Training in progress, step 500
Browse files- README.md +324 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k18_task2_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 |
+
# ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k18_task2_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: 0.5999
|
| 19 |
+
- Qwk: 0.4729
|
| 20 |
+
- Mse: 0.5999
|
| 21 |
+
- Rmse: 0.7745
|
| 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 | 0.0217 | 2 | 4.4755 | -0.0182 | 4.4755 | 2.1155 |
|
| 53 |
+
| No log | 0.0435 | 4 | 2.5785 | -0.0311 | 2.5785 | 1.6058 |
|
| 54 |
+
| No log | 0.0652 | 6 | 1.5327 | 0.0107 | 1.5327 | 1.2380 |
|
| 55 |
+
| No log | 0.0870 | 8 | 0.9215 | 0.0112 | 0.9215 | 0.9600 |
|
| 56 |
+
| No log | 0.1087 | 10 | 0.7554 | 0.1989 | 0.7554 | 0.8692 |
|
| 57 |
+
| No log | 0.1304 | 12 | 0.7954 | 0.1761 | 0.7954 | 0.8918 |
|
| 58 |
+
| No log | 0.1522 | 14 | 0.7669 | 0.2863 | 0.7669 | 0.8758 |
|
| 59 |
+
| No log | 0.1739 | 16 | 0.7581 | 0.2950 | 0.7581 | 0.8707 |
|
| 60 |
+
| No log | 0.1957 | 18 | 0.9114 | 0.3127 | 0.9114 | 0.9547 |
|
| 61 |
+
| No log | 0.2174 | 20 | 1.5961 | 0.1776 | 1.5961 | 1.2634 |
|
| 62 |
+
| No log | 0.2391 | 22 | 1.4258 | 0.2409 | 1.4258 | 1.1940 |
|
| 63 |
+
| No log | 0.2609 | 24 | 0.9936 | 0.3063 | 0.9936 | 0.9968 |
|
| 64 |
+
| No log | 0.2826 | 26 | 0.8759 | 0.2610 | 0.8759 | 0.9359 |
|
| 65 |
+
| No log | 0.3043 | 28 | 0.9690 | 0.248 | 0.9690 | 0.9844 |
|
| 66 |
+
| No log | 0.3261 | 30 | 0.9485 | 0.2807 | 0.9485 | 0.9739 |
|
| 67 |
+
| No log | 0.3478 | 32 | 0.9661 | 0.2807 | 0.9661 | 0.9829 |
|
| 68 |
+
| No log | 0.3696 | 34 | 0.7324 | 0.4511 | 0.7324 | 0.8558 |
|
| 69 |
+
| No log | 0.3913 | 36 | 0.7103 | 0.4749 | 0.7103 | 0.8428 |
|
| 70 |
+
| No log | 0.4130 | 38 | 1.0714 | 0.2719 | 1.0714 | 1.0351 |
|
| 71 |
+
| No log | 0.4348 | 40 | 1.3635 | 0.2395 | 1.3635 | 1.1677 |
|
| 72 |
+
| No log | 0.4565 | 42 | 1.2104 | 0.3335 | 1.2104 | 1.1002 |
|
| 73 |
+
| No log | 0.4783 | 44 | 0.8032 | 0.5201 | 0.8032 | 0.8962 |
|
| 74 |
+
| No log | 0.5 | 46 | 0.6329 | 0.4895 | 0.6329 | 0.7955 |
|
| 75 |
+
| No log | 0.5217 | 48 | 0.7703 | 0.3785 | 0.7703 | 0.8777 |
|
| 76 |
+
| No log | 0.5435 | 50 | 0.8004 | 0.3348 | 0.8004 | 0.8947 |
|
| 77 |
+
| No log | 0.5652 | 52 | 0.8132 | 0.4617 | 0.8132 | 0.9017 |
|
| 78 |
+
| No log | 0.5870 | 54 | 1.0158 | 0.4151 | 1.0158 | 1.0079 |
|
| 79 |
+
| No log | 0.6087 | 56 | 1.0812 | 0.3787 | 1.0812 | 1.0398 |
|
| 80 |
+
| No log | 0.6304 | 58 | 0.9299 | 0.4668 | 0.9299 | 0.9643 |
|
| 81 |
+
