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_k15_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_k15_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: 0.6954
|
| 19 |
+
- Qwk: 0.4408
|
| 20 |
+
- Mse: 0.6954
|
| 21 |
+
- Rmse: 0.8339
|
| 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 | 0.0263 | 2 | 2.5671 | -0.1213 | 2.5671 | 1.6022 |
|
| 53 |
+
| No log | 0.0526 | 4 | 1.1395 | 0.0315 | 1.1395 | 1.0675 |
|
| 54 |
+
| No log | 0.0789 | 6 | 1.3465 | -0.2263 | 1.3465 | 1.1604 |
|
| 55 |
+
| No log | 0.1053 | 8 | 1.3369 | -0.1812 | 1.3369 | 1.1562 |
|
| 56 |
+
| No log | 0.1316 | 10 | 1.2033 | 0.0040 | 1.2033 | 1.0969 |
|
| 57 |
+
| No log | 0.1579 | 12 | 1.1342 | -0.0216 | 1.1342 | 1.0650 |
|
| 58 |
+
| No log | 0.1842 | 14 | 1.1047 | -0.0735 | 1.1047 | 1.0511 |
|
| 59 |
+
| No log | 0.2105 | 16 | 0.9725 | 0.0927 | 0.9725 | 0.9861 |
|
| 60 |
+
| No log | 0.2368 | 18 | 0.8668 | 0.0757 | 0.8668 | 0.9310 |
|
| 61 |
+
| No log | 0.2632 | 20 | 0.8396 | 0.0717 | 0.8396 | 0.9163 |
|
| 62 |
+
| No log | 0.2895 | 22 | 0.8556 | 0.0608 | 0.8556 | 0.9250 |
|
| 63 |
+
| No log | 0.3158 | 24 | 0.8465 | 0.0608 | 0.8465 | 0.9200 |
|
| 64 |
+
| No log | 0.3421 | 26 | 0.8385 | 0.0966 | 0.8385 | 0.9157 |
|
| 65 |
+
| No log | 0.3684 | 28 | 0.8339 | 0.1846 | 0.8339 | 0.9132 |
|
| 66 |
+
| No log | 0.3947 | 30 | 0.8907 | 0.0455 | 0.8907 | 0.9438 |
|
| 67 |
+
| No log | 0.4211 | 32 | 0.9666 | 0.0875 | 0.9666 | 0.9831 |
|
| 68 |
+
| No log | 0.4474 | 34 | 1.0095 | 0.0890 | 1.0095 | 1.0048 |
|
| 69 |
+
| No log | 0.4737 | 36 | 1.0918 | 0.0569 | 1.0918 | 1.0449 |
|
| 70 |
+
| No log | 0.5 | 38 | 1.0740 | 0.0893 | 1.0740 | 1.0363 |
|
| 71 |
+
| No log | 0.5263 | 40 | 0.9803 | 0.0842 | 0.9803 | 0.9901 |
|
| 72 |
+
| No log | 0.5526 | 42 | 1.0192 | 0.0847 | 1.0192 | 1.0096 |
|
| 73 |
+
| No log | 0.5789 | 44 | 0.9869 | 0.0847 | 0.9869 | 0.9934 |
|
| 74 |
+
| No log | 0.6053 | 46 | 0.9619 | 0.0451 | 0.9619 | 0.9808 |
|
| 75 |
+
| No log | 0.6316 | 48 | 0.9246 | 0.1263 | 0.9246 | 0.9616 |
|
| 76 |
+
| No log | 0.6579 | 50 | 0.8594 | 0.1829 | 0.8594 | 0.9270 |
|
| 77 |
+
| No log | 0.6842 | 52 | 0.9096 | 0.1706 | 0.9096 | 0.9537 |
|
| 78 |
+
| No log | 0.7105 | 54 | 0.9078 | 0.2574 | 0.9078 | 0.9528 |
|
