Training in progress, step 500
Browse files- README.md +326 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k8_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_usingALLEssays_FineTuningAraBERT_run1_AugV5_k8_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: 0.6380
|
| 19 |
+
- Qwk: 0.2923
|
| 20 |
+
- Mse: 0.6380
|
| 21 |
+
- Rmse: 0.7987
|
| 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 | 0.0769 | 2 | 2.5695 | -0.0109 | 2.5695 | 1.6030 |
|
| 53 |
+
| No log | 0.1538 | 4 | 1.3333 | 0.0495 | 1.3333 | 1.1547 |
|
| 54 |
+
| No log | 0.2308 | 6 | 0.9296 | -0.0660 | 0.9296 | 0.9642 |
|
| 55 |
+
| No log | 0.3077 | 8 | 0.9385 | -0.0753 | 0.9385 | 0.9687 |
|
| 56 |
+
| No log | 0.3846 | 10 | 0.8994 | 0.0393 | 0.8994 | 0.9484 |
|
| 57 |
+
| No log | 0.4615 | 12 | 0.9084 | 0.0 | 0.9084 | 0.9531 |
|
| 58 |
+
| No log | 0.5385 | 14 | 0.8571 | 0.0 | 0.8571 | 0.9258 |
|
| 59 |
+
| No log | 0.6154 | 16 | 0.8319 | 0.0937 | 0.8319 | 0.9121 |
|
| 60 |
+
| No log | 0.6923 | 18 | 0.7918 | 0.1372 | 0.7918 | 0.8898 |
|
| 61 |
+
| No log | 0.7692 | 20 | 0.8439 | 0.2087 | 0.8439 | 0.9186 |
|
| 62 |
+
| No log | 0.8462 | 22 | 0.8182 | 0.2736 | 0.8182 | 0.9045 |
|
| 63 |
+
| No log | 0.9231 | 24 | 0.8555 | 0.3553 | 0.8555 | 0.9249 |
|
| 64 |
+
| No log | 1.0 | 26 | 1.1313 | 0.2723 | 1.1313 | 1.0636 |
|
| 65 |
+
| No log | 1.0769 | 28 | 1.4611 | 0.0192 | 1.4611 | 1.2088 |
|
| 66 |
+
| No log | 1.1538 | 30 | 1.2870 | 0.1222 | 1.2870 | 1.1345 |
|
| 67 |
+
| No log | 1.2308 | 32 | 0.9100 | 0.3385 | 0.9100 | 0.9540 |
|
| 68 |
+
| No log | 1.3077 | 34 | 0.7790 | 0.2919 | 0.7790 | 0.8826 |
|
| 69 |
+
| No log | 1.3846 | 36 | 0.7823 | 0.1786 | 0.7823 | 0.8845 |
|
| 70 |
+
| No log | 1.4615 | 38 | 0.9119 | 0.1345 | 0.9119 | 0.9549 |
|
| 71 |
+
| No log | 1.5385 | 40 | 0.9719 | 0.2464 | 0.9719 | 0.9858 |
|
| 72 |
+
| No log | 1.6154 | 42 | 1.0416 | 0.3013 | 1.0416 | 1.0206 |
|
| 73 |
+
| No log | 1.6923 | 44 | 0.9915 | 0.4035 | 0.9915 | 0.9958 |
|
| 74 |
+
| No log | 1.7692 | 46 | 0.9373 | 0.3645 | 0.9373 | 0.9682 |
|
| 75 |
+
| No log | 1.8462 | 48 | 0.8762 | 0.3354 | 0.8762 | 0.9361 |
|
| 76 |
+
| No log | 1.9231 | 50 | 0.7713 | 0.3051 | 0.7713 | 0.8782 |
|
| 77 |
+
| No log | 2.0 | 52 | 0.7747 | 0.4120 | 0.7747 | 0.8801 |
|
| 78 |
+
| No log | 2.0769 | 54 | 1.0287 | 0.3111 | 1.0287 | 1.0143 |
|
| 79 |
+
| No log | 2.1538 | 56 | 1.2642 | 0.1005 | 1.2642 | 1.1243 |
|
| 80 |
+
| No log | 2.2308 | 58 | 1.0340 | 0.3111 | 1.0340 | 1.0169 |
|
| 81 |
+
| No log | 2.3077 | 60 | 0.7268 | 0.3143 | 0.7268 | 0.8525 |
|
| 82 |
+
