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_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k12_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 |
+
# ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k12_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: 0.7214
|
| 19 |
+
- Qwk: 0.5538
|
| 20 |
+
- Mse: 0.7214
|
| 21 |
+
- Rmse: 0.8494
|
| 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 | 0.0294 | 2 | 4.2730 | 0.0086 | 4.2730 | 2.0671 |
|
| 53 |
+
| No log | 0.0588 | 4 | 2.3984 | 0.1002 | 2.3984 | 1.5487 |
|
| 54 |
+
| No log | 0.0882 | 6 | 1.7139 | 0.0493 | 1.7139 | 1.3092 |
|
| 55 |
+
| No log | 0.1176 | 8 | 1.1979 | 0.2001 | 1.1979 | 1.0945 |
|
| 56 |
+
| No log | 0.1471 | 10 | 1.1977 | 0.1952 | 1.1977 | 1.0944 |
|
| 57 |
+
| No log | 0.1765 | 12 | 1.9500 | 0.0491 | 1.9500 | 1.3964 |
|
| 58 |
+
| No log | 0.2059 | 14 | 2.0430 | 0.1599 | 2.0430 | 1.4293 |
|
| 59 |
+
| No log | 0.2353 | 16 | 1.2036 | 0.1354 | 1.2036 | 1.0971 |
|
| 60 |
+
| No log | 0.2647 | 18 | 1.1109 | 0.2440 | 1.1109 | 1.0540 |
|
| 61 |
+
| No log | 0.2941 | 20 | 1.0413 | 0.2969 | 1.0413 | 1.0204 |
|
| 62 |
+
| No log | 0.3235 | 22 | 1.0871 | 0.3644 | 1.0871 | 1.0427 |
|
| 63 |
+
| No log | 0.3529 | 24 | 1.0536 | 0.3705 | 1.0536 | 1.0265 |
|
| 64 |
+
| No log | 0.3824 | 26 | 0.9785 | 0.4568 | 0.9785 | 0.9892 |
|
| 65 |
+
| No log | 0.4118 | 28 | 0.9430 | 0.4681 | 0.9430 | 0.9711 |
|
| 66 |
+
| No log | 0.4412 | 30 | 0.9352 | 0.5127 | 0.9352 | 0.9671 |
|
| 67 |
+
| No log | 0.4706 | 32 | 0.9166 | 0.5534 | 0.9166 | 0.9574 |
|
| 68 |
+
| No log | 0.5 | 34 | 0.9438 | 0.5963 | 0.9438 | 0.9715 |
|
| 69 |
+
| No log | 0.5294 | 36 | 1.0117 | 0.5210 | 1.0117 | 1.0058 |
|
| 70 |
+
| No log | 0.5588 | 38 | 0.8932 | 0.4777 | 0.8932 | 0.9451 |
|
| 71 |
+
| No log | 0.5882 | 40 | 1.0846 | 0.3549 | 1.0846 | 1.0414 |
|
| 72 |
+
| No log | 0.6176 | 42 | 1.1037 | 0.3682 | 1.1037 | 1.0506 |
|
| 73 |
+
| No log | 0.6471 | 44 | 1.0152 | 0.3686 | 1.0152 | 1.0076 |
|
| 74 |
+
| No log | 0.6765 | 46 | 0.8878 | 0.4626 | 0.8878 | 0.9422 |
|
| 75 |
+
| No log | 0.7059 | 48 | 0.8614 | 0.4910 | 0.8614 | 0.9281 |
|
| 76 |
+
| No log | 0.7353 | 50 | 0.8525 | 0.5611 | 0.8525 | 0.9233 |
|
| 77 |
+
| No log | 0.7647 | 52 | 0.8114 | 0.5647 | 0.8114 | 0.9008 |
|
| 78 |
+
| No log | 0.7941 | 54 | 0.7986 | 0.6006 | 0.7986 | 0.8937 |
|
| 79 |
+
| No log | 0.8235 | 56 | 0.7772 | 0.5895 | 0.7772 | 0.8816 |
|
| 80 |
+
