 0.6375
|
| 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 | 0.3333 | 2 | 2.5382 | 0.0052 | 2.5382 | 1.5932 |
|
| 53 |
+
| No log | 0.6667 | 4 | 1.1671 | 0.0992 | 1.1671 | 1.0803 |
|
| 54 |
+
| No log | 1.0 | 6 | 0.7084 | 0.0937 | 0.7084 | 0.8417 |
|
| 55 |
+
| No log | 1.3333 | 8 | 0.7375 | 0.3069 | 0.7375 | 0.8588 |
|
| 56 |
+
| No log | 1.6667 | 10 | 0.6419 | 0.4294 | 0.6419 | 0.8012 |
|
| 57 |
+
| No log | 2.0 | 12 | 0.7532 | 0.4044 | 0.7532 | 0.8679 |
|
| 58 |
+
| No log | 2.3333 | 14 | 0.6105 | 0.4153 | 0.6105 | 0.7814 |
|
| 59 |
+
| No log | 2.6667 | 16 | 0.5692 | 0.5173 | 0.5692 | 0.7544 |
|
| 60 |
+
| No log | 3.0 | 18 | 0.5407 | 0.5033 | 0.5407 | 0.7353 |
|
| 61 |
+
| No log | 3.3333 | 20 | 0.7809 | 0.4738 | 0.7809 | 0.8837 |
|
| 62 |
+
| No log | 3.6667 | 22 | 0.4801 | 0.6439 | 0.4801 | 0.6929 |
|
| 63 |
+
| No log | 4.0 | 24 | 0.6111 | 0.6400 | 0.6111 | 0.7817 |
|
| 64 |
+
| No log | 4.3333 | 26 | 0.5689 | 0.5906 | 0.5689 | 0.7542 |
|
| 65 |
+
| No log | 4.6667 | 28 | 0.4165 | 0.6053 | 0.4165 | 0.6454 |
|
| 66 |
+
| No log | 5.0 | 30 | 0.9044 | 0.3921 | 0.9044 | 0.9510 |
|
| 67 |
+
| No log | 5.3333 | 32 | 1.1691 | 0.1913 | 1.1691 | 1.0812 |
|
| 68 |
+
| No log | 5.6667 | 34 | 0.8068 | 0.4667 | 0.8068 | 0.8982 |
|
| 69 |
+
| No log | 6.0 | 36 | 0.4732 | 0.5321 | 0.4732 | 0.6879 |
|
| 70 |
+
| No log | 6.3333 | 38 | 0.4774 | 0.6289 | 0.4774 | 0.6909 |
|
| 71 |
+
| No log | 6.6667 | 40 | 0.4750 | 0.5786 | 0.4750 | 0.6892 |
|
| 72 |
+
| No log | 7.0 | 42 | 0.4629 | 0.5786 | 0.4629 | 0.6804 |
|
| 73 |
+
| No log | 7.3333 | 44 | 0.4136 | 0.5995 | 0.4136 | 0.6431 |
|
| 74 |
+
| No log | 7.6667 | 46 | 0.4132 | 0.5861 | 0.4132 | 0.6428 |
|
| 75 |
+
| No log | 8.0 | 48 | 0.4049 | 0.6690 | 0.4049 | 0.6363 |
|
| 76 |
+
| No log | 8.3333 | 50 | 0.4130 | 0.5816 | 0.4130 | 0.6426 |
|
| 77 |
+
| No log | 8.6667 | 52 | 0.4385 | 0.6018 | 0.4385 | 0.6622 |
|
| 78 |
+
| No log | 9.0 | 54 | 0.4105 | 0.6383 | 0.4105 | 0.6407 |
|
| 79 |
+
| No log | 9.3333 | 56 | 0.5326 | 0.6390 | 0.5326 | 0.7298 |
|
| 80 |
+
| No log | 9.6667 | 58 | 0.6001 | 0.5515 | 0.6001 | 0.7747 |
|
| 81 |
+
| No log | 10.0 | 60 | 0.4318 | 0.7062 | 0.4318 | 0.6572 |
|
| 82 |
+
| No log | 10.3333 | 62 | 0.5254 | 0.6142 | 0.5254 | 0.7248 |
|
| 83 |
+
| No log | 10.6667 | 64 | 0.5300 | 0.6156 | 0.5300 | 0.7280 |
|
| 84 |
+
| No log | 11.0 | 66 | 0.4178 | 0.5677 | 0.4178 | 0.6464 |
|
| 85 |
+