| No log | 2.3846 | 62 | 0.5886 | 0.3575 | 0.5886 | 0.7672 |
|
| 83 |
+
| No log | 2.4615 | 64 | 0.7206 | 0.4072 | 0.7206 | 0.8489 |
|
| 84 |
+
| No log | 2.5385 | 66 | 0.6815 | 0.4513 | 0.6815 | 0.8256 |
|
| 85 |
+
| No log | 2.6154 | 68 | 0.5964 | 0.2572 | 0.5964 | 0.7723 |
|
| 86 |
+
| No log | 2.6923 | 70 | 0.6828 | 0.2486 | 0.6828 | 0.8263 |
|
| 87 |
+
| No log | 2.7692 | 72 | 0.7895 | 0.3772 | 0.7895 | 0.8885 |
|
| 88 |
+
| No log | 2.8462 | 74 | 0.7792 | 0.3772 | 0.7792 | 0.8827 |
|
| 89 |
+
| No log | 2.9231 | 76 | 0.7471 | 0.3746 | 0.7471 | 0.8643 |
|
| 90 |
+
| No log | 3.0 | 78 | 0.6571 | 0.3640 | 0.6571 | 0.8106 |
|
| 91 |
+
| No log | 3.0769 | 80 | 0.6126 | 0.3690 | 0.6126 | 0.7827 |
|
| 92 |
+
| No log | 3.1538 | 82 | 0.6156 | 0.4788 | 0.6156 | 0.7846 |
|
| 93 |
+
| No log | 3.2308 | 84 | 0.6580 | 0.4788 | 0.6580 | 0.8112 |
|
| 94 |
+
| No log | 3.3077 | 86 | 0.7435 | 0.4074 | 0.7435 | 0.8623 |
|
| 95 |
+
| No log | 3.3846 | 88 | 0.8863 | 0.4277 | 0.8863 | 0.9415 |
|
| 96 |
+
| No log | 3.4615 | 90 | 0.9179 | 0.3747 | 0.9179 | 0.9581 |
|
| 97 |
+
| No log | 3.5385 | 92 | 0.7826 | 0.4280 | 0.7826 | 0.8846 |
|
| 98 |
+
| No log | 3.6154 | 94 | 0.6846 | 0.4776 | 0.6846 | 0.8274 |
|
| 99 |
+
| No log | 3.6923 | 96 | 0.5854 | 0.4923 | 0.5854 | 0.7651 |
|
| 100 |
+
| No log | 3.7692 | 98 | 0.5975 | 0.4958 | 0.5975 | 0.7730 |
|
| 101 |
+
| No log | 3.8462 | 100 | 0.6489 | 0.5578 | 0.6489 | 0.8056 |
|
| 102 |
+
| No log | 3.9231 | 102 | 0.7139 | 0.5457 | 0.7139 | 0.8449 |
|
| 103 |
+
| No log | 4.0 | 104 | 0.7526 | 0.4914 | 0.7526 | 0.8676 |
|
| 104 |
+
| No log | 4.0769 | 106 | 0.6913 | 0.4935 | 0.6913 | 0.8314 |
|
| 105 |
+
| No log | 4.1538 | 108 | 0.5743 | 0.5057 | 0.5743 | 0.7578 |
|
| 106 |
+
| No log | 4.2308 | 110 | 0.6157 | 0.4664 | 0.6157 | 0.7847 |
|
| 107 |
+
| No log | 4.3077 | 112 | 0.6260 | 0.4219 | 0.6260 | 0.7912 |
|
| 108 |
+
| No log | 4.3846 | 114 | 0.5799 | 0.4634 | 0.5799 | 0.7615 |
|
| 109 |
+
| No log | 4.4615 | 116 | 0.6923 | 0.3783 | 0.6923 | 0.8321 |
|
| 110 |
+
| No log | 4.5385 | 118 | 0.7469 | 0.3983 | 0.7469 | 0.8642 |
|
| 111 |
+
| No log | 4.6154 | 120 | 0.6561 | 0.4271 | 0.6561 | 0.8100 |
|
| 112 |
+
| No log | 4.6923 | 122 | 0.6110 | 0.5162 | 0.6110 | 0.7816 |
|
| 113 |
+
| No log | 4.7692 | 124 | 0.6075 | 0.4199 | 0.6075 | 0.7794 |
|
| 114 |
+
| No log | 4.8462 | 126 | 0.6180 | 0.4437 | 0.6180 | 0.7861 |
|
| 115 |
+
| No log | 4.9231 | 128 | 0.5953 | 0.5734 | 0.5953 | 0.7715 |
|
| 116 |
+
| No log | 5.0 | 130 | 0.6845 | 0.4672 | 0.6845 | 0.8274 |
|
| 117 |
+
| No log | 5.0769 | 132 | 0.7863 | 0.3790 | 0.7863 | 0.8867 |