| No log | 0.8529 | 58 | 0.7173 | 0.6275 | 0.7173 | 0.8469 |
|
| 81 |
+
| No log | 0.8824 | 60 | 0.7115 | 0.5709 | 0.7115 | 0.8435 |
|
| 82 |
+
| No log | 0.9118 | 62 | 0.8198 | 0.5383 | 0.8198 | 0.9055 |
|
| 83 |
+
| No log | 0.9412 | 64 | 1.0225 | 0.4449 | 1.0225 | 1.0112 |
|
| 84 |
+
| No log | 0.9706 | 66 | 0.8714 | 0.5192 | 0.8714 | 0.9335 |
|
| 85 |
+
| No log | 1.0 | 68 | 0.7353 | 0.5699 | 0.7353 | 0.8575 |
|
| 86 |
+
| No log | 1.0294 | 70 | 0.7171 | 0.5902 | 0.7171 | 0.8468 |
|
| 87 |
+
| No log | 1.0588 | 72 | 0.7810 | 0.6021 | 0.7810 | 0.8837 |
|
| 88 |
+
| No log | 1.0882 | 74 | 0.8179 | 0.6262 | 0.8179 | 0.9044 |
|
| 89 |
+
| No log | 1.1176 | 76 | 0.8659 | 0.5993 | 0.8659 | 0.9305 |
|
| 90 |
+
| No log | 1.1471 | 78 | 1.0140 | 0.5744 | 1.0140 | 1.0070 |
|
| 91 |
+
| No log | 1.1765 | 80 | 0.8753 | 0.6024 | 0.8753 | 0.9356 |
|
| 92 |
+
| No log | 1.2059 | 82 | 0.9341 | 0.6149 | 0.9341 | 0.9665 |
|
| 93 |
+
| No log | 1.2353 | 84 | 0.8904 | 0.5760 | 0.8904 | 0.9436 |
|
| 94 |
+
| No log | 1.2647 | 86 | 0.8396 | 0.6279 | 0.8396 | 0.9163 |
|
| 95 |
+
| No log | 1.2941 | 88 | 0.8303 | 0.6014 | 0.8303 | 0.9112 |
|
| 96 |
+
| No log | 1.3235 | 90 | 0.8279 | 0.6489 | 0.8279 | 0.9099 |
|
| 97 |
+
| No log | 1.3529 | 92 | 0.7567 | 0.5621 | 0.7567 | 0.8699 |
|
| 98 |
+
| No log | 1.3824 | 94 | 0.7935 | 0.5089 | 0.7935 | 0.8908 |
|
| 99 |
+
| No log | 1.4118 | 96 | 0.7523 | 0.5255 | 0.7523 | 0.8674 |
|
| 100 |
+
| No log | 1.4412 | 98 | 0.8427 | 0.6079 | 0.8427 | 0.9180 |
|
| 101 |
+
| No log | 1.4706 | 100 | 0.9324 | 0.5534 | 0.9324 | 0.9656 |
|
| 102 |
+
| No log | 1.5 | 102 | 0.7841 | 0.6583 | 0.7841 | 0.8855 |
|
| 103 |
+
| No log | 1.5294 | 104 | 0.7589 | 0.5121 | 0.7589 | 0.8711 |
|
| 104 |
+
| No log | 1.5588 | 106 | 0.8080 | 0.5187 | 0.8080 | 0.8989 |
|
| 105 |
+
| No log | 1.5882 | 108 | 0.8005 | 0.5910 | 0.8005 | 0.8947 |
|
| 106 |
+
| No log | 1.6176 | 110 | 0.8325 | 0.5910 | 0.8325 | 0.9124 |
|
| 107 |
+
| No log | 1.6471 | 112 | 0.8688 | 0.6168 | 0.8688 | 0.9321 |
|
| 108 |
+
| No log | 1.6765 | 114 | 0.9007 | 0.5699 | 0.9007 | 0.9491 |
|
| 109 |
+
| No log | 1.7059 | 116 | 0.9313 | 0.5525 | 0.9313 | 0.9651 |
|
| 110 |
+
| No log | 1.7353 | 118 | 0.8991 | 0.6274 | 0.8991 | 0.9482 |
|
| 111 |
+
| No log | 1.7647 | 120 | 0.8622 | 0.5706 | 0.8622 | 0.9285 |
|
| 112 |
+
| No log | 1.7941 | 122 | 0.8541 | 0.5115 | 0.8541 | 0.9242 |
|
| 113 |
+