| No log | 11.3333 | 68 | 0.4611 | 0.6337 | 0.4611 | 0.6790 |
|
| 86 |
+
| No log | 11.6667 | 70 | 0.4911 | 0.5979 | 0.4911 | 0.7008 |
|
| 87 |
+
| No log | 12.0 | 72 | 0.4394 | 0.5913 | 0.4394 | 0.6628 |
|
| 88 |
+
| No log | 12.3333 | 74 | 0.4617 | 0.5859 | 0.4617 | 0.6795 |
|
| 89 |
+
| No log | 12.6667 | 76 | 0.6169 | 0.6469 | 0.6169 | 0.7854 |
|
| 90 |
+
| No log | 13.0 | 78 | 0.6114 | 0.6288 | 0.6114 | 0.7819 |
|
| 91 |
+
| No log | 13.3333 | 80 | 0.4965 | 0.5601 | 0.4965 | 0.7046 |
|
| 92 |
+
| No log | 13.6667 | 82 | 0.5274 | 0.5744 | 0.5274 | 0.7262 |
|
| 93 |
+
| No log | 14.0 | 84 | 0.4627 | 0.5071 | 0.4627 | 0.6802 |
|
| 94 |
+
| No log | 14.3333 | 86 | 0.4272 | 0.5625 | 0.4272 | 0.6536 |
|
| 95 |
+
| No log | 14.6667 | 88 | 0.4551 | 0.6419 | 0.4551 | 0.6746 |
|
| 96 |
+
| No log | 15.0 | 90 | 0.5220 | 0.6194 | 0.5220 | 0.7225 |
|
| 97 |
+
| No log | 15.3333 | 92 | 0.4509 | 0.6709 | 0.4509 | 0.6715 |
|
| 98 |
+
| No log | 15.6667 | 94 | 0.4131 | 0.6105 | 0.4131 | 0.6427 |
|
| 99 |
+
| No log | 16.0 | 96 | 0.4292 | 0.5874 | 0.4292 | 0.6551 |
|
| 100 |
+
| No log | 16.3333 | 98 | 0.4371 | 0.5846 | 0.4371 | 0.6611 |
|
| 101 |
+
| No log | 16.6667 | 100 | 0.4494 | 0.5951 | 0.4494 | 0.6704 |
|
| 102 |
+
| No log | 17.0 | 102 | 0.5094 | 0.5726 | 0.5094 | 0.7137 |
|
| 103 |
+
| No log | 17.3333 | 104 | 0.5796 | 0.5259 | 0.5796 | 0.7613 |
|
| 104 |
+
| No log | 17.6667 | 106 | 0.5061 | 0.5395 | 0.5061 | 0.7114 |
|
| 105 |
+
| No log | 18.0 | 108 | 0.4799 | 0.5289 | 0.4799 | 0.6928 |
|
| 106 |
+
| No log | 18.3333 | 110 | 0.4567 | 0.5472 | 0.4567 | 0.6758 |
|
| 107 |
+
| No log | 18.6667 | 112 | 0.4590 | 0.6269 | 0.4590 | 0.6775 |
|
| 108 |
+
| No log | 19.0 | 114 | 0.4654 | 0.6269 | 0.4654 | 0.6822 |
|
| 109 |
+
| No log | 19.3333 | 116 | 0.4757 | 0.5703 | 0.4757 | 0.6897 |
|
| 110 |
+
| No log | 19.6667 | 118 | 0.4751 | 0.5488 | 0.4751 | 0.6893 |
|
| 111 |
+
| No log | 20.0 | 120 | 0.4665 | 0.5846 | 0.4665 | 0.6830 |
|
| 112 |
+
| No log | 20.3333 | 122 | 0.4509 | 0.5846 | 0.4509 | 0.6715 |
|
| 113 |
+
| No log | 20.6667 | 124 | 0.4509 | 0.5784 | 0.4509 | 0.6715 |
|
| 114 |
+
| No log | 21.0 | 126 | 0.5736 | 0.5659 | 0.5736 | 0.7573 |
|
| 115 |
+
| No log | 21.3333 | 128 | 0.6350 | 0.5249 | 0.6350 | 0.7969 |
|
| 116 |
+
| No log | 21.6667 | 130 | 0.5587 | 0.5659 | 0.5587 | 0.7474 |
|
| 117 |
+
| No log | 22.0 | 132 | 0.4702 | 0.5947 | 0.4702 | 0.6857 |
|
| 118 |