|
| 118 |
+
| No log | 5.1538 | 134 | 0.7472 | 0.4635 | 0.7472 | 0.8644 |
|
| 119 |
+
| No log | 5.2308 | 136 | 0.6011 | 0.4339 | 0.6011 | 0.7753 |
|
| 120 |
+
| No log | 5.3077 | 138 | 0.5545 | 0.5333 | 0.5545 | 0.7446 |
|
| 121 |
+
| No log | 5.3846 | 140 | 0.6023 | 0.4939 | 0.6023 | 0.7761 |
|
| 122 |
+
| No log | 5.4615 | 142 | 0.7074 | 0.4635 | 0.7074 | 0.8411 |
|
| 123 |
+
| No log | 5.5385 | 144 | 0.6583 | 0.4987 | 0.6583 | 0.8114 |
|
| 124 |
+
| No log | 5.6154 | 146 | 0.6391 | 0.4892 | 0.6391 | 0.7995 |
|
| 125 |
+
| No log | 5.6923 | 148 | 0.6062 | 0.4850 | 0.6062 | 0.7786 |
|
| 126 |
+
| No log | 5.7692 | 150 | 0.6425 | 0.4373 | 0.6425 | 0.8016 |
|
| 127 |
+
| No log | 5.8462 | 152 | 0.6052 | 0.4584 | 0.6052 | 0.7780 |
|
| 128 |
+
| No log | 5.9231 | 154 | 0.5688 | 0.4289 | 0.5688 | 0.7542 |
|
| 129 |
+
| No log | 6.0 | 156 | 0.5933 | 0.3416 | 0.5933 | 0.7702 |
|
| 130 |
+
| No log | 6.0769 | 158 | 0.6720 | 0.2036 | 0.6720 | 0.8198 |
|
| 131 |
+
| No log | 6.1538 | 160 | 0.8012 | 0.3068 | 0.8012 | 0.8951 |
|
| 132 |
+
| No log | 6.2308 | 162 | 0.8153 | 0.2677 | 0.8153 | 0.9029 |
|
| 133 |
+
| No log | 6.3077 | 164 | 0.8240 | 0.3432 | 0.8240 | 0.9077 |
|
| 134 |
+
| No log | 6.3846 | 166 | 0.8500 | 0.2754 | 0.8500 | 0.9220 |
|
| 135 |
+
| No log | 6.4615 | 168 | 0.7437 | 0.4482 | 0.7437 | 0.8624 |
|
| 136 |
+
| No log | 6.5385 | 170 | 0.6210 | 0.4264 | 0.6210 | 0.7881 |
|
| 137 |
+
| No log | 6.6154 | 172 | 0.6034 | 0.4352 | 0.6034 | 0.7768 |
|
| 138 |
+
| No log | 6.6923 | 174 | 0.6318 | 0.4997 | 0.6318 | 0.7949 |
|
| 139 |
+
| No log | 6.7692 | 176 | 0.7800 | 0.4186 | 0.7800 | 0.8832 |
|
| 140 |
+
| No log | 6.8462 | 178 | 0.8661 | 0.2907 | 0.8661 | 0.9306 |
|
| 141 |
+
| No log | 6.9231 | 180 | 0.7584 | 0.3381 | 0.7584 | 0.8709 |
|
| 142 |
+
| No log | 7.0 | 182 | 0.5883 | 0.4838 | 0.5883 | 0.7670 |
|
| 143 |
+
| No log | 7.0769 | 184 | 0.5861 | 0.3092 | 0.5861 | 0.7656 |
|
| 144 |
+
| No log | 7.1538 | 186 | 0.6606 | 0.4134 | 0.6606 | 0.8128 |
|
| 145 |
+
| No log | 7.2308 | 188 | 0.6577 | 0.3673 | 0.6577 | 0.8110 |
|
| 146 |
+
| No log | 7.3077 | 190 | 0.6141 | 0.3243 | 0.6141 | 0.7837 |
|
| 147 |
+
| No log | 7.3846 | 192 | 0.6337 | 0.2443 | 0.6337 | 0.7961 |
|
| 148 |
+
| No log | 7.4615 | 194 | 0.7739 | 0.3103 | 0.7739 | 0.8797 |
|
| 149 |
+
| No log | 7.5385 | 196 | 0.8529 | 0.2512 | 0.8529 | 0.9235 |
|
| 150 |
+
| No log | 7.6154 | 198 | 0.7904 | 0.2803 | 0.7904 | 0.8891 |
|
| 151 |
+
| No log | 7.6923 | 200 | 0.7043 | 0.4544 | 0.7043 | 0.8392 |
|
| 152 |
+
| No log | 7.7692 | 202 | 0.7089 | 0.4459 | 0.7089 | 0.8420 |