| No log | 0.6522 | 60 | 0.6429 | 0.4905 | 0.6429 | 0.8018 |
|
| 82 |
+
| No log | 0.6739 | 62 | 0.5667 | 0.4573 | 0.5667 | 0.7528 |
|
| 83 |
+
| No log | 0.6957 | 64 | 0.5821 | 0.5065 | 0.5821 | 0.7629 |
|
| 84 |
+
| No log | 0.7174 | 66 | 0.5890 | 0.5496 | 0.5890 | 0.7675 |
|
| 85 |
+
| No log | 0.7391 | 68 | 0.5501 | 0.5222 | 0.5501 | 0.7417 |
|
| 86 |
+
| No log | 0.7609 | 70 | 0.6946 | 0.4673 | 0.6946 | 0.8335 |
|
| 87 |
+
| No log | 0.7826 | 72 | 1.1268 | 0.4068 | 1.1268 | 1.0615 |
|
| 88 |
+
| No log | 0.8043 | 74 | 1.3513 | 0.3602 | 1.3513 | 1.1624 |
|
| 89 |
+
| No log | 0.8261 | 76 | 1.2013 | 0.4126 | 1.2013 | 1.0960 |
|
| 90 |
+
| No log | 0.8478 | 78 | 0.9217 | 0.4446 | 0.9217 | 0.9601 |
|
| 91 |
+
| No log | 0.8696 | 80 | 0.8619 | 0.4546 | 0.8619 | 0.9284 |
|
| 92 |
+
| No log | 0.8913 | 82 | 0.7562 | 0.5145 | 0.7562 | 0.8696 |
|
| 93 |
+
| No log | 0.9130 | 84 | 0.7483 | 0.5250 | 0.7483 | 0.8651 |
|
| 94 |
+
| No log | 0.9348 | 86 | 0.7401 | 0.5099 | 0.7401 | 0.8603 |
|
| 95 |
+
| No log | 0.9565 | 88 | 0.7755 | 0.4642 | 0.7755 | 0.8806 |
|
| 96 |
+
| No log | 0.9783 | 90 | 0.7854 | 0.4701 | 0.7854 | 0.8862 |
|
| 97 |
+
| No log | 1.0 | 92 | 0.7081 | 0.5145 | 0.7081 | 0.8415 |
|
| 98 |
+
| No log | 1.0217 | 94 | 0.6405 | 0.5004 | 0.6405 | 0.8003 |
|
| 99 |
+
| No log | 1.0435 | 96 | 0.6606 | 0.5402 | 0.6606 | 0.8128 |
|
| 100 |
+
| No log | 1.0652 | 98 | 0.7107 | 0.5232 | 0.7107 | 0.8431 |
|
| 101 |
+
| No log | 1.0870 | 100 | 0.7390 | 0.5717 | 0.7390 | 0.8596 |
|
| 102 |
+
| No log | 1.1087 | 102 | 0.7150 | 0.5496 | 0.7150 | 0.8456 |
|
| 103 |
+
| No log | 1.1304 | 104 | 0.7347 | 0.4854 | 0.7347 | 0.8571 |
|
| 104 |
+
| No log | 1.1522 | 106 | 0.7103 | 0.5598 | 0.7103 | 0.8428 |
|
| 105 |
+
| No log | 1.1739 | 108 | 0.7524 | 0.5357 | 0.7524 | 0.8674 |
|
| 106 |
+
| No log | 1.1957 | 110 | 0.8977 | 0.4867 | 0.8977 | 0.9475 |
|
| 107 |
+
| No log | 1.2174 | 112 | 0.8473 | 0.5447 | 0.8473 | 0.9205 |
|
| 108 |
+
| No log | 1.2391 | 114 | 0.7036 | 0.5124 | 0.7036 | 0.8388 |
|
| 109 |
+
| No log | 1.2609 | 116 | 0.6730 | 0.5322 | 0.6730 | 0.8204 |
|
| 110 |
+
| No log | 1.2826 | 118 | 0.6736 | 0.5129 | 0.6736 | 0.8207 |
|
| 111 |
+
| No log | 1.3043 | 120 | 0.6857 | 0.4898 | 0.6857 | 0.8280 |
|
| 112 |
+
| No log | 1.3261 | 122 | 0.6725 | 0.4921 | 0.6725 | 0.8200 |
|
| 113 |
+
| No log | 1.3478 | 124 | 0.7127 | 0.5077 | 0.7127 | 0.8442 |
|
| 114 |
+
| No log | 1.3696 | 126 | 0.6528 | 0.4721 | 0.6528 | 0.8079 |
|
| 115 |
+
| No log | 1.3913 | 128 | 0.6565 | 0.4880 | 0.6565 | 0.8102 |
|
| 116 |
+