+
| No log | 22.3333 | 134 | 0.4800 | 0.5923 | 0.4800 | 0.6928 |
|
| 119 |
+
| No log | 22.6667 | 136 | 0.5632 | 0.5931 | 0.5632 | 0.7504 |
|
| 120 |
+
| No log | 23.0 | 138 | 0.7313 | 0.5564 | 0.7313 | 0.8551 |
|
| 121 |
+
| No log | 23.3333 | 140 | 0.7557 | 0.5240 | 0.7557 | 0.8693 |
|
| 122 |
+
| No log | 23.6667 | 142 | 0.5599 | 0.5845 | 0.5599 | 0.7483 |
|
| 123 |
+
| No log | 24.0 | 144 | 0.4447 | 0.5899 | 0.4447 | 0.6668 |
|
| 124 |
+
| No log | 24.3333 | 146 | 0.4635 | 0.5028 | 0.4635 | 0.6808 |
|
| 125 |
+
| No log | 24.6667 | 148 | 0.4390 | 0.5765 | 0.4390 | 0.6625 |
|
| 126 |
+
| No log | 25.0 | 150 | 0.4492 | 0.5912 | 0.4492 | 0.6702 |
|
| 127 |
+
| No log | 25.3333 | 152 | 0.5442 | 0.5744 | 0.5442 | 0.7377 |
|
| 128 |
+
| No log | 25.6667 | 154 | 0.5253 | 0.5966 | 0.5253 | 0.7247 |
|
| 129 |
+
| No log | 26.0 | 156 | 0.4452 | 0.6032 | 0.4452 | 0.6673 |
|
| 130 |
+
| No log | 26.3333 | 158 | 0.4382 | 0.6402 | 0.4382 | 0.6619 |
|
| 131 |
+
| No log | 26.6667 | 160 | 0.4466 | 0.6317 | 0.4466 | 0.6683 |
|
| 132 |
+
| No log | 27.0 | 162 | 0.4184 | 0.6228 | 0.4184 | 0.6469 |
|
| 133 |
+
| No log | 27.3333 | 164 | 0.4661 | 0.5123 | 0.4661 | 0.6827 |
|
| 134 |
+
| No log | 27.6667 | 166 | 0.5321 | 0.5661 | 0.5321 | 0.7294 |
|
| 135 |
+
| No log | 28.0 | 168 | 0.4753 | 0.5345 | 0.4753 | 0.6894 |
|
| 136 |
+
| No log | 28.3333 | 170 | 0.4136 | 0.5784 | 0.4136 | 0.6431 |
|
| 137 |
+
| No log | 28.6667 | 172 | 0.4050 | 0.6228 | 0.4050 | 0.6364 |
|
| 138 |
+
| No log | 29.0 | 174 | 0.4098 | 0.6228 | 0.4098 | 0.6402 |
|
| 139 |
+
| No log | 29.3333 | 176 | 0.4132 | 0.6228 | 0.4132 | 0.6428 |
|
| 140 |
+
| No log | 29.6667 | 178 | 0.4171 | 0.5784 | 0.4171 | 0.6458 |
|
| 141 |
+
| No log | 30.0 | 180 | 0.4886 | 0.5468 | 0.4886 | 0.6990 |
|
| 142 |
+
| No log | 30.3333 | 182 | 0.5730 | 0.5758 | 0.5730 | 0.7569 |
|
| 143 |
+
| No log | 30.6667 | 184 | 0.5323 | 0.5773 | 0.5323 | 0.7296 |
|
| 144 |
+
| No log | 31.0 | 186 | 0.4464 | 0.5631 | 0.4464 | 0.6681 |
|
| 145 |
+
| No log | 31.3333 | 188 | 0.4269 | 0.6228 | 0.4269 | 0.6534 |
|
| 146 |
+
| No log | 31.6667 | 190 | 0.4278 | 0.6228 | 0.4278 | 0.6541 |
|
| 147 |
+
| No log | 32.0 | 192 | 0.4302 | 0.6228 | 0.4302 | 0.6559 |
|
| 148 |
+
| No log | 32.3333 | 194 | 0.4263 | 0.6010 | 0.4263 | 0.6529 |
|
| 149 |
+
| No log | 32.6667 | 196 | 0.4222 | 0.6010 | 0.4222 | 0.6497 |
|
| 150 |
+