|
| 153 |
+
| No log | 7.8462 | 204 | 0.7029 | 0.4510 | 0.7029 | 0.8384 |
|
| 154 |
+
| No log | 7.9231 | 206 | 0.6652 | 0.5161 | 0.6652 | 0.8156 |
|
| 155 |
+
| No log | 8.0 | 208 | 0.6266 | 0.5449 | 0.6266 | 0.7916 |
|
| 156 |
+
| No log | 8.0769 | 210 | 0.6716 | 0.4807 | 0.6716 | 0.8195 |
|
| 157 |
+
| No log | 8.1538 | 212 | 0.6744 | 0.4807 | 0.6744 | 0.8212 |
|
| 158 |
+
| No log | 8.2308 | 214 | 0.6217 | 0.4429 | 0.6217 | 0.7885 |
|
| 159 |
+
| No log | 8.3077 | 216 | 0.6020 | 0.4384 | 0.6020 | 0.7759 |
|
| 160 |
+
| No log | 8.3846 | 218 | 0.6048 | 0.3988 | 0.6048 | 0.7777 |
|
| 161 |
+
| No log | 8.4615 | 220 | 0.6516 | 0.5014 | 0.6516 | 0.8072 |
|
| 162 |
+
| No log | 8.5385 | 222 | 0.6939 | 0.4179 | 0.6939 | 0.8330 |
|
| 163 |
+
| No log | 8.6154 | 224 | 0.6722 | 0.5074 | 0.6722 | 0.8199 |
|
| 164 |
+
| No log | 8.6923 | 226 | 0.6098 | 0.5168 | 0.6098 | 0.7809 |
|
| 165 |
+
| No log | 8.7692 | 228 | 0.5836 | 0.5217 | 0.5836 | 0.7639 |
|
| 166 |
+
| No log | 8.8462 | 230 | 0.5787 | 0.5234 | 0.5787 | 0.7607 |
|
| 167 |
+
| No log | 8.9231 | 232 | 0.5859 | 0.5587 | 0.5859 | 0.7654 |
|
| 168 |
+
| No log | 9.0 | 234 | 0.6019 | 0.5682 | 0.6019 | 0.7758 |
|
| 169 |
+
| No log | 9.0769 | 236 | 0.5925 | 0.5682 | 0.5925 | 0.7697 |
|
| 170 |
+
| No log | 9.1538 | 238 | 0.5599 | 0.5117 | 0.5599 | 0.7483 |
|
| 171 |
+
| No log | 9.2308 | 240 | 0.5392 | 0.5010 | 0.5392 | 0.7343 |
|
| 172 |
+
| No log | 9.3077 | 242 | 0.5392 | 0.5085 | 0.5392 | 0.7343 |
|
| 173 |
+
| No log | 9.3846 | 244 | 0.5412 | 0.5085 | 0.5412 | 0.7357 |
|
| 174 |
+
| No log | 9.4615 | 246 | 0.5611 | 0.5117 | 0.5611 | 0.7490 |
|
| 175 |
+
| No log | 9.5385 | 248 | 0.6240 | 0.4411 | 0.6240 | 0.7900 |
|
| 176 |
+
| No log | 9.6154 | 250 | 0.6279 | 0.4868 | 0.6279 | 0.7924 |
|
| 177 |
+
| No log | 9.6923 | 252 | 0.5932 | 0.5144 | 0.5932 | 0.7702 |
|
| 178 |
+
| No log | 9.7692 | 254 | 0.5464 | 0.5555 | 0.5464 | 0.7392 |
|
| 179 |
+
| No log | 9.8462 | 256 | 0.5414 | 0.5505 | 0.5414 | 0.7358 |
|
| 180 |
+
| No log | 9.9231 | 258 | 0.5413 | 0.5022 | 0.5413 | 0.7357 |
|
| 181 |
+
| No log | 10.0 | 260 | 0.5422 | 0.4276 | 0.5422 | 0.7364 |
|
| 182 |
+
| No log | 10.0769 | 262 | 0.5471 | 0.5061 | 0.5471 | 0.7396 |
|
| 183 |
+
| No log | 10.1538 | 264 | 0.5792 | 0.5127 | 0.5792 | 0.7610 |
|
| 184 |
+
| No log | 10.2308 | 266 | 0.6040 | 0.5127 | 0.6040 | 0.7772 |
|
| 185 |
+
| No log | 10.3077 | 268 | 0.5728 | 0.5321 | 0.5728 | 0.7568 |
|
| 186 |
+
| No log | 10.3846 | 270 | 0.5720 | 0.5304 | 0.5720 | 0.7563 |
|
| 187 |
+