| No log | 1.8235 | 124 | 0.8595 | 0.4575 | 0.8595 | 0.9271 |
|
| 114 |
+
| No log | 1.8529 | 126 | 0.8462 | 0.5431 | 0.8462 | 0.9199 |
|
| 115 |
+
| No log | 1.8824 | 128 | 0.8500 | 0.4489 | 0.8500 | 0.9220 |
|
| 116 |
+
| No log | 1.9118 | 130 | 0.8485 | 0.4961 | 0.8485 | 0.9211 |
|
| 117 |
+
| No log | 1.9412 | 132 | 1.0201 | 0.4323 | 1.0201 | 1.0100 |
|
| 118 |
+
| No log | 1.9706 | 134 | 0.9571 | 0.4689 | 0.9571 | 0.9783 |
|
| 119 |
+
| No log | 2.0 | 136 | 0.8864 | 0.4878 | 0.8864 | 0.9415 |
|
| 120 |
+
| No log | 2.0294 | 138 | 0.7805 | 0.6107 | 0.7805 | 0.8834 |
|
| 121 |
+
| No log | 2.0588 | 140 | 0.9094 | 0.5636 | 0.9094 | 0.9536 |
|
| 122 |
+
| No log | 2.0882 | 142 | 1.0143 | 0.4545 | 1.0143 | 1.0071 |
|
| 123 |
+
| No log | 2.1176 | 144 | 0.8407 | 0.5892 | 0.8407 | 0.9169 |
|
| 124 |
+
| No log | 2.1471 | 146 | 0.7992 | 0.6260 | 0.7992 | 0.8940 |
|
| 125 |
+
| No log | 2.1765 | 148 | 0.9018 | 0.5339 | 0.9018 | 0.9496 |
|
| 126 |
+
| No log | 2.2059 | 150 | 0.8918 | 0.4912 | 0.8918 | 0.9444 |
|
| 127 |
+
| No log | 2.2353 | 152 | 0.8254 | 0.5027 | 0.8254 | 0.9085 |
|
| 128 |
+
| No log | 2.2647 | 154 | 0.9096 | 0.4130 | 0.9096 | 0.9537 |
|
| 129 |
+
| No log | 2.2941 | 156 | 0.8505 | 0.4934 | 0.8505 | 0.9222 |
|
| 130 |
+
| No log | 2.3235 | 158 | 0.8094 | 0.5055 | 0.8094 | 0.8996 |
|
| 131 |
+
| No log | 2.3529 | 160 | 0.8962 | 0.4613 | 0.8962 | 0.9467 |
|
| 132 |
+
| No log | 2.3824 | 162 | 0.8210 | 0.4902 | 0.8210 | 0.9061 |
|
| 133 |
+
| No log | 2.4118 | 164 | 0.7910 | 0.5327 | 0.7910 | 0.8894 |
|
| 134 |
+
| No log | 2.4412 | 166 | 0.8331 | 0.5675 | 0.8331 | 0.9127 |
|
| 135 |
+
| No log | 2.4706 | 168 | 1.0218 | 0.5329 | 1.0218 | 1.0108 |
|
| 136 |
+
| No log | 2.5 | 170 | 0.8592 | 0.6046 | 0.8592 | 0.9269 |
|
| 137 |
+
| No log | 2.5294 | 172 | 0.7707 | 0.5902 | 0.7707 | 0.8779 |
|
| 138 |
+
| No log | 2.5588 | 174 | 0.9748 | 0.5495 | 0.9748 | 0.9873 |
|
| 139 |
+
| No log | 2.5882 | 176 | 0.9230 | 0.5636 | 0.9230 | 0.9607 |
|
| 140 |
+
| No log | 2.6176 | 178 | 0.7726 | 0.5462 | 0.7726 | 0.8790 |
|
| 141 |
+
| No log | 2.6471 | 180 | 0.8444 | 0.4962 | 0.8444 | 0.9189 |
|
| 142 |
+
| No log | 2.6765 | 182 | 0.9965 | 0.4909 | 0.9965 | 0.9983 |
|
| 143 |
+
| No log | 2.7059 | 184 | 0.8935 | 0.5075 | 0.8935 | 0.9453 |
|
| 144 |
+
| No log | 2.7353 | 186 | 0.7656 | 0.5931 | 0.7656 | 0.8750 |
|
| 145 |
+
| No log | 2.7647 | 188 | 0.9214 | 0.5958 | 0.9214 | 0.9599 |
|
| 146 |
+