| No log | 33.0 | 198 | 0.4264 | 0.6010 | 0.4264 | 0.6530 |
|
| 151 |
+
| No log | 33.3333 | 200 | 0.4243 | 0.6010 | 0.4243 | 0.6514 |
|
| 152 |
+
| No log | 33.6667 | 202 | 0.4225 | 0.6010 | 0.4225 | 0.6500 |
|
| 153 |
+
| No log | 34.0 | 204 | 0.4317 | 0.6214 | 0.4317 | 0.6571 |
|
| 154 |
+
| No log | 34.3333 | 206 | 0.4897 | 0.5677 | 0.4897 | 0.6998 |
|
| 155 |
+
| No log | 34.6667 | 208 | 0.4877 | 0.5712 | 0.4877 | 0.6984 |
|
| 156 |
+
| No log | 35.0 | 210 | 0.4605 | 0.5909 | 0.4605 | 0.6786 |
|
| 157 |
+
| No log | 35.3333 | 212 | 0.4415 | 0.5816 | 0.4415 | 0.6644 |
|
| 158 |
+
| No log | 35.6667 | 214 | 0.4333 | 0.5816 | 0.4333 | 0.6583 |
|
| 159 |
+
| No log | 36.0 | 216 | 0.4351 | 0.5784 | 0.4351 | 0.6596 |
|
| 160 |
+
| No log | 36.3333 | 218 | 0.4414 | 0.5868 | 0.4414 | 0.6643 |
|
| 161 |
+
| No log | 36.6667 | 220 | 0.4508 | 0.5631 | 0.4508 | 0.6714 |
|
| 162 |
+
| No log | 37.0 | 222 | 0.4909 | 0.6052 | 0.4909 | 0.7006 |
|
| 163 |
+
| No log | 37.3333 | 224 | 0.5603 | 0.5857 | 0.5603 | 0.7485 |
|
| 164 |
+
| No log | 37.6667 | 226 | 0.5428 | 0.5455 | 0.5428 | 0.7368 |
|
| 165 |
+
| No log | 38.0 | 228 | 0.4708 | 0.6067 | 0.4708 | 0.6861 |
|
| 166 |
+
| No log | 38.3333 | 230 | 0.4312 | 0.6010 | 0.4312 | 0.6567 |
|
| 167 |
+
| No log | 38.6667 | 232 | 0.4230 | 0.6142 | 0.4230 | 0.6504 |
|
| 168 |
+
| No log | 39.0 | 234 | 0.4198 | 0.6228 | 0.4198 | 0.6480 |
|
| 169 |
+
| No log | 39.3333 | 236 | 0.4389 | 0.5868 | 0.4389 | 0.6625 |
|
| 170 |
+
| No log | 39.6667 | 238 | 0.5088 | 0.5755 | 0.5088 | 0.7133 |
|
| 171 |
+
| No log | 40.0 | 240 | 0.5899 | 0.5631 | 0.5899 | 0.7681 |
|
| 172 |
+
| No log | 40.3333 | 242 | 0.6088 | 0.5949 | 0.6088 | 0.7803 |
|
| 173 |
+
| No log | 40.6667 | 244 | 0.5222 | 0.6464 | 0.5222 | 0.7226 |
|
| 174 |
+
| No log | 41.0 | 246 | 0.4613 | 0.6105 | 0.4613 | 0.6792 |
|
| 175 |
+
| No log | 41.3333 | 248 | 0.4327 | 0.5784 | 0.4327 | 0.6578 |
|
| 176 |
+
| No log | 41.6667 | 250 | 0.4316 | 0.5846 | 0.4316 | 0.6569 |
|
| 177 |
+
| No log | 42.0 | 252 | 0.4530 | 0.5479 | 0.4530 | 0.6731 |
|
| 178 |
+
| No log | 42.3333 | 254 | 0.4387 | 0.5846 | 0.4387 | 0.6624 |
|
| 179 |
+
| No log | 42.6667 | 256 | 0.4484 | 0.5784 | 0.4484 | 0.6696 |
|
| 180 |
+
| No log | 43.0 | 258 | 0.4786 | 0.5516 | 0.4786 | 0.6918 |
|
| 181 |
+
| No log | 43.3333 | 260 | 0.4720 | 0.5516 | 0.4720 | 0.6870 |
|
| 182 |
+
| No log | 43.6667 | 262 | 0.4504 | 0.6024 | 0.4504 | 0.6712 |