| No log | 10.4615 | 272 | 0.5935 | 0.5266 | 0.5935 | 0.7704 |
|
| 188 |
+
| No log | 10.5385 | 274 | 0.5988 | 0.5046 | 0.5988 | 0.7738 |
|
| 189 |
+
| No log | 10.6154 | 276 | 0.5860 | 0.4767 | 0.5860 | 0.7655 |
|
| 190 |
+
| No log | 10.6923 | 278 | 0.5987 | 0.4584 | 0.5987 | 0.7738 |
|
| 191 |
+
| No log | 10.7692 | 280 | 0.5953 | 0.3396 | 0.5953 | 0.7716 |
|
| 192 |
+
| No log | 10.8462 | 282 | 0.6037 | 0.3396 | 0.6037 | 0.7770 |
|
| 193 |
+
| No log | 10.9231 | 284 | 0.5925 | 0.4061 | 0.5925 | 0.7697 |
|
| 194 |
+
| No log | 11.0 | 286 | 0.5704 | 0.3385 | 0.5704 | 0.7552 |
|
| 195 |
+
| No log | 11.0769 | 288 | 0.5668 | 0.3916 | 0.5668 | 0.7528 |
|
| 196 |
+
| No log | 11.1538 | 290 | 0.5796 | 0.4767 | 0.5796 | 0.7613 |
|
| 197 |
+
| No log | 11.2308 | 292 | 0.5998 | 0.4888 | 0.5998 | 0.7745 |
|
| 198 |
+
| No log | 11.3077 | 294 | 0.5756 | 0.4767 | 0.5756 | 0.7587 |
|
| 199 |
+
| No log | 11.3846 | 296 | 0.5665 | 0.4767 | 0.5665 | 0.7527 |
|
| 200 |
+
| No log | 11.4615 | 298 | 0.5626 | 0.4211 | 0.5626 | 0.7500 |
|
| 201 |
+
| No log | 11.5385 | 300 | 0.5722 | 0.4767 | 0.5722 | 0.7564 |
|
| 202 |
+
| No log | 11.6154 | 302 | 0.5993 | 0.5030 | 0.5993 | 0.7741 |
|
| 203 |
+
| No log | 11.6923 | 304 | 0.6473 | 0.4927 | 0.6473 | 0.8046 |
|
| 204 |
+
| No log | 11.7692 | 306 | 0.7006 | 0.3352 | 0.7006 | 0.8370 |
|
| 205 |
+
| No log | 11.8462 | 308 | 0.6823 | 0.4860 | 0.6823 | 0.8260 |
|
| 206 |
+
| No log | 11.9231 | 310 | 0.6206 | 0.4888 | 0.6206 | 0.7878 |
|
| 207 |
+
| No log | 12.0 | 312 | 0.5782 | 0.4211 | 0.5782 | 0.7604 |
|
| 208 |
+
| No log | 12.0769 | 314 | 0.5747 | 0.3651 | 0.5747 | 0.7581 |
|
| 209 |
+
| No log | 12.1538 | 316 | 0.5764 | 0.3915 | 0.5764 | 0.7592 |
|
| 210 |
+
| No log | 12.2308 | 318 | 0.5740 | 0.3213 | 0.5740 | 0.7576 |
|
| 211 |
+
| No log | 12.3077 | 320 | 0.5861 | 0.3916 | 0.5861 | 0.7656 |
|
| 212 |
+
| No log | 12.3846 | 322 | 0.6118 | 0.4059 | 0.6118 | 0.7821 |
|
| 213 |
+
| No log | 12.4615 | 324 | 0.6149 | 0.3911 | 0.6149 | 0.7842 |
|
| 214 |
+
| No log | 12.5385 | 326 | 0.5932 | 0.3916 | 0.5932 | 0.7702 |
|
| 215 |
+
| No log | 12.6154 | 328 | 0.5761 | 0.3661 | 0.5761 | 0.7590 |
|
| 216 |
+
| No log | 12.6923 | 330 | 0.5756 | 0.3552 | 0.5756 | 0.7587 |
|
| 217 |
+
| No log | 12.7692 | 332 | 0.5730 | 0.3502 | 0.5730 | 0.7570 |
|
| 218 |
+
| No log | 12.8462 | 334 | 0.5745 | 0.3481 | 0.5745 | 0.7579 |
|
| 219 |
+
| No log | 12.9231 | 336 | 0.5741 | 0.3780 | 0.5741 | 0.7577 |
|
| 220 |
+
| No log | 13.0 | 338 | 0.5870 | 0.4767 | 0.5870 | 0.7662 |
|
| 221 |
+
| No log | 13.0769 | 340 | 0.6019 | 0.4174 | 0.6019 | 0.7758 |