| No log | 2.7941 | 190 | 0.9385 | 0.5932 | 0.9385 | 0.9688 |
|
| 147 |
+
| No log | 2.8235 | 192 | 0.9247 | 0.5958 | 0.9247 | 0.9616 |
|
| 148 |
+
| No log | 2.8529 | 194 | 0.7918 | 0.5152 | 0.7918 | 0.8898 |
|
| 149 |
+
| No log | 2.8824 | 196 | 0.7826 | 0.4866 | 0.7826 | 0.8846 |
|
| 150 |
+
| No log | 2.9118 | 198 | 0.7712 | 0.5807 | 0.7712 | 0.8782 |
|
| 151 |
+
| No log | 2.9412 | 200 | 0.8091 | 0.6545 | 0.8091 | 0.8995 |
|
| 152 |
+
| No log | 2.9706 | 202 | 0.9155 | 0.5992 | 0.9155 | 0.9568 |
|
| 153 |
+
| No log | 3.0 | 204 | 0.8466 | 0.6888 | 0.8466 | 0.9201 |
|
| 154 |
+
| No log | 3.0294 | 206 | 0.7243 | 0.5426 | 0.7243 | 0.8510 |
|
| 155 |
+
| No log | 3.0588 | 208 | 0.7236 | 0.5684 | 0.7236 | 0.8506 |
|
| 156 |
+
| No log | 3.0882 | 210 | 0.7441 | 0.5399 | 0.7441 | 0.8626 |
|
| 157 |
+
| No log | 3.1176 | 212 | 0.7693 | 0.4763 | 0.7693 | 0.8771 |
|
| 158 |
+
| No log | 3.1471 | 214 | 0.7425 | 0.6311 | 0.7425 | 0.8617 |
|
| 159 |
+
| No log | 3.1765 | 216 | 0.8438 | 0.5683 | 0.8438 | 0.9186 |
|
| 160 |
+
| No log | 3.2059 | 218 | 1.0061 | 0.5389 | 1.0061 | 1.0030 |
|
| 161 |
+
| No log | 3.2353 | 220 | 0.9324 | 0.5393 | 0.9324 | 0.9656 |
|
| 162 |
+
| No log | 3.2647 | 222 | 0.7587 | 0.6287 | 0.7587 | 0.8711 |
|
| 163 |
+
| No log | 3.2941 | 224 | 0.7498 | 0.5437 | 0.7498 | 0.8659 |
|
| 164 |
+
| No log | 3.3235 | 226 | 0.7485 | 0.5569 | 0.7485 | 0.8651 |
|
| 165 |
+
| No log | 3.3529 | 228 | 0.7407 | 0.6005 | 0.7407 | 0.8607 |
|
| 166 |
+
| No log | 3.3824 | 230 | 0.7579 | 0.6290 | 0.7579 | 0.8706 |
|
| 167 |
+
| No log | 3.4118 | 232 | 0.7899 | 0.6258 | 0.7899 | 0.8887 |
|
| 168 |
+
| No log | 3.4412 | 234 | 0.9281 | 0.5913 | 0.9281 | 0.9634 |
|
| 169 |
+
| No log | 3.4706 | 236 | 0.9278 | 0.5766 | 0.9278 | 0.9632 |
|
| 170 |
+
| No log | 3.5 | 238 | 0.8239 | 0.5981 | 0.8239 | 0.9077 |
|
| 171 |
+
| No log | 3.5294 | 240 | 0.7720 | 0.4980 | 0.7720 | 0.8786 |
|
| 172 |
+
| No log | 3.5588 | 242 | 0.8022 | 0.5483 | 0.8022 | 0.8957 |
|
| 173 |
+
| No log | 3.5882 | 244 | 0.7893 | 0.5208 | 0.7893 | 0.8884 |
|
| 174 |
+
| No log | 3.6176 | 246 | 0.8578 | 0.5779 | 0.8578 | 0.9262 |
|
| 175 |
+
| No log | 3.6471 | 248 | 0.9232 | 0.5515 | 0.9232 | 0.9608 |
|
| 176 |
+
| No log | 3.6765 | 250 | 0.8570 | 0.5194 | 0.8570 | 0.9257 |
|
| 177 |
+
| No log | 3.7059 | 252 | 0.7862 | 0.5746 | 0.7862 | 0.8867 |
|
| 178 |
+
| No log | 3.7353 | 254 | 0.7486 | 0.5915 | 0.7486 | 0.8652 |
|
| 179 |
+