|
| 183 |
+
| No log | 44.0 | 264 | 0.4559 | 0.6317 | 0.4559 | 0.6752 |
|
| 184 |
+
| No log | 44.3333 | 266 | 0.4876 | 0.5516 | 0.4876 | 0.6983 |
|
| 185 |
+
| No log | 44.6667 | 268 | 0.5381 | 0.5237 | 0.5381 | 0.7336 |
|
| 186 |
+
| No log | 45.0 | 270 | 0.5154 | 0.5639 | 0.5154 | 0.7179 |
|
| 187 |
+
| No log | 45.3333 | 272 | 0.4834 | 0.5420 | 0.4834 | 0.6953 |
|
| 188 |
+
| No log | 45.6667 | 274 | 0.4673 | 0.5516 | 0.4673 | 0.6836 |
|
| 189 |
+
| No log | 46.0 | 276 | 0.4431 | 0.6096 | 0.4431 | 0.6657 |
|
| 190 |
+
| No log | 46.3333 | 278 | 0.4404 | 0.5868 | 0.4404 | 0.6636 |
|
| 191 |
+
| No log | 46.6667 | 280 | 0.4478 | 0.5386 | 0.4478 | 0.6691 |
|
| 192 |
+
| No log | 47.0 | 282 | 0.4742 | 0.5420 | 0.4742 | 0.6887 |
|
| 193 |
+
| No log | 47.3333 | 284 | 0.4640 | 0.5516 | 0.4640 | 0.6812 |
|
| 194 |
+
| No log | 47.6667 | 286 | 0.4379 | 0.5386 | 0.4379 | 0.6617 |
|
| 195 |
+
| No log | 48.0 | 288 | 0.4318 | 0.5765 | 0.4318 | 0.6571 |
|
| 196 |
+
| No log | 48.3333 | 290 | 0.4314 | 0.5986 | 0.4314 | 0.6568 |
|
| 197 |
+
| No log | 48.6667 | 292 | 0.4296 | 0.5631 | 0.4296 | 0.6554 |
|
| 198 |
+
| No log | 49.0 | 294 | 0.4543 | 0.5386 | 0.4543 | 0.6740 |
|
| 199 |
+
| No log | 49.3333 | 296 | 0.4762 | 0.5345 | 0.4762 | 0.6901 |
|
| 200 |
+
| No log | 49.6667 | 298 | 0.4684 | 0.5386 | 0.4684 | 0.6844 |
|
| 201 |
+
| No log | 50.0 | 300 | 0.4442 | 0.5386 | 0.4442 | 0.6665 |
|
| 202 |
+
| No log | 50.3333 | 302 | 0.4381 | 0.5386 | 0.4381 | 0.6619 |
|
| 203 |
+
| No log | 50.6667 | 304 | 0.4313 | 0.5631 | 0.4313 | 0.6567 |
|
| 204 |
+
| No log | 51.0 | 306 | 0.4378 | 0.5386 | 0.4378 | 0.6617 |
|
| 205 |
+
| No log | 51.3333 | 308 | 0.4512 | 0.5386 | 0.4512 | 0.6717 |
|
| 206 |
+
| No log | 51.6667 | 310 | 0.4655 | 0.5386 | 0.4655 | 0.6823 |
|
| 207 |
+
| No log | 52.0 | 312 | 0.4652 | 0.5386 | 0.4652 | 0.6821 |
|
| 208 |
+
| No log | 52.3333 | 314 | 0.4535 | 0.5386 | 0.4535 | 0.6734 |
|
| 209 |
+
| No log | 52.6667 | 316 | 0.4506 | 0.5386 | 0.4506 | 0.6713 |
|
| 210 |
+
| No log | 53.0 | 318 | 0.4604 | 0.5386 | 0.4604 | 0.6785 |
|
| 211 |
+
| No log | 53.3333 | 320 | 0.4623 | 0.5386 | 0.4623 | 0.6800 |
|
| 212 |
+
| No log | 53.6667 | 322 | 0.4512 | 0.5631 | 0.4512 | 0.6717 |
|
| 213 |
+
| No log | 54.0 | 324 | 0.4592 | 0.5631 | 0.4592 | 0.6777 |
|
| 214 |
+
| No log | 54.3333 | 326 | 0.4693 | 0.5631 | 0.4693 | 0.6850 |
|
| 215 |
+