|
| 222 |
+
| No log | 13.1538 | 342 | 0.6077 | 0.3885 | 0.6077 | 0.7796 |
|
| 223 |
+
| No log | 13.2308 | 344 | 0.5988 | 0.3585 | 0.5988 | 0.7738 |
|
| 224 |
+
| No log | 13.3077 | 346 | 0.5858 | 0.3336 | 0.5858 | 0.7653 |
|
| 225 |
+
| No log | 13.3846 | 348 | 0.5700 | 0.3604 | 0.5700 | 0.7550 |
|
| 226 |
+
| No log | 13.4615 | 350 | 0.5631 | 0.3890 | 0.5631 | 0.7504 |
|
| 227 |
+
| No log | 13.5385 | 352 | 0.5584 | 0.4276 | 0.5584 | 0.7473 |
|
| 228 |
+
| No log | 13.6154 | 354 | 0.5703 | 0.5079 | 0.5703 | 0.7552 |
|
| 229 |
+
| No log | 13.6923 | 356 | 0.5848 | 0.4849 | 0.5848 | 0.7647 |
|
| 230 |
+
| No log | 13.7692 | 358 | 0.5746 | 0.4849 | 0.5746 | 0.7580 |
|
| 231 |
+
| No log | 13.8462 | 360 | 0.5776 | 0.4322 | 0.5776 | 0.7600 |
|
| 232 |
+
| No log | 13.9231 | 362 | 0.5791 | 0.4322 | 0.5791 | 0.7610 |
|
| 233 |
+
| No log | 14.0 | 364 | 0.6035 | 0.5265 | 0.6035 | 0.7769 |
|
| 234 |
+
| No log | 14.0769 | 366 | 0.6328 | 0.4841 | 0.6328 | 0.7955 |
|
| 235 |
+
| No log | 14.1538 | 368 | 0.6781 | 0.4652 | 0.6781 | 0.8235 |
|
| 236 |
+
| No log | 14.2308 | 370 | 0.7217 | 0.4250 | 0.7217 | 0.8495 |
|
| 237 |
+
| No log | 14.3077 | 372 | 0.7104 | 0.4302 | 0.7104 | 0.8429 |
|
| 238 |
+
| No log | 14.3846 | 374 | 0.6592 | 0.4652 | 0.6592 | 0.8119 |
|
| 239 |
+
| No log | 14.4615 | 376 | 0.6459 | 0.3953 | 0.6459 | 0.8037 |
|
| 240 |
+
| No log | 14.5385 | 378 | 0.6257 | 0.4452 | 0.6257 | 0.7910 |
|
| 241 |
+
| No log | 14.6154 | 380 | 0.6085 | 0.3885 | 0.6085 | 0.7800 |
|
| 242 |
+
| No log | 14.6923 | 382 | 0.6071 | 0.3302 | 0.6071 | 0.7791 |
|
| 243 |
+
| No log | 14.7692 | 384 | 0.6162 | 0.2642 | 0.6162 | 0.7850 |
|
| 244 |
+
| No log | 14.8462 | 386 | 0.6383 | 0.3001 | 0.6383 | 0.7990 |
|
| 245 |
+
| No log | 14.9231 | 388 | 0.6558 | 0.3189 | 0.6558 | 0.8098 |
|
| 246 |
+
| No log | 15.0 | 390 | 0.6713 | 0.4237 | 0.6713 | 0.8193 |
|
| 247 |
+
| No log | 15.0769 | 392 | 0.6740 | 0.4237 | 0.6740 | 0.8210 |
|
| 248 |
+
| No log | 15.1538 | 394 | 0.6528 | 0.4468 | 0.6528 | 0.8080 |
|
| 249 |
+
| No log | 15.2308 | 396 | 0.6501 | 0.4468 | 0.6501 | 0.8063 |
|
| 250 |
+
| No log | 15.3077 | 398 | 0.6152 | 0.4349 | 0.6152 | 0.7843 |
|
| 251 |
+
| No log | 15.3846 | 400 | 0.6087 | 0.4466 | 0.6087 | 0.7802 |
|
| 252 |
+
| No log | 15.4615 | 402 | 0.5998 | 0.4044 | 0.5998 | 0.7745 |
|
| 253 |
+
| No log | 15.5385 | 404 | 0.6032 | 0.3916 | 0.6032 | 0.7767 |
|
| 254 |
+
| No log | 15.6154 | 406 | 0.6107 | 0.2947 | 0.6107 | 0.7815 |
|
| 255 |
+
| No log | 15.6923 | 408 | 0.6104 | 0.3608 | 0.6104 | 0.7813 |
|
| 256 |