| No log | 3.7647 | 256 | 0.7399 | 0.5536 | 0.7399 | 0.8602 |
|
| 180 |
+
| No log | 3.7941 | 258 | 0.7401 | 0.5868 | 0.7401 | 0.8603 |
|
| 181 |
+
| No log | 3.8235 | 260 | 0.7397 | 0.5387 | 0.7397 | 0.8601 |
|
| 182 |
+
| No log | 3.8529 | 262 | 0.7424 | 0.5854 | 0.7424 | 0.8616 |
|
| 183 |
+
| No log | 3.8824 | 264 | 0.7432 | 0.5946 | 0.7432 | 0.8621 |
|
| 184 |
+
| No log | 3.9118 | 266 | 0.7374 | 0.5902 | 0.7374 | 0.8587 |
|
| 185 |
+
| No log | 3.9412 | 268 | 0.7319 | 0.5633 | 0.7319 | 0.8555 |
|
| 186 |
+
| No log | 3.9706 | 270 | 0.7177 | 0.5855 | 0.7177 | 0.8472 |
|
| 187 |
+
| No log | 4.0 | 272 | 0.7168 | 0.5794 | 0.7168 | 0.8467 |
|
| 188 |
+
| No log | 4.0294 | 274 | 0.7685 | 0.5678 | 0.7685 | 0.8766 |
|
| 189 |
+
| No log | 4.0588 | 276 | 0.7213 | 0.5458 | 0.7213 | 0.8493 |
|
| 190 |
+
| No log | 4.0882 | 278 | 0.7483 | 0.6131 | 0.7483 | 0.8650 |
|
| 191 |
+
| No log | 4.1176 | 280 | 0.7964 | 0.5541 | 0.7964 | 0.8924 |
|
| 192 |
+
| No log | 4.1471 | 282 | 0.7203 | 0.6528 | 0.7203 | 0.8487 |
|
| 193 |
+
| No log | 4.1765 | 284 | 0.7116 | 0.5895 | 0.7116 | 0.8436 |
|
| 194 |
+
| No log | 4.2059 | 286 | 0.7989 | 0.5050 | 0.7989 | 0.8938 |
|
| 195 |
+
| No log | 4.2353 | 288 | 0.7312 | 0.5593 | 0.7312 | 0.8551 |
|
| 196 |
+
| No log | 4.2647 | 290 | 0.6792 | 0.6311 | 0.6792 | 0.8241 |
|
| 197 |
+
| No log | 4.2941 | 292 | 0.7163 | 0.6097 | 0.7163 | 0.8464 |
|
| 198 |
+
| No log | 4.3235 | 294 | 0.8063 | 0.5380 | 0.8063 | 0.8979 |
|
| 199 |
+
| No log | 4.3529 | 296 | 0.8074 | 0.4998 | 0.8074 | 0.8985 |
|
| 200 |
+
| No log | 4.3824 | 298 | 0.7678 | 0.5774 | 0.7678 | 0.8763 |
|
| 201 |
+
| No log | 4.4118 | 300 | 0.7631 | 0.5150 | 0.7631 | 0.8735 |
|
| 202 |
+
| No log | 4.4412 | 302 | 0.7851 | 0.4915 | 0.7851 | 0.8860 |
|
| 203 |
+
| No log | 4.4706 | 304 | 0.7214 | 0.5253 | 0.7214 | 0.8494 |
|
| 204 |
+
| No log | 4.5 | 306 | 0.7950 | 0.6305 | 0.7950 | 0.8916 |
|
| 205 |
+
| No log | 4.5294 | 308 | 0.9553 | 0.5818 | 0.9553 | 0.9774 |
|
| 206 |
+
| No log | 4.5588 | 310 | 0.9298 | 0.5938 | 0.9298 | 0.9643 |
|
| 207 |
+
| No log | 4.5882 | 312 | 0.7862 | 0.5922 | 0.7862 | 0.8867 |
|
| 208 |
+
| No log | 4.6176 | 314 | 0.7464 | 0.5451 | 0.7464 | 0.8640 |
|
| 209 |
+
| No log | 4.6471 | 316 | 0.8069 | 0.4598 | 0.8069 | 0.8983 |
|
| 210 |
+
| No log | 4.6765 | 318 | 0.8243 | 0.4606 | 0.8243 | 0.9079 |
|
| 211 |
+
| No log | 4.7059 | 320 | 0.7771 | 0.4872 | 0.7771 | 0.8815 |
|
| 212 |