| No log | 54.6667 | 328 | 0.4559 | 0.5631 | 0.4559 | 0.6752 |
|
| 216 |
+
| No log | 55.0 | 330 | 0.4390 | 0.5631 | 0.4390 | 0.6626 |
|
| 217 |
+
| No log | 55.3333 | 332 | 0.4377 | 0.5631 | 0.4377 | 0.6616 |
|
| 218 |
+
| No log | 55.6667 | 334 | 0.4528 | 0.5631 | 0.4528 | 0.6729 |
|
| 219 |
+
| No log | 56.0 | 336 | 0.4727 | 0.5289 | 0.4727 | 0.6875 |
|
| 220 |
+
| No log | 56.3333 | 338 | 0.4581 | 0.5631 | 0.4581 | 0.6768 |
|
| 221 |
+
| No log | 56.6667 | 340 | 0.4309 | 0.5732 | 0.4309 | 0.6564 |
|
| 222 |
+
| No log | 57.0 | 342 | 0.4188 | 0.5749 | 0.4188 | 0.6471 |
|
| 223 |
+
| No log | 57.3333 | 344 | 0.4174 | 0.6017 | 0.4174 | 0.6461 |
|
| 224 |
+
| No log | 57.6667 | 346 | 0.4088 | 0.5986 | 0.4088 | 0.6393 |
|
| 225 |
+
| No log | 58.0 | 348 | 0.4104 | 0.5732 | 0.4104 | 0.6406 |
|
| 226 |
+
| No log | 58.3333 | 350 | 0.4450 | 0.5533 | 0.4450 | 0.6671 |
|
| 227 |
+
| No log | 58.6667 | 352 | 0.4789 | 0.5327 | 0.4789 | 0.6920 |
|
| 228 |
+
| No log | 59.0 | 354 | 0.4789 | 0.5736 | 0.4789 | 0.6920 |
|
| 229 |
+
| No log | 59.3333 | 356 | 0.4599 | 0.5516 | 0.4599 | 0.6782 |
|
| 230 |
+
| No log | 59.6667 | 358 | 0.4366 | 0.5533 | 0.4366 | 0.6607 |
|
| 231 |
+
| No log | 60.0 | 360 | 0.4255 | 0.5631 | 0.4255 | 0.6523 |
|
| 232 |
+
| No log | 60.3333 | 362 | 0.4213 | 0.5631 | 0.4213 | 0.6491 |
|
| 233 |
+
| No log | 60.6667 | 364 | 0.4183 | 0.5631 | 0.4183 | 0.6467 |
|
| 234 |
+
| No log | 61.0 | 366 | 0.4144 | 0.5631 | 0.4144 | 0.6438 |
|
| 235 |
+
| No log | 61.3333 | 368 | 0.4139 | 0.5631 | 0.4139 | 0.6434 |
|
| 236 |
+
| No log | 61.6667 | 370 | 0.4055 | 0.5631 | 0.4055 | 0.6368 |
|
| 237 |
+
| No log | 62.0 | 372 | 0.4031 | 0.5631 | 0.4031 | 0.6349 |
|
| 238 |
+
| No log | 62.3333 | 374 | 0.4044 | 0.5631 | 0.4044 | 0.6359 |
|
| 239 |
+
| No log | 62.6667 | 376 | 0.4103 | 0.5631 | 0.4103 | 0.6405 |
|
| 240 |
+
| No log | 63.0 | 378 | 0.4185 | 0.5533 | 0.4185 | 0.6469 |
|
| 241 |
+
| No log | 63.3333 | 380 | 0.4251 | 0.5533 | 0.4251 | 0.6520 |
|
| 242 |
+
| No log | 63.6667 | 382 | 0.4263 | 0.5533 | 0.4263 | 0.6529 |
|
| 243 |
+
| No log | 64.0 | 384 | 0.4336 | 0.5533 | 0.4336 | 0.6585 |
|
| 244 |
+
| No log | 64.3333 | 386 | 0.4290 | 0.5533 | 0.4290 | 0.6550 |
|
| 245 |
+
| No log | 64.6667 | 388 | 0.4165 | 0.5533 | 0.4165 | 0.6454 |
|
| 246 |
+
| No log | 65.0 | 390 | 0.4144 | 0.5533 | 0.4144 | 0.6437 |
|
| 247 |
+
| No log | 65.3333 | 392 | 0.4277 | 0.5533 | 0.4277 | 0.6540 |