| 79 |
+
| No log | 0.7368 | 56 | 0.8922 | 0.2244 | 0.8922 | 0.9446 |
|
| 80 |
+
| No log | 0.7632 | 58 | 0.8210 | 0.2353 | 0.8210 | 0.9061 |
|
| 81 |
+
| No log | 0.7895 | 60 | 0.7663 | 0.2205 | 0.7663 | 0.8754 |
|
| 82 |
+
| No log | 0.8158 | 62 | 0.8141 | 0.1714 | 0.8141 | 0.9023 |
|
| 83 |
+
| No log | 0.8421 | 64 | 0.8707 | 0.0952 | 0.8707 | 0.9331 |
|
| 84 |
+
| No log | 0.8684 | 66 | 0.8103 | 0.0944 | 0.8103 | 0.9002 |
|
| 85 |
+
| No log | 0.8947 | 68 | 0.7461 | 0.1903 | 0.7461 | 0.8638 |
|
| 86 |
+
| No log | 0.9211 | 70 | 0.7387 | 0.1903 | 0.7387 | 0.8595 |
|
| 87 |
+
| No log | 0.9474 | 72 | 0.7652 | 0.1263 | 0.7652 | 0.8748 |
|
| 88 |
+
| No log | 0.9737 | 74 | 0.8685 | 0.2008 | 0.8685 | 0.9320 |
|
| 89 |
+
| No log | 1.0 | 76 | 0.9680 | 0.1609 | 0.9680 | 0.9839 |
|
| 90 |
+
| No log | 1.0263 | 78 | 0.9767 | 0.1609 | 0.9767 | 0.9883 |
|
| 91 |
+
| No log | 1.0526 | 80 | 0.8270 | 0.2031 | 0.8270 | 0.9094 |
|
| 92 |
+
| No log | 1.0789 | 82 | 0.7137 | 0.2513 | 0.7137 | 0.8448 |
|
| 93 |
+
| No log | 1.1053 | 84 | 0.7249 | 0.2516 | 0.7249 | 0.8514 |
|
| 94 |
+
| No log | 1.1316 | 86 | 0.7768 | 0.2857 | 0.7768 | 0.8814 |
|
| 95 |
+
| No log | 1.1579 | 88 | 0.8737 | 0.2154 | 0.8737 | 0.9347 |
|
| 96 |
+
| No log | 1.1842 | 90 | 0.7746 | 0.3707 | 0.7746 | 0.8801 |
|
| 97 |
+
| No log | 1.2105 | 92 | 0.7651 | 0.3189 | 0.7651 | 0.8747 |
|
| 98 |
+
| No log | 1.2368 | 94 | 0.7128 | 0.1854 | 0.7128 | 0.8443 |
|
| 99 |
+
| No log | 1.2632 | 96 | 0.6914 | 0.1834 | 0.6914 | 0.8315 |
|
| 100 |
+
| No log | 1.2895 | 98 | 0.6649 | 0.3546 | 0.6649 | 0.8154 |
|
| 101 |
+
| No log | 1.3158 | 100 | 0.6625 | 0.3839 | 0.6625 | 0.8139 |
|
| 102 |
+
| No log | 1.3421 | 102 | 0.6503 | 0.3243 | 0.6503 | 0.8064 |
|
| 103 |
+
| No log | 1.3684 | 104 | 0.6354 | 0.3243 | 0.6354 | 0.7971 |
|
| 104 |
+
| No log | 1.3947 | 106 | 0.6261 | 0.3575 | 0.6261 | 0.7913 |
|
| 105 |
+
| No log | 1.4211 | 108 | 0.6746 | 0.3470 | 0.6746 | 0.8213 |
|
| 106 |
+
| No log | 1.4474 | 110 | 0.8111 | 0.3239 | 0.8111 | 0.9006 |
|
| 107 |
+
| No log | 1.4737 | 112 | 0.9614 | 0.28 | 0.9614 | 0.9805 |
|
| 108 |
+
| No log | 1.5 | 114 | 1.0007 | 0.2775 | 1.0007 | 1.0004 |
|
| 109 |
+
| No log | 1.5263 | 116 | 0.8019 | 0.2476 | 0.8019 | 0.8955 |