+
| No log | 4.7353 | 322 | 0.7784 | 0.6011 | 0.7784 | 0.8823 |
|
| 213 |
+
| No log | 4.7647 | 324 | 0.8611 | 0.5892 | 0.8611 | 0.9279 |
|
| 214 |
+
| No log | 4.7941 | 326 | 0.8560 | 0.6026 | 0.8560 | 0.9252 |
|
| 215 |
+
| No log | 4.8235 | 328 | 0.7973 | 0.5884 | 0.7973 | 0.8929 |
|
| 216 |
+
| No log | 4.8529 | 330 | 0.8530 | 0.4225 | 0.8530 | 0.9236 |
|
| 217 |
+
| No log | 4.8824 | 332 | 1.0558 | 0.4136 | 1.0558 | 1.0275 |
|
| 218 |
+
| No log | 4.9118 | 334 | 1.0903 | 0.4019 | 1.0903 | 1.0442 |
|
| 219 |
+
| No log | 4.9412 | 336 | 0.9387 | 0.4532 | 0.9387 | 0.9689 |
|
| 220 |
+
| No log | 4.9706 | 338 | 0.8377 | 0.4555 | 0.8377 | 0.9153 |
|
| 221 |
+
| No log | 5.0 | 340 | 0.8419 | 0.5311 | 0.8419 | 0.9175 |
|
| 222 |
+
| No log | 5.0294 | 342 | 0.8844 | 0.5313 | 0.8844 | 0.9404 |
|
| 223 |
+
| No log | 5.0588 | 344 | 0.8525 | 0.5601 | 0.8525 | 0.9233 |
|
| 224 |
+
| No log | 5.0882 | 346 | 0.7672 | 0.5815 | 0.7672 | 0.8759 |
|
| 225 |
+
| No log | 5.1176 | 348 | 0.7608 | 0.5407 | 0.7608 | 0.8722 |
|
| 226 |
+
| No log | 5.1471 | 350 | 0.7707 | 0.6049 | 0.7707 | 0.8779 |
|
| 227 |
+
| No log | 5.1765 | 352 | 0.8124 | 0.6309 | 0.8124 | 0.9013 |
|
| 228 |
+
| No log | 5.2059 | 354 | 0.8227 | 0.6190 | 0.8227 | 0.9070 |
|
| 229 |
+
| No log | 5.2353 | 356 | 0.8126 | 0.5743 | 0.8126 | 0.9014 |
|
| 230 |
+
| No log | 5.2647 | 358 | 0.8342 | 0.5026 | 0.8342 | 0.9133 |
|
| 231 |
+
| No log | 5.2941 | 360 | 0.8490 | 0.5197 | 0.8490 | 0.9214 |
|
| 232 |
+
| No log | 5.3235 | 362 | 0.8471 | 0.5262 | 0.8471 | 0.9204 |
|
| 233 |
+
| No log | 5.3529 | 364 | 0.8255 | 0.5262 | 0.8255 | 0.9085 |
|
| 234 |
+
| No log | 5.3824 | 366 | 0.7842 | 0.5540 | 0.7842 | 0.8856 |
|
| 235 |
+
| No log | 5.4118 | 368 | 0.7597 | 0.6107 | 0.7597 | 0.8716 |
|
| 236 |
+
| No log | 5.4412 | 370 | 0.7605 | 0.6790 | 0.7605 | 0.8720 |
|
| 237 |
+
| No log | 5.4706 | 372 | 0.7384 | 0.6032 | 0.7384 | 0.8593 |
|
| 238 |
+
| No log | 5.5 | 374 | 0.7557 | 0.6220 | 0.7557 | 0.8693 |
|
| 239 |
+
| No log | 5.5294 | 376 | 0.7994 | 0.5596 | 0.7994 | 0.8941 |
|
| 240 |
+
| No log | 5.5588 | 378 | 0.8279 | 0.5248 | 0.8279 | 0.9099 |
|
| 241 |
+
| No log | 5.5882 | 380 | 0.8225 | 0.4280 | 0.8225 | 0.9069 |
|
| 242 |
+
| No log | 5.6176 | 382 | 0.8218 | 0.5163 | 0.8218 | 0.9065 |
|
| 243 |
+
| No log | 5.6471 | 384 | 0.8054 | 0.5163 | 0.8054 | 0.8974 |
|
| 244 |
+
| No log | 5.6765 | 386 | 0.7692 | 0.5028 | 0.7692 | 0.8770 |