| No log | 1.4130 | 130 | 0.6378 | 0.4998 | 0.6378 | 0.7986 |
|
| 117 |
+
| No log | 1.4348 | 132 | 0.6440 | 0.4779 | 0.6440 | 0.8025 |
|
| 118 |
+
| No log | 1.4565 | 134 | 0.6357 | 0.5158 | 0.6357 | 0.7973 |
|
| 119 |
+
| No log | 1.4783 | 136 | 0.6257 | 0.5162 | 0.6257 | 0.7910 |
|
| 120 |
+
| No log | 1.5 | 138 | 0.6453 | 0.4807 | 0.6453 | 0.8033 |
|
| 121 |
+
| No log | 1.5217 | 140 | 0.6374 | 0.4711 | 0.6374 | 0.7984 |
|
| 122 |
+
| No log | 1.5435 | 142 | 0.7102 | 0.5208 | 0.7102 | 0.8427 |
|
| 123 |
+
| No log | 1.5652 | 144 | 0.8421 | 0.5120 | 0.8421 | 0.9177 |
|
| 124 |
+
| No log | 1.5870 | 146 | 0.7337 | 0.5066 | 0.7337 | 0.8566 |
|
| 125 |
+
| No log | 1.6087 | 148 | 0.7579 | 0.5431 | 0.7579 | 0.8706 |
|
| 126 |
+
| No log | 1.6304 | 150 | 0.7645 | 0.5108 | 0.7645 | 0.8743 |
|
| 127 |
+
| No log | 1.6522 | 152 | 0.8169 | 0.5347 | 0.8169 | 0.9038 |
|
| 128 |
+
| No log | 1.6739 | 154 | 0.8666 | 0.5251 | 0.8666 | 0.9309 |
|
| 129 |
+
| No log | 1.6957 | 156 | 0.7571 | 0.5045 | 0.7571 | 0.8701 |
|
| 130 |
+
| No log | 1.7174 | 158 | 0.7130 | 0.5066 | 0.7130 | 0.8444 |
|
| 131 |
+
| No log | 1.7391 | 160 | 0.7535 | 0.5464 | 0.7535 | 0.8680 |
|
| 132 |
+
| No log | 1.7609 | 162 | 0.8011 | 0.5066 | 0.8011 | 0.8951 |
|
| 133 |
+
| No log | 1.7826 | 164 | 0.7444 | 0.5564 | 0.7444 | 0.8628 |
|
| 134 |
+
| No log | 1.8043 | 166 | 0.6537 | 0.5398 | 0.6537 | 0.8085 |
|
| 135 |
+
| No log | 1.8261 | 168 | 0.6463 | 0.4779 | 0.6463 | 0.8039 |
|
| 136 |
+
| No log | 1.8478 | 170 | 0.6609 | 0.5555 | 0.6609 | 0.8130 |
|
| 137 |
+
| No log | 1.8696 | 172 | 0.8188 | 0.4798 | 0.8188 | 0.9049 |
|
| 138 |
+
| No log | 1.8913 | 174 | 0.7376 | 0.4815 | 0.7376 | 0.8588 |
|
| 139 |
+
| No log | 1.9130 | 176 | 0.6160 | 0.5475 | 0.6160 | 0.7849 |
|
| 140 |
+
| No log | 1.9348 | 178 | 0.6283 | 0.5355 | 0.6283 | 0.7927 |
|
| 141 |
+
| No log | 1.9565 | 180 | 0.6199 | 0.4909 | 0.6199 | 0.7874 |
|
| 142 |
+
| No log | 1.9783 | 182 | 0.6708 | 0.5634 | 0.6708 | 0.8190 |
|
| 143 |
+
| No log | 2.0 | 184 | 1.0537 | 0.3513 | 1.0537 | 1.0265 |
|
| 144 |
+
| No log | 2.0217 | 186 | 1.3159 | 0.3190 | 1.3159 | 1.1471 |
|
| 145 |
+
| No log | 2.0435 | 188 | 1.1424 | 0.3017 | 1.1424 | 1.0688 |
|
| 146 |
+
| No log | 2.0652 | 190 | 0.7831 | 0.5185 | 0.7831 | 0.8849 |
|
| 147 |
+
| No log | 2.0870 | 192 | 0.6712 | 0.5076 | 0.6712 | 0.8193 |
|
| 148 |
+
| No log | 2.1087 | 194 | 0.6744 | 0.5248 | 0.6744 | 0.8212 |
|
| 149 |
+
| No log | 2.1304 | 196 | 0.7026 | 0.5563 | 0.7026 | 0.8382 |
|
| 150 |
+
| No log | 2.1522 | 198 | 0.7320 | 0.5479 | 0.7320 | 0.8555 |