|
| 110 |
+
| No log | 1.5526 | 118 | 0.7024 | 0.2085 | 0.7024 | 0.8381 |
|
| 111 |
+
| No log | 1.5789 | 120 | 0.6935 | 0.3253 | 0.6935 | 0.8328 |
|
| 112 |
+
| No log | 1.6053 | 122 | 0.7211 | 0.3471 | 0.7211 | 0.8492 |
|
| 113 |
+
| No log | 1.6316 | 124 | 0.6977 | 0.3341 | 0.6977 | 0.8353 |
|
| 114 |
+
| No log | 1.6579 | 126 | 0.6999 | 0.1624 | 0.6999 | 0.8366 |
|
| 115 |
+
| No log | 1.6842 | 128 | 0.7116 | 0.1850 | 0.7116 | 0.8436 |
|
| 116 |
+
| No log | 1.7105 | 130 | 0.7235 | 0.2334 | 0.7235 | 0.8506 |
|
| 117 |
+
| No log | 1.7368 | 132 | 0.8027 | 0.1591 | 0.8027 | 0.8959 |
|
| 118 |
+
| No log | 1.7632 | 134 | 0.8006 | 0.2224 | 0.8006 | 0.8948 |
|
| 119 |
+
| No log | 1.7895 | 136 | 0.7517 | 0.3043 | 0.7517 | 0.8670 |
|
| 120 |
+
| No log | 1.8158 | 138 | 0.7723 | 0.3892 | 0.7723 | 0.8788 |
|
| 121 |
+
| No log | 1.8421 | 140 | 0.6700 | 0.4697 | 0.6700 | 0.8185 |
|
| 122 |
+
| No log | 1.8684 | 142 | 0.6806 | 0.4767 | 0.6806 | 0.8250 |
|
| 123 |
+
| No log | 1.8947 | 144 | 0.6453 | 0.4941 | 0.6453 | 0.8033 |
|
| 124 |
+
| No log | 1.9211 | 146 | 0.6287 | 0.5190 | 0.6287 | 0.7929 |
|
| 125 |
+
| No log | 1.9474 | 148 | 0.6211 | 0.5640 | 0.6211 | 0.7881 |
|
| 126 |
+
| No log | 1.9737 | 150 | 0.7410 | 0.5065 | 0.7410 | 0.8608 |
|
| 127 |
+
| No log | 2.0 | 152 | 0.7809 | 0.4873 | 0.7810 | 0.8837 |
|
| 128 |
+
| No log | 2.0263 | 154 | 0.6344 | 0.5476 | 0.6344 | 0.7965 |
|
| 129 |
+
| No log | 2.0526 | 156 | 0.6044 | 0.5725 | 0.6044 | 0.7774 |
|
| 130 |
+
| No log | 2.0789 | 158 | 0.5880 | 0.4874 | 0.5880 | 0.7668 |
|
| 131 |
+
| No log | 2.1053 | 160 | 0.5996 | 0.4816 | 0.5996 | 0.7743 |
|
| 132 |
+
| No log | 2.1316 | 162 | 0.6079 | 0.4659 | 0.6079 | 0.7797 |
|
| 133 |
+
| No log | 2.1579 | 164 | 0.6128 | 0.4659 | 0.6128 | 0.7828 |
|
| 134 |
+
| No log | 2.1842 | 166 | 0.6019 | 0.4091 | 0.6019 | 0.7758 |
|
| 135 |
+
| No log | 2.2105 | 168 | 0.5942 | 0.5213 | 0.5942 | 0.7709 |
|
| 136 |
+
| No log | 2.2368 | 170 | 0.6013 | 0.4700 | 0.6013 | 0.7755 |
|
| 137 |
+
| No log | 2.2632 | 172 | 0.6653 | 0.4681 | 0.6653 | 0.8157 |
|
| 138 |
+
| No log | 2.2895 | 174 | 0.6501 | 0.5206 | 0.6501 | 0.8063 |
|
| 139 |
+
| No log | 2.3158 | 176 | 0.6938 | 0.5063 | 0.6938 | 0.8329 |
|
| 140 |
+