|
| 248 |
+
| No log | 65.6667 | 394 | 0.4403 | 0.5533 | 0.4403 | 0.6635 |
|
| 249 |
+
| No log | 66.0 | 396 | 0.4319 | 0.5533 | 0.4319 | 0.6572 |
|
| 250 |
+
| No log | 66.3333 | 398 | 0.4130 | 0.5912 | 0.4130 | 0.6426 |
|
| 251 |
+
| No log | 66.6667 | 400 | 0.3991 | 0.6228 | 0.3991 | 0.6317 |
|
| 252 |
+
| No log | 67.0 | 402 | 0.4072 | 0.6357 | 0.4072 | 0.6381 |
|
| 253 |
+
| No log | 67.3333 | 404 | 0.4157 | 0.6282 | 0.4157 | 0.6448 |
|
| 254 |
+
| No log | 67.6667 | 406 | 0.4132 | 0.6229 | 0.4132 | 0.6428 |
|
| 255 |
+
| No log | 68.0 | 408 | 0.4131 | 0.6111 | 0.4131 | 0.6427 |
|
| 256 |
+
| No log | 68.3333 | 410 | 0.4216 | 0.5868 | 0.4216 | 0.6493 |
|
| 257 |
+
| No log | 68.6667 | 412 | 0.4393 | 0.5533 | 0.4393 | 0.6628 |
|
| 258 |
+
| No log | 69.0 | 414 | 0.4445 | 0.5533 | 0.4445 | 0.6667 |
|
| 259 |
+
| No log | 69.3333 | 416 | 0.4442 | 0.5533 | 0.4442 | 0.6665 |
|
| 260 |
+
| No log | 69.6667 | 418 | 0.4485 | 0.5533 | 0.4485 | 0.6697 |
|
| 261 |
+
| No log | 70.0 | 420 | 0.4446 | 0.5533 | 0.4446 | 0.6668 |
|
| 262 |
+
| No log | 70.3333 | 422 | 0.4394 | 0.5868 | 0.4394 | 0.6628 |
|
| 263 |
+
| No log | 70.6667 | 424 | 0.4352 | 0.5868 | 0.4352 | 0.6597 |
|
| 264 |
+
| No log | 71.0 | 426 | 0.4285 | 0.5868 | 0.4285 | 0.6546 |
|
| 265 |
+
| No log | 71.3333 | 428 | 0.4230 | 0.6001 | 0.4230 | 0.6504 |
|
| 266 |
+
| No log | 71.6667 | 430 | 0.4217 | 0.6229 | 0.4217 | 0.6494 |
|
| 267 |
+
| No log | 72.0 | 432 | 0.4212 | 0.6229 | 0.4212 | 0.6490 |
|
| 268 |
+
| No log | 72.3333 | 434 | 0.4176 | 0.6229 | 0.4176 | 0.6462 |
|
| 269 |
+
| No log | 72.6667 | 436 | 0.4132 | 0.6229 | 0.4132 | 0.6428 |
|
| 270 |
+
| No log | 73.0 | 438 | 0.4094 | 0.6215 | 0.4094 | 0.6399 |
|
| 271 |
+
| No log | 73.3333 | 440 | 0.4086 | 0.6096 | 0.4086 | 0.6392 |
|
| 272 |
+
| No log | 73.6667 | 442 | 0.4065 | 0.6111 | 0.4065 | 0.6375 |
|
| 273 |
+
| No log | 74.0 | 444 | 0.4059 | 0.6010 | 0.4059 | 0.6371 |
|
| 274 |
+
| No log | 74.3333 | 446 | 0.4064 | 0.6010 | 0.4064 | 0.6375 |
|
| 275 |
+
| No log | 74.6667 | 448 | 0.4100 | 0.5784 | 0.4100 | 0.6403 |
|
| 276 |
+
| No log | 75.0 | 450 | 0.4179 | 0.5631 | 0.4179 | 0.6465 |
|
| 277 |
+
| No log | 75.3333 | 452 | 0.4226 | 0.5631 | 0.4226 | 0.6501 |
|
| 278 |
+
| No log | 75.6667 | 454 | 0.4254 | 0.5631 | 0.4254 | 0.6523 |
|
| 279 |
+
| No log | 76.0 | 456 | 0.4246 | 0.5631 | 0.4246 | 0.6516 |
|
| 280 |
+