|
| 151 |
+
| No log | 2.1739 | 200 | 0.6724 | 0.4919 | 0.6724 | 0.8200 |
|
| 152 |
+
| No log | 2.1957 | 202 | 0.6699 | 0.5289 | 0.6699 | 0.8185 |
|
| 153 |
+
| No log | 2.2174 | 204 | 0.7057 | 0.4478 | 0.7057 | 0.8401 |
|
| 154 |
+
| No log | 2.2391 | 206 | 0.6530 | 0.5306 | 0.6530 | 0.8081 |
|
| 155 |
+
| No log | 2.2609 | 208 | 0.6552 | 0.5028 | 0.6552 | 0.8095 |
|
| 156 |
+
| No log | 2.2826 | 210 | 0.6854 | 0.5179 | 0.6854 | 0.8279 |
|
| 157 |
+
| No log | 2.3043 | 212 | 0.6292 | 0.5048 | 0.6292 | 0.7932 |
|
| 158 |
+
| No log | 2.3261 | 214 | 0.6122 | 0.5378 | 0.6122 | 0.7824 |
|
| 159 |
+
| No log | 2.3478 | 216 | 0.5978 | 0.4948 | 0.5978 | 0.7732 |
|
| 160 |
+
| No log | 2.3696 | 218 | 0.5894 | 0.4576 | 0.5894 | 0.7677 |
|
| 161 |
+
| No log | 2.3913 | 220 | 0.5921 | 0.4408 | 0.5921 | 0.7695 |
|
| 162 |
+
| No log | 2.4130 | 222 | 0.6028 | 0.4726 | 0.6028 | 0.7764 |
|
| 163 |
+
| No log | 2.4348 | 224 | 0.6187 | 0.5258 | 0.6187 | 0.7866 |
|
| 164 |
+
| No log | 2.4565 | 226 | 0.6515 | 0.5408 | 0.6515 | 0.8071 |
|
| 165 |
+
| No log | 2.4783 | 228 | 0.6535 | 0.5353 | 0.6535 | 0.8084 |
|
| 166 |
+
| No log | 2.5 | 230 | 0.6408 | 0.5336 | 0.6408 | 0.8005 |
|
| 167 |
+
| No log | 2.5217 | 232 | 0.6459 | 0.5149 | 0.6459 | 0.8037 |
|
| 168 |
+
| No log | 2.5435 | 234 | 0.6606 | 0.5213 | 0.6606 | 0.8128 |
|
| 169 |
+
| No log | 2.5652 | 236 | 0.6701 | 0.5475 | 0.6701 | 0.8186 |
|
| 170 |
+
| No log | 2.5870 | 238 | 0.6759 | 0.5303 | 0.6759 | 0.8221 |
|
| 171 |
+
| No log | 2.6087 | 240 | 0.7164 | 0.5466 | 0.7164 | 0.8464 |
|
| 172 |
+
| No log | 2.6304 | 242 | 0.7211 | 0.5590 | 0.7211 | 0.8492 |
|
| 173 |
+
| No log | 2.6522 | 244 | 0.6597 | 0.5616 | 0.6597 | 0.8122 |
|
| 174 |
+
| No log | 2.6739 | 246 | 0.6412 | 0.5264 | 0.6412 | 0.8008 |
|
| 175 |
+
| No log | 2.6957 | 248 | 0.6380 | 0.5548 | 0.6380 | 0.7988 |
|
| 176 |
+
| No log | 2.7174 | 250 | 0.6565 | 0.5793 | 0.6565 | 0.8102 |
|
| 177 |
+
| No log | 2.7391 | 252 | 0.6687 | 0.5799 | 0.6687 | 0.8177 |
|
| 178 |
+
| No log | 2.7609 | 254 | 0.7328 | 0.5324 | 0.7328 | 0.8560 |
|
| 179 |
+
| No log | 2.7826 | 256 | 0.8840 | 0.4164 | 0.8840 | 0.9402 |
|
| 180 |
+
| No log | 2.8043 | 258 | 1.1472 | 0.3276 | 1.1472 | 1.0711 |
|
| 181 |
+
| No log | 2.8261 | 260 | 1.1223 | 0.3539 | 1.1223 | 1.0594 |
|
| 182 |
+
| No log | 2.8478 | 262 | 0.9535 | 0.4276 | 0.9535 | 0.9765 |
|
| 183 |
+
| No log | 2.8696 | 264 | 0.8000 | 0.4760 | 0.8000 | 0.8944 |
|
| 184 |
+
| No log | 2.8913 | 266 | 0.7087 | 0.5262 | 0.7087 | 0.8418 |
|
| 185 |
+