|
| 245 |
+
| No log | 5.7059 | 388 | 0.7786 | 0.5791 | 0.7786 | 0.8824 |
|
| 246 |
+
| No log | 5.7353 | 390 | 0.7313 | 0.5815 | 0.7313 | 0.8552 |
|
| 247 |
+
| No log | 5.7647 | 392 | 0.6783 | 0.5835 | 0.6783 | 0.8236 |
|
| 248 |
+
| No log | 5.7941 | 394 | 0.7483 | 0.5482 | 0.7483 | 0.8650 |
|
| 249 |
+
| No log | 5.8235 | 396 | 0.7919 | 0.5275 | 0.7919 | 0.8899 |
|
| 250 |
+
| No log | 5.8529 | 398 | 0.7487 | 0.5551 | 0.7487 | 0.8653 |
|
| 251 |
+
| No log | 5.8824 | 400 | 0.6572 | 0.6280 | 0.6572 | 0.8107 |
|
| 252 |
+
| No log | 5.9118 | 402 | 0.7783 | 0.6269 | 0.7783 | 0.8822 |
|
| 253 |
+
| No log | 5.9412 | 404 | 0.9111 | 0.5488 | 0.9111 | 0.9545 |
|
| 254 |
+
| No log | 5.9706 | 406 | 0.8429 | 0.5553 | 0.8429 | 0.9181 |
|
| 255 |
+
| No log | 6.0 | 408 | 0.7547 | 0.5270 | 0.7547 | 0.8687 |
|
| 256 |
+
| No log | 6.0294 | 410 | 0.7467 | 0.5606 | 0.7467 | 0.8641 |
|
| 257 |
+
| No log | 6.0588 | 412 | 0.7560 | 0.5125 | 0.7560 | 0.8695 |
|
| 258 |
+
| No log | 6.0882 | 414 | 0.7453 | 0.5327 | 0.7453 | 0.8633 |
|
| 259 |
+
| No log | 6.1176 | 416 | 0.7298 | 0.6041 | 0.7298 | 0.8543 |
|
| 260 |
+
| No log | 6.1471 | 418 | 0.7544 | 0.5902 | 0.7544 | 0.8685 |
|
| 261 |
+
| No log | 6.1765 | 420 | 0.7866 | 0.6148 | 0.7866 | 0.8869 |
|
| 262 |
+
| No log | 6.2059 | 422 | 0.7648 | 0.5655 | 0.7648 | 0.8745 |
|
| 263 |
+
| No log | 6.2353 | 424 | 0.7857 | 0.5383 | 0.7857 | 0.8864 |
|
| 264 |
+
| No log | 6.2647 | 426 | 0.8158 | 0.5387 | 0.8158 | 0.9032 |
|
| 265 |
+
| No log | 6.2941 | 428 | 0.7813 | 0.5352 | 0.7813 | 0.8839 |
|
| 266 |
+
| No log | 6.3235 | 430 | 0.7937 | 0.5322 | 0.7937 | 0.8909 |
|
| 267 |
+
| No log | 6.3529 | 432 | 0.8789 | 0.5301 | 0.8789 | 0.9375 |
|
| 268 |
+
| No log | 6.3824 | 434 | 1.0456 | 0.4906 | 1.0456 | 1.0225 |
|
| 269 |
+
| No log | 6.4118 | 436 | 1.0569 | 0.4894 | 1.0569 | 1.0281 |
|
| 270 |
+
| No log | 6.4412 | 438 | 0.9433 | 0.4857 | 0.9433 | 0.9712 |
|
| 271 |
+
| No log | 6.4706 | 440 | 0.8083 | 0.5586 | 0.8083 | 0.8990 |
|
| 272 |
+
| No log | 6.5 | 442 | 0.7700 | 0.5547 | 0.7700 | 0.8775 |
|
| 273 |
+
| No log | 6.5294 | 444 | 0.7484 | 0.5501 | 0.7484 | 0.8651 |
|
| 274 |
+
| No log | 6.5588 | 446 | 0.7197 | 0.5835 | 0.7197 | 0.8483 |
|
| 275 |
+
| No log | 6.5882 | 448 | 0.7084 | 0.6088 | 0.7084 | 0.8416 |
|
| 276 |
+
| No log | 6.6176 | 450 | 0.7104 | 0.6215 | 0.7104 | 0.8429 |
|
| 277 |
+
| No log | 6.6471 | 452 | 0.7082 | 0.6215 | 0.7082 | 0.8415 |