+
| No log | 15.7692 | 410 | 0.6026 | 0.3608 | 0.6026 | 0.7763 |
|
| 257 |
+
| No log | 15.8462 | 412 | 0.5981 | 0.3305 | 0.5981 | 0.7734 |
|
| 258 |
+
| No log | 15.9231 | 414 | 0.6048 | 0.2930 | 0.6048 | 0.7777 |
|
| 259 |
+
| No log | 16.0 | 416 | 0.6034 | 0.2243 | 0.6034 | 0.7768 |
|
| 260 |
+
| No log | 16.0769 | 418 | 0.6045 | 0.2607 | 0.6045 | 0.7775 |
|
| 261 |
+
| No log | 16.1538 | 420 | 0.6016 | 0.2607 | 0.6016 | 0.7756 |
|
| 262 |
+
| No log | 16.2308 | 422 | 0.5927 | 0.3608 | 0.5927 | 0.7699 |
|
| 263 |
+
| No log | 16.3077 | 424 | 0.5875 | 0.4150 | 0.5875 | 0.7665 |
|
| 264 |
+
| No log | 16.3846 | 426 | 0.5902 | 0.4307 | 0.5902 | 0.7683 |
|
| 265 |
+
| No log | 16.4615 | 428 | 0.5900 | 0.4345 | 0.5900 | 0.7681 |
|
| 266 |
+
| No log | 16.5385 | 430 | 0.5947 | 0.4361 | 0.5947 | 0.7712 |
|
| 267 |
+
| No log | 16.6154 | 432 | 0.6016 | 0.3502 | 0.6016 | 0.7756 |
|
| 268 |
+
| No log | 16.6923 | 434 | 0.6037 | 0.3274 | 0.6037 | 0.7770 |
|
| 269 |
+
| No log | 16.7692 | 436 | 0.5992 | 0.2713 | 0.5992 | 0.7741 |
|
| 270 |
+
| No log | 16.8462 | 438 | 0.6066 | 0.3396 | 0.6066 | 0.7789 |
|
| 271 |
+
| No log | 16.9231 | 440 | 0.6166 | 0.3857 | 0.6166 | 0.7852 |
|
| 272 |
+
| No log | 17.0 | 442 | 0.6229 | 0.4139 | 0.6229 | 0.7892 |
|
| 273 |
+
| No log | 17.0769 | 444 | 0.6058 | 0.4389 | 0.6058 | 0.7783 |
|
| 274 |
+
| No log | 17.1538 | 446 | 0.6037 | 0.4389 | 0.6037 | 0.7770 |
|
| 275 |
+
| No log | 17.2308 | 448 | 0.5914 | 0.3860 | 0.5914 | 0.7690 |
|
| 276 |
+
| No log | 17.3077 | 450 | 0.5776 | 0.3502 | 0.5776 | 0.7600 |
|
| 277 |
+
| No log | 17.3846 | 452 | 0.5793 | 0.3808 | 0.5793 | 0.7611 |
|
| 278 |
+
| No log | 17.4615 | 454 | 0.5940 | 0.3703 | 0.5940 | 0.7707 |
|
| 279 |
+
| No log | 17.5385 | 456 | 0.6084 | 0.4821 | 0.6084 | 0.7800 |
|
| 280 |
+
| No log | 17.6154 | 458 | 0.6067 | 0.4427 | 0.6067 | 0.7789 |
|
| 281 |
+
| No log | 17.6923 | 460 | 0.6178 | 0.5065 | 0.6178 | 0.7860 |
|
| 282 |
+
| No log | 17.7692 | 462 | 0.6363 | 0.4841 | 0.6363 | 0.7977 |
|
| 283 |
+
| No log | 17.8462 | 464 | 0.6306 | 0.4351 | 0.6306 | 0.7941 |
|
| 284 |
+
| No log | 17.9231 | 466 | 0.6179 | 0.3331 | 0.6179 | 0.7861 |
|
| 285 |
+
| No log | 18.0 | 468 | 0.6290 | 0.3331 | 0.6290 | 0.7931 |
|
| 286 |
+
| No log | 18.0769 | 470 | 0.6355 | 0.2674 | 0.6355 | 0.7972 |
|
| 287 |
+
| No log | 18.1538 | 472 | 0.6478 | 0.2740 | 0.6478 | 0.8049 |
|
| 288 |
+
| No log | 18.2308 | 474 | 0.6457 | 0.2674 | 0.6457 | 0.8036 |
|
| 289 |
+
| No log | 18.3077 | 476 | 0.6385 | 0.3640 | 0.6385 | 0.7991 |
|
| 290 |
+