| No log | 76.3333 | 458 | 0.4228 | 0.5631 | 0.4228 | 0.6502 |
|
| 281 |
+
| No log | 76.6667 | 460 | 0.4204 | 0.5631 | 0.4204 | 0.6484 |
|
| 282 |
+
| No log | 77.0 | 462 | 0.4202 | 0.5868 | 0.4202 | 0.6482 |
|
| 283 |
+
| No log | 77.3333 | 464 | 0.4276 | 0.5631 | 0.4276 | 0.6539 |
|
| 284 |
+
| No log | 77.6667 | 466 | 0.4387 | 0.5852 | 0.4387 | 0.6623 |
|
| 285 |
+
| No log | 78.0 | 468 | 0.4404 | 0.5852 | 0.4404 | 0.6636 |
|
| 286 |
+
| No log | 78.3333 | 470 | 0.4349 | 0.5852 | 0.4349 | 0.6594 |
|
| 287 |
+
| No log | 78.6667 | 472 | 0.4232 | 0.5868 | 0.4232 | 0.6506 |
|
| 288 |
+
| No log | 79.0 | 474 | 0.4199 | 0.5868 | 0.4199 | 0.6480 |
|
| 289 |
+
| No log | 79.3333 | 476 | 0.4125 | 0.5868 | 0.4125 | 0.6423 |
|
| 290 |
+
| No log | 79.6667 | 478 | 0.4069 | 0.5868 | 0.4069 | 0.6379 |
|
| 291 |
+
| No log | 80.0 | 480 | 0.4064 | 0.5868 | 0.4064 | 0.6375 |
|
| 292 |
+
| No log | 80.3333 | 482 | 0.4059 | 0.5868 | 0.4059 | 0.6371 |
|
| 293 |
+
| No log | 80.6667 | 484 | 0.4073 | 0.5868 | 0.4073 | 0.6382 |
|
| 294 |
+
| No log | 81.0 | 486 | 0.4102 | 0.5868 | 0.4102 | 0.6405 |
|
| 295 |
+
| No log | 81.3333 | 488 | 0.4142 | 0.5631 | 0.4142 | 0.6436 |
|
| 296 |
+
| No log | 81.6667 | 490 | 0.4224 | 0.5631 | 0.4224 | 0.6500 |
|
| 297 |
+
| No log | 82.0 | 492 | 0.4335 | 0.5631 | 0.4335 | 0.6584 |
|
| 298 |
+
| No log | 82.3333 | 494 | 0.4361 | 0.5852 | 0.4361 | 0.6604 |
|
| 299 |
+
| No log | 82.6667 | 496 | 0.4275 | 0.5631 | 0.4275 | 0.6539 |
|
| 300 |
+
| No log | 83.0 | 498 | 0.4130 | 0.5868 | 0.4130 | 0.6427 |
|
| 301 |
+
| 0.1878 | 83.3333 | 500 | 0.4029 | 0.6111 | 0.4029 | 0.6347 |
|
| 302 |
+
| 0.1878 | 83.6667 | 502 | 0.4003 | 0.6111 | 0.4003 | 0.6327 |
|
| 303 |
+
| 0.1878 | 84.0 | 504 | 0.4002 | 0.6111 | 0.4002 | 0.6326 |
|
| 304 |
+
| 0.1878 | 84.3333 | 506 | 0.4011 | 0.6111 | 0.4011 | 0.6334 |
|
| 305 |
+
| 0.1878 | 84.6667 | 508 | 0.4031 | 0.6111 | 0.4031 | 0.6349 |
|
| 306 |
+
| 0.1878 | 85.0 | 510 | 0.4065 | 0.5784 | 0.4065 | 0.6375 |
|
| 307 |
+
|
| 308 |
+
|
| 309 |
+
### Framework versions
|
| 310 |
+
|
| 311 |
+
- Transformers 4.44.2
|
| 312 |
+
- Pytorch 2.4.0+cu118
|
| 313 |
+
- Datasets 2.21.0
|
| 314 |
+
- 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:ef08359a380d55a9874789de35f2a03a5889d0072dd08f6563c9f53a321097c1
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c137b78d02e1de349cccf7f85e0f17ced6937d0ffff4c3bd4d13ec436fa4b0a
|
| 3 |
+
size 5304
|