| No log | 2.9130 | 268 | 0.6779 | 0.5919 | 0.6779 | 0.8234 |
|
| 186 |
+
| No log | 2.9348 | 270 | 0.6172 | 0.6196 | 0.6172 | 0.7856 |
|
| 187 |
+
| No log | 2.9565 | 272 | 0.6113 | 0.6084 | 0.6113 | 0.7818 |
|
| 188 |
+
| No log | 2.9783 | 274 | 0.6249 | 0.5986 | 0.6249 | 0.7905 |
|
| 189 |
+
| No log | 3.0 | 276 | 0.6665 | 0.5590 | 0.6665 | 0.8164 |
|
| 190 |
+
| No log | 3.0217 | 278 | 0.7998 | 0.5120 | 0.7998 | 0.8943 |
|
| 191 |
+
| No log | 3.0435 | 280 | 0.9150 | 0.4323 | 0.9150 | 0.9566 |
|
| 192 |
+
| No log | 3.0652 | 282 | 0.8291 | 0.4985 | 0.8291 | 0.9105 |
|
| 193 |
+
| No log | 3.0870 | 284 | 0.6780 | 0.5186 | 0.6780 | 0.8234 |
|
| 194 |
+
| No log | 3.1087 | 286 | 0.5657 | 0.5556 | 0.5657 | 0.7521 |
|
| 195 |
+
| No log | 3.1304 | 288 | 0.5673 | 0.5026 | 0.5673 | 0.7532 |
|
| 196 |
+
| No log | 3.1522 | 290 | 0.5735 | 0.5319 | 0.5735 | 0.7573 |
|
| 197 |
+
| No log | 3.1739 | 292 | 0.5776 | 0.5063 | 0.5776 | 0.7600 |
|
| 198 |
+
| No log | 3.1957 | 294 | 0.6022 | 0.5614 | 0.6022 | 0.7760 |
|
| 199 |
+
| No log | 3.2174 | 296 | 0.6055 | 0.5356 | 0.6055 | 0.7781 |
|
| 200 |
+
| No log | 3.2391 | 298 | 0.6045 | 0.5534 | 0.6045 | 0.7775 |
|
| 201 |
+
| No log | 3.2609 | 300 | 0.6234 | 0.5201 | 0.6234 | 0.7896 |
|
| 202 |
+
| No log | 3.2826 | 302 | 0.6360 | 0.5201 | 0.6360 | 0.7975 |
|
| 203 |
+
| No log | 3.3043 | 304 | 0.7113 | 0.5133 | 0.7113 | 0.8434 |
|
| 204 |
+
| No log | 3.3261 | 306 | 0.6486 | 0.5217 | 0.6486 | 0.8053 |
|
| 205 |
+
| No log | 3.3478 | 308 | 0.5948 | 0.5595 | 0.5948 | 0.7712 |
|
| 206 |
+
| No log | 3.3696 | 310 | 0.6315 | 0.5121 | 0.6315 | 0.7947 |
|
| 207 |
+
| No log | 3.3913 | 312 | 0.6244 | 0.5528 | 0.6244 | 0.7902 |
|
| 208 |
+
| No log | 3.4130 | 314 | 0.6193 | 0.5528 | 0.6193 | 0.7870 |
|
| 209 |
+
| No log | 3.4348 | 316 | 0.5971 | 0.5587 | 0.5971 | 0.7727 |
|
| 210 |
+
| No log | 3.4565 | 318 | 0.6555 | 0.5329 | 0.6555 | 0.8096 |
|
| 211 |
+
| No log | 3.4783 | 320 | 0.7068 | 0.5569 | 0.7068 | 0.8407 |
|
| 212 |
+
| No log | 3.5 | 322 | 0.6325 | 0.5186 | 0.6325 | 0.7953 |
|
| 213 |
+
| No log | 3.5217 | 324 | 0.5767 | 0.4918 | 0.5767 | 0.7594 |
|
| 214 |
+
| No log | 3.5435 | 326 | 0.6252 | 0.5111 | 0.6252 | 0.7907 |
|
| 215 |
+
| No log | 3.5652 | 328 | 0.6068 | 0.5371 | 0.6068 | 0.7790 |
|
| 216 |
+
| No log | 3.5870 | 330 | 0.5819 | 0.5561 | 0.5819 | 0.7628 |
|
| 217 |
+
| No log | 3.6087 | 332 | 0.6270 | 0.5306 | 0.6270 | 0.7918 |
|
| 218 |
+
| No log | 3.6304 | 334 | 0.6816 | 0.5355 | 0.6816 | 0.8256 |
|
| 219 |
+
| No log | 3.6522 | 336 | 0.6788 | 0.5502 | 0.6788 | 0.8239 |