| No log | 18.3846 | 478 | 0.6216 | 0.3612 | 0.6216 | 0.7884 |
|
| 291 |
+
| No log | 18.4615 | 480 | 0.6312 | 0.4174 | 0.6312 | 0.7945 |
|
| 292 |
+
| No log | 18.5385 | 482 | 0.6362 | 0.3779 | 0.6362 | 0.7976 |
|
| 293 |
+
| No log | 18.6154 | 484 | 0.6265 | 0.3779 | 0.6265 | 0.7915 |
|
| 294 |
+
| No log | 18.6923 | 486 | 0.6076 | 0.3558 | 0.6076 | 0.7795 |
|
| 295 |
+
| No log | 18.7692 | 488 | 0.6076 | 0.3183 | 0.6076 | 0.7795 |
|
| 296 |
+
| No log | 18.8462 | 490 | 0.6104 | 0.2852 | 0.6104 | 0.7813 |
|
| 297 |
+
| No log | 18.9231 | 492 | 0.6180 | 0.2890 | 0.6180 | 0.7861 |
|
| 298 |
+
| No log | 19.0 | 494 | 0.6269 | 0.3866 | 0.6269 | 0.7918 |
|
| 299 |
+
| No log | 19.0769 | 496 | 0.6289 | 0.3575 | 0.6289 | 0.7930 |
|
| 300 |
+
| No log | 19.1538 | 498 | 0.6350 | 0.3243 | 0.6350 | 0.7969 |
|
| 301 |
+
| 0.2835 | 19.2308 | 500 | 0.6300 | 0.3575 | 0.6300 | 0.7937 |
|
| 302 |
+
| 0.2835 | 19.3077 | 502 | 0.6258 | 0.3575 | 0.6258 | 0.7911 |
|
| 303 |
+
| 0.2835 | 19.3846 | 504 | 0.6170 | 0.2923 | 0.6170 | 0.7855 |
|
| 304 |
+
| 0.2835 | 19.4615 | 506 | 0.6145 | 0.3580 | 0.6145 | 0.7839 |
|
| 305 |
+
| 0.2835 | 19.5385 | 508 | 0.6178 | 0.3889 | 0.6178 | 0.7860 |
|
| 306 |
+
| 0.2835 | 19.6154 | 510 | 0.6242 | 0.3509 | 0.6242 | 0.7901 |
|
| 307 |
+
| 0.2835 | 19.6923 | 512 | 0.6373 | 0.4059 | 0.6373 | 0.7983 |
|
| 308 |
+
| 0.2835 | 19.7692 | 514 | 0.6327 | 0.3462 | 0.6327 | 0.7954 |
|
| 309 |
+
| 0.2835 | 19.8462 | 516 | 0.6277 | 0.3462 | 0.6277 | 0.7923 |
|
| 310 |
+
| 0.2835 | 19.9231 | 518 | 0.6402 | 0.4139 | 0.6402 | 0.8001 |
|
| 311 |
+
| 0.2835 | 20.0 | 520 | 0.6466 | 0.3882 | 0.6466 | 0.8041 |
|
| 312 |
+
| 0.2835 | 20.0769 | 522 | 0.6378 | 0.3691 | 0.6378 | 0.7987 |
|
| 313 |
+
| 0.2835 | 20.1538 | 524 | 0.6262 | 0.3580 | 0.6262 | 0.7913 |
|
| 314 |
+
| 0.2835 | 20.2308 | 526 | 0.6275 | 0.3258 | 0.6275 | 0.7921 |
|
| 315 |
+
| 0.2835 | 20.3077 | 528 | 0.6385 | 0.3258 | 0.6385 | 0.7991 |
|
| 316 |
+
| 0.2835 | 20.3846 | 530 | 0.6515 | 0.3274 | 0.6515 | 0.8072 |
|
| 317 |
+
| 0.2835 | 20.4615 | 532 | 0.6465 | 0.2963 | 0.6465 | 0.8041 |
|
| 318 |
+
| 0.2835 | 20.5385 | 534 | 0.6380 | 0.2923 | 0.6380 | 0.7987 |
|
| 319 |
+
|
| 320 |
+
|
| 321 |
+
### Framework versions
|
| 322 |
+
|
| 323 |
+
- Transformers 4.44.2
|
| 324 |
+
- Pytorch 2.4.0+cu118
|
| 325 |
+
- Datasets 2.21.0
|
| 326 |
+
- 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:f94fb51c4286c7c3cc3643ef0de7456ecdfe589a7ef8ea8eab8d29dbeed8f001
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed7ef06420178dadc5d78edee0e3f6e30c376279116c7198c165e853f4df7735
|
| 3 |
+
size 5304
|