| No log | 2.3421 | 178 | 0.7996 | 0.4632 | 0.7996 | 0.8942 |
|
| 141 |
+
| No log | 2.3684 | 180 | 0.8962 | 0.3700 | 0.8962 | 0.9467 |
|
| 142 |
+
| No log | 2.3947 | 182 | 1.0194 | 0.3542 | 1.0194 | 1.0097 |
|
| 143 |
+
| No log | 2.4211 | 184 | 0.9195 | 0.3379 | 0.9195 | 0.9589 |
|
| 144 |
+
| No log | 2.4474 | 186 | 0.8084 | 0.3571 | 0.8084 | 0.8991 |
|
| 145 |
+
| No log | 2.4737 | 188 | 0.7996 | 0.2634 | 0.7996 | 0.8942 |
|
| 146 |
+
| No log | 2.5 | 190 | 0.7837 | 0.2634 | 0.7837 | 0.8853 |
|
| 147 |
+
| No log | 2.5263 | 192 | 0.7875 | 0.3162 | 0.7875 | 0.8874 |
|
| 148 |
+
| No log | 2.5526 | 194 | 1.0732 | 0.3183 | 1.0732 | 1.0360 |
|
| 149 |
+
| No log | 2.5789 | 196 | 1.2639 | 0.1864 | 1.2639 | 1.1242 |
|
| 150 |
+
| No log | 2.6053 | 198 | 1.0834 | 0.2802 | 1.0834 | 1.0408 |
|
| 151 |
+
| No log | 2.6316 | 200 | 0.8092 | 0.3105 | 0.8092 | 0.8996 |
|
| 152 |
+
| No log | 2.6579 | 202 | 0.7099 | 0.2135 | 0.7099 | 0.8425 |
|
| 153 |
+
| No log | 2.6842 | 204 | 0.7114 | 0.2389 | 0.7114 | 0.8434 |
|
| 154 |
+
| No log | 2.7105 | 206 | 0.6976 | 0.1539 | 0.6976 | 0.8352 |
|
| 155 |
+
| No log | 2.7368 | 208 | 0.7396 | 0.3737 | 0.7396 | 0.8600 |
|
| 156 |
+
| No log | 2.7632 | 210 | 0.7751 | 0.4167 | 0.7751 | 0.8804 |
|
| 157 |
+
| No log | 2.7895 | 212 | 0.7173 | 0.3544 | 0.7173 | 0.8469 |
|
| 158 |
+
| No log | 2.8158 | 214 | 0.6907 | 0.4103 | 0.6907 | 0.8311 |
|
| 159 |
+
| No log | 2.8421 | 216 | 0.7039 | 0.4207 | 0.7039 | 0.8390 |
|
| 160 |
+
| No log | 2.8684 | 218 | 0.7399 | 0.4644 | 0.7399 | 0.8602 |
|
| 161 |
+
| No log | 2.8947 | 220 | 0.7922 | 0.4389 | 0.7922 | 0.8901 |
|
| 162 |
+
| No log | 2.9211 | 222 | 0.7987 | 0.4315 | 0.7987 | 0.8937 |
|
| 163 |
+
| No log | 2.9474 | 224 | 0.8481 | 0.3731 | 0.8481 | 0.9209 |
|
| 164 |
+
| No log | 2.9737 | 226 | 0.7915 | 0.4072 | 0.7915 | 0.8896 |
|
| 165 |
+
| No log | 3.0 | 228 | 0.6920 | 0.4504 | 0.6920 | 0.8319 |
|
| 166 |
+
| No log | 3.0263 | 230 | 0.6862 | 0.3910 | 0.6862 | 0.8283 |
|
| 167 |
+
| No log | 3.0526 | 232 | 0.7019 | 0.3571 | 0.7019 | 0.8378 |
|
| 168 |
+
| No log | 3.0789 | 234 | 0.7043 | 0.3339 | 0.7043 | 0.8392 |
|
| 169 |
+
| No log | 3.1053 | 236 | 0.7261 | 0.4394 | 0.7261 | 0.8521 |
|
| 170 |
+