|
| 220 |
+
| No log | 3.6739 | 338 | 0.6662 | 0.5304 | 0.6662 | 0.8162 |
|
| 221 |
+
| No log | 3.6957 | 340 | 0.6170 | 0.5520 | 0.6170 | 0.7855 |
|
| 222 |
+
| No log | 3.7174 | 342 | 0.6180 | 0.5362 | 0.6180 | 0.7861 |
|
| 223 |
+
| No log | 3.7391 | 344 | 0.6189 | 0.5463 | 0.6189 | 0.7867 |
|
| 224 |
+
| No log | 3.7609 | 346 | 0.6201 | 0.5221 | 0.6201 | 0.7875 |
|
| 225 |
+
| No log | 3.7826 | 348 | 0.6704 | 0.5096 | 0.6704 | 0.8188 |
|
| 226 |
+
| No log | 3.8043 | 350 | 0.6256 | 0.5036 | 0.6256 | 0.7910 |
|
| 227 |
+
| No log | 3.8261 | 352 | 0.5805 | 0.4367 | 0.5805 | 0.7619 |
|
| 228 |
+
| No log | 3.8478 | 354 | 0.5856 | 0.4227 | 0.5856 | 0.7653 |
|
| 229 |
+
| No log | 3.8696 | 356 | 0.5752 | 0.4329 | 0.5752 | 0.7584 |
|
| 230 |
+
| No log | 3.8913 | 358 | 0.5738 | 0.4387 | 0.5738 | 0.7575 |
|
| 231 |
+
| No log | 3.9130 | 360 | 0.6211 | 0.5084 | 0.6211 | 0.7881 |
|
| 232 |
+
| No log | 3.9348 | 362 | 0.6213 | 0.5449 | 0.6213 | 0.7882 |
|
| 233 |
+
| No log | 3.9565 | 364 | 0.6150 | 0.5881 | 0.6150 | 0.7842 |
|
| 234 |
+
| No log | 3.9783 | 366 | 0.6006 | 0.5640 | 0.6006 | 0.7750 |
|
| 235 |
+
| No log | 4.0 | 368 | 0.5939 | 0.5290 | 0.5939 | 0.7706 |
|
| 236 |
+
| No log | 4.0217 | 370 | 0.5988 | 0.5723 | 0.5988 | 0.7738 |
|
| 237 |
+
| No log | 4.0435 | 372 | 0.6693 | 0.5009 | 0.6693 | 0.8181 |
|
| 238 |
+
| No log | 4.0652 | 374 | 0.8070 | 0.4601 | 0.8070 | 0.8983 |
|
| 239 |
+
| No log | 4.0870 | 376 | 0.8670 | 0.4438 | 0.8670 | 0.9311 |
|
| 240 |
+
| No log | 4.1087 | 378 | 0.7286 | 0.4644 | 0.7286 | 0.8536 |
|
| 241 |
+
| No log | 4.1304 | 380 | 0.5927 | 0.4810 | 0.5927 | 0.7699 |
|
| 242 |
+
| No log | 4.1522 | 382 | 0.5890 | 0.4772 | 0.5890 | 0.7675 |
|
| 243 |
+
| No log | 4.1739 | 384 | 0.6137 | 0.5021 | 0.6137 | 0.7834 |
|
| 244 |
+
| No log | 4.1957 | 386 | 0.5920 | 0.5403 | 0.5920 | 0.7694 |
|
| 245 |
+
| No log | 4.2174 | 388 | 0.6020 | 0.4882 | 0.6020 | 0.7759 |
|
| 246 |
+
| No log | 4.2391 | 390 | 0.7943 | 0.4940 | 0.7943 | 0.8913 |
|
| 247 |
+
| No log | 4.2609 | 392 | 1.0526 | 0.4151 | 1.0526 | 1.0259 |
|
| 248 |
+
| No log | 4.2826 | 394 | 1.0880 | 0.4066 | 1.0880 | 1.0431 |
|
| 249 |
+
| No log | 4.3043 | 396 | 0.9139 | 0.4664 | 0.9139 | 0.9560 |
|
| 250 |
+
| No log | 4.3261 | 398 | 0.7078 | 0.5172 | 0.7078 | 0.8413 |
|
| 251 |
+
| No log | 4.3478 | 400 | 0.6309 | 0.5363 | 0.6309 | 0.7943 |
|
| 252 |
+
| No log | 4.3696 | 402 | 0.6044 | 0.5556 | 0.6044 | 0.7774 |
|
| 253 |
+
| No log | 4.3913 | 404 | 0.5947 | 0.5474 | 0.5947 | 0.7712 |
|