|
| 278 |
+
| No log | 6.6765 | 454 | 0.6855 | 0.6324 | 0.6855 | 0.8280 |
|
| 279 |
+
| No log | 6.7059 | 456 | 0.6944 | 0.6190 | 0.6944 | 0.8333 |
|
| 280 |
+
| No log | 6.7353 | 458 | 0.7052 | 0.6283 | 0.7052 | 0.8397 |
|
| 281 |
+
| No log | 6.7647 | 460 | 0.7535 | 0.6208 | 0.7535 | 0.8680 |
|
| 282 |
+
| No log | 6.7941 | 462 | 0.7892 | 0.6208 | 0.7892 | 0.8884 |
|
| 283 |
+
| No log | 6.8235 | 464 | 0.7727 | 0.5936 | 0.7727 | 0.8790 |
|
| 284 |
+
| No log | 6.8529 | 466 | 0.7631 | 0.5785 | 0.7631 | 0.8736 |
|
| 285 |
+
| No log | 6.8824 | 468 | 0.7334 | 0.5059 | 0.7334 | 0.8564 |
|
| 286 |
+
| No log | 6.9118 | 470 | 0.7159 | 0.5059 | 0.7159 | 0.8461 |
|
| 287 |
+
| No log | 6.9412 | 472 | 0.6929 | 0.6097 | 0.6929 | 0.8324 |
|
| 288 |
+
| No log | 6.9706 | 474 | 0.6928 | 0.6163 | 0.6928 | 0.8323 |
|
| 289 |
+
| No log | 7.0 | 476 | 0.6819 | 0.6377 | 0.6819 | 0.8258 |
|
| 290 |
+
| No log | 7.0294 | 478 | 0.6790 | 0.6377 | 0.6790 | 0.8240 |
|
| 291 |
+
| No log | 7.0588 | 480 | 0.6701 | 0.6450 | 0.6701 | 0.8186 |
|
| 292 |
+
| No log | 7.0882 | 482 | 0.6813 | 0.6088 | 0.6813 | 0.8254 |
|
| 293 |
+
| No log | 7.1176 | 484 | 0.7703 | 0.5876 | 0.7703 | 0.8777 |
|
| 294 |
+
| No log | 7.1471 | 486 | 0.8101 | 0.5637 | 0.8101 | 0.9000 |
|
| 295 |
+
| No log | 7.1765 | 488 | 0.8075 | 0.5490 | 0.8075 | 0.8986 |
|
| 296 |
+
| No log | 7.2059 | 490 | 0.7309 | 0.5636 | 0.7309 | 0.8549 |
|
| 297 |
+
| No log | 7.2353 | 492 | 0.6960 | 0.5678 | 0.6960 | 0.8343 |
|
| 298 |
+
| No log | 7.2647 | 494 | 0.7001 | 0.5483 | 0.7001 | 0.8367 |
|
| 299 |
+
| No log | 7.2941 | 496 | 0.7020 | 0.5701 | 0.7020 | 0.8378 |
|
| 300 |
+
| No log | 7.3235 | 498 | 0.7053 | 0.6154 | 0.7053 | 0.8398 |
|
| 301 |
+
| 0.3011 | 7.3529 | 500 | 0.7026 | 0.6455 | 0.7026 | 0.8382 |
|
| 302 |
+
| 0.3011 | 7.3824 | 502 | 0.7025 | 0.5791 | 0.7025 | 0.8382 |
|
| 303 |
+
| 0.3011 | 7.4118 | 504 | 0.7139 | 0.5255 | 0.7139 | 0.8449 |
|
| 304 |
+
| 0.3011 | 7.4412 | 506 | 0.7208 | 0.5740 | 0.7208 | 0.8490 |
|
| 305 |
+
| 0.3011 | 7.4706 | 508 | 0.7271 | 0.5740 | 0.7271 | 0.8527 |
|
| 306 |
+
| 0.3011 | 7.5 | 510 | 0.7214 | 0.5538 | 0.7214 | 0.8494 |
|
| 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 sha256:3ae2b7a050f0560a094b377becfa0eeb6317e2771f7fee9eb0b9f4ea8f2443ae
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a4090170547a3590797bf99efe9656666cfb0244045075b34cd8ab06f627eef
|
| 3 |
+
size 5304
|