| 254 |
+
| No log | 4.4130 | 406 | 0.5897 | 0.5107 | 0.5897 | 0.7679 |
|
| 255 |
+
| No log | 4.4348 | 408 | 0.6018 | 0.5038 | 0.6018 | 0.7758 |
|
| 256 |
+
| No log | 4.4565 | 410 | 0.5948 | 0.5164 | 0.5948 | 0.7712 |
|
| 257 |
+
| No log | 4.4783 | 412 | 0.5953 | 0.5074 | 0.5953 | 0.7715 |
|
| 258 |
+
| No log | 4.5 | 414 | 0.6267 | 0.5289 | 0.6267 | 0.7916 |
|
| 259 |
+
| No log | 4.5217 | 416 | 0.6291 | 0.5053 | 0.6291 | 0.7932 |
|
| 260 |
+
| No log | 4.5435 | 418 | 0.6327 | 0.4743 | 0.6327 | 0.7954 |
|
| 261 |
+
| No log | 4.5652 | 420 | 0.6297 | 0.4743 | 0.6297 | 0.7936 |
|
| 262 |
+
| No log | 4.5870 | 422 | 0.5881 | 0.5025 | 0.5881 | 0.7669 |
|
| 263 |
+
| No log | 4.6087 | 424 | 0.5662 | 0.4548 | 0.5662 | 0.7524 |
|
| 264 |
+
| No log | 4.6304 | 426 | 0.5653 | 0.4539 | 0.5653 | 0.7519 |
|
| 265 |
+
| No log | 4.6522 | 428 | 0.5775 | 0.4840 | 0.5775 | 0.7600 |
|
| 266 |
+
| No log | 4.6739 | 430 | 0.5836 | 0.4704 | 0.5836 | 0.7639 |
|
| 267 |
+
| No log | 4.6957 | 432 | 0.6074 | 0.4845 | 0.6074 | 0.7794 |
|
| 268 |
+
| No log | 4.7174 | 434 | 0.6440 | 0.4639 | 0.6440 | 0.8025 |
|
| 269 |
+
| No log | 4.7391 | 436 | 0.6787 | 0.4984 | 0.6787 | 0.8238 |
|
| 270 |
+
| No log | 4.7609 | 438 | 0.6285 | 0.5363 | 0.6285 | 0.7928 |
|
| 271 |
+
| No log | 4.7826 | 440 | 0.6145 | 0.5778 | 0.6145 | 0.7839 |
|
| 272 |
+
| No log | 4.8043 | 442 | 0.6317 | 0.5237 | 0.6317 | 0.7948 |
|
| 273 |
+
| No log | 4.8261 | 444 | 0.6222 | 0.5445 | 0.6222 | 0.7888 |
|
| 274 |
+
| No log | 4.8478 | 446 | 0.5819 | 0.5427 | 0.5819 | 0.7628 |
|
| 275 |
+
| No log | 4.8696 | 448 | 0.5689 | 0.5475 | 0.5689 | 0.7543 |
|
| 276 |
+
| No log | 4.8913 | 450 | 0.5795 | 0.4644 | 0.5795 | 0.7612 |
|
| 277 |
+
| No log | 4.9130 | 452 | 0.5949 | 0.4873 | 0.5949 | 0.7713 |
|
| 278 |
+
| No log | 4.9348 | 454 | 0.5666 | 0.4833 | 0.5666 | 0.7528 |
|
| 279 |
+
| No log | 4.9565 | 456 | 0.5647 | 0.4797 | 0.5647 | 0.7515 |
|
| 280 |
+
| No log | 4.9783 | 458 | 0.5713 | 0.5040 | 0.5713 | 0.7558 |
|
| 281 |
+
| No log | 5.0 | 460 | 0.5740 | 0.5621 | 0.5740 | 0.7576 |
|
| 282 |
+
| No log | 5.0217 | 462 | 0.5835 | 0.5234 | 0.5835 | 0.7639 |
|
| 283 |
+
| No log | 5.0435 | 464 | 0.5848 | 0.4957 | 0.5848 | 0.7647 |
|
| 284 |
+
| No log | 5.0652 | 466 | 0.5743 | 0.5088 | 0.5743 | 0.7578 |
|
| 285 |
+
| No log | 5.0870 | 468 | 0.5683 | 0.4489 | 0.5683 | 0.7538 |
|
| 286 |
+
| No log | 5.1087 | 470 | 0.5709 | 0.4822 | 0.5709 | 0.7556 |
|
| 287 |
+
| No log | 5.1304 | 472 | 0.5895 | 0.5071 | 0.5895 | 0.7678 |
|
| 288 |
+
| No log | 5.1522 | 474 | 0.5748 | 0.4726 | 0.5748 | 0.7582 |
|
| 289 |
+
| No log | 5.1739 | 476 | 0.5587 | 0.5316 | 0.5587 | 0.7474 |
|
| 290 |
+
| No log | 5.1957 | 478 | 0.5664 | 0.5288 | 0.5664 | 0.7526 |
|
| 291 |
+
| No log | 5.2174 | 480 | 0.5816 | 0.4794 | 0.5816 | 0.7626 |
|
| 292 |
+
| No log | 5.2391 | 482 | 0.5707 | 0.4937 | 0.5707 | 0.7554 |
|
| 293 |
+
| No log | 5.2609 | 484 | 0.5757 | 0.4876 | 0.5757 | 0.7587 |
|
| 294 |
+
| No log | 5.2826 | 486 | 0.5779 | 0.5123 | 0.5779 | 0.7602 |
|
| 295 |
+
| No log | 5.3043 | 488 | 0.5710 | 0.5299 | 0.5710 | 0.7557 |
|
| 296 |
+
| No log | 5.3261 | 490 | 0.5678 | 0.5040 | 0.5678 | 0.7536 |
|
| 297 |
+
| No log | 5.3478 | 492 | 0.5779 | 0.5058 | 0.5779 | 0.7602 |
|
| 298 |
+
| No log | 5.3696 | 494 | 0.6011 | 0.5168 | 0.6011 | 0.7753 |
|
| 299 |
+
| No log | 5.3913 | 496 | 0.5961 | 0.5168 | 0.5961 | 0.7721 |
|
| 300 |
+
| No log | 5.4130 | 498 | 0.5710 | 0.5310 | 0.5710 | 0.7557 |
|
| 301 |
+
| 0.352 | 5.4348 | 500 | 0.5853 | 0.5042 | 0.5853 | 0.7651 |
|
| 302 |
+
| 0.352 | 5.4565 | 502 | 0.6063 | 0.5179 | 0.6063 | 0.7787 |
|
| 303 |
+
| 0.352 | 5.4783 | 504 | 0.5909 | 0.5587 | 0.5909 | 0.7687 |
|
| 304 |
+
| 0.352 | 5.5 | 506 | 0.6180 | 0.4866 | 0.6180 | 0.7861 |
|
| 305 |
+
| 0.352 | 5.5217 | 508 | 0.6526 | 0.5113 | 0.6526 | 0.8078 |
|
| 306 |
+
| 0.352 | 5.5435 | 510 | 0.6067 | 0.5216 | 0.6067 | 0.7789 |
|
| 307 |
+
| 0.352 | 5.5652 | 512 | 0.5736 | 0.5248 | 0.5736 | 0.7574 |
|
| 308 |
+
| 0.352 | 5.5870 | 514 | 0.5770 | 0.5161 | 0.5770 | 0.7596 |
|
| 309 |
+
| 0.352 | 5.6087 | 516 | 0.5816 | 0.5135 | 0.5816 | 0.7626 |
|
| 310 |
+
| 0.352 | 5.6304 | 518 | 0.5988 | 0.5428 | 0.5988 | 0.7738 |
|
| 311 |
+
| 0.352 | 5.6522 | 520 | 0.5896 | 0.5527 | 0.5896 | 0.7678 |
|
| 312 |
+
| 0.352 | 5.6739 | 522 | 0.5792 | 0.4467 | 0.5792 | 0.7611 |
|
| 313 |
+
| 0.352 | 5.6957 | 524 | 0.5840 | 0.4251 | 0.5840 | 0.7642 |
|
| 314 |
+
| 0.352 | 5.7174 | 526 | 0.5797 | 0.4393 | 0.5797 | 0.7614 |
|
| 315 |
+
| 0.352 | 5.7391 | 528 | 0.5813 | 0.4662 | 0.5813 | 0.7624 |
|
| 316 |
+
| 0.352 | 5.7609 | 530 | 0.5999 | 0.4729 | 0.5999 | 0.7745 |
|
| 317 |
+
|
| 318 |
+
|
| 319 |
+
### Framework versions
|
| 320 |
+
|
| 321 |
+
- Transformers 4.44.2
|
| 322 |
+
- Pytorch 2.4.0+cu118
|
| 323 |
+
- Datasets 2.21.0
|
| 324 |
+
- 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 sha256:70d6f3720893b21ba09c07ac7b9e4d36b050fcae7ead042510b9eb25b7816bc9
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c321848d8d711dae70f01798f09a3b47860c679380c358f6f90397315398782
|
| 3 |
+
size 5304
|