| No log | 3.1316 | 238 | 0.7504 | 0.4608 | 0.7504 | 0.8663 |
|
| 171 |
+
| No log | 3.1579 | 240 | 0.7639 | 0.4394 | 0.7639 | 0.8740 |
|
| 172 |
+
| No log | 3.1842 | 242 | 0.7157 | 0.4608 | 0.7157 | 0.8460 |
|
| 173 |
+
| No log | 3.2105 | 244 | 0.6670 | 0.4958 | 0.6670 | 0.8167 |
|
| 174 |
+
| No log | 3.2368 | 246 | 0.6788 | 0.4504 | 0.6788 | 0.8239 |
|
| 175 |
+
| No log | 3.2632 | 248 | 0.6979 | 0.4260 | 0.6979 | 0.8354 |
|
| 176 |
+
| No log | 3.2895 | 250 | 0.6713 | 0.4260 | 0.6713 | 0.8193 |
|
| 177 |
+
| No log | 3.3158 | 252 | 0.6239 | 0.4455 | 0.6239 | 0.7899 |
|
| 178 |
+
| No log | 3.3421 | 254 | 0.6304 | 0.4377 | 0.6304 | 0.7940 |
|
| 179 |
+
| No log | 3.3684 | 256 | 0.6683 | 0.4504 | 0.6683 | 0.8175 |
|
| 180 |
+
| No log | 3.3947 | 258 | 0.7481 | 0.3976 | 0.7481 | 0.8649 |
|
| 181 |
+
| No log | 3.4211 | 260 | 0.7801 | 0.4097 | 0.7801 | 0.8833 |
|
| 182 |
+
| No log | 3.4474 | 262 | 0.7068 | 0.4460 | 0.7068 | 0.8407 |
|
| 183 |
+
| No log | 3.4737 | 264 | 0.6313 | 0.4555 | 0.6313 | 0.7946 |
|
| 184 |
+
| No log | 3.5 | 266 | 0.6350 | 0.4475 | 0.6350 | 0.7969 |
|
| 185 |
+
| No log | 3.5263 | 268 | 0.7456 | 0.4646 | 0.7456 | 0.8635 |
|
| 186 |
+
| No log | 3.5526 | 270 | 0.7891 | 0.4265 | 0.7891 | 0.8883 |
|
| 187 |
+
| No log | 3.5789 | 272 | 0.6984 | 0.4582 | 0.6984 | 0.8357 |
|
| 188 |
+
| No log | 3.6053 | 274 | 0.6465 | 0.4555 | 0.6465 | 0.8041 |
|
| 189 |
+
| No log | 3.6316 | 276 | 0.6590 | 0.4555 | 0.6590 | 0.8118 |
|
| 190 |
+
| No log | 3.6579 | 278 | 0.7448 | 0.4356 | 0.7448 | 0.8630 |
|
| 191 |
+
| No log | 3.6842 | 280 | 0.9794 | 0.2961 | 0.9794 | 0.9896 |
|
| 192 |
+
| No log | 3.7105 | 282 | 0.9864 | 0.3183 | 0.9864 | 0.9932 |
|
| 193 |
+
| No log | 3.7368 | 284 | 0.8301 | 0.4217 | 0.8301 | 0.9111 |
|
| 194 |
+
| No log | 3.7632 | 286 | 0.7135 | 0.4467 | 0.7135 | 0.8447 |
|
| 195 |
+
| No log | 3.7895 | 288 | 0.6919 | 0.4248 | 0.6919 | 0.8318 |
|
| 196 |
+
| No log | 3.8158 | 290 | 0.7207 | 0.3906 | 0.7207 | 0.8489 |
|
| 197 |
+
| No log | 3.8421 | 292 | 0.8375 | 0.3727 | 0.8375 | 0.9152 |
|
| 198 |
+
| No log | 3.8684 | 294 | 0.8737 | 0.3707 | 0.8737 | 0.9347 |
|
| 199 |
+
| No log | 3.8947 | 296 | 0.7774 | 0.4171 | 0.7774 | 0.8817 |
|
| 200 |
+
| No log | 3.9211 | 298 | 0.6528 | 0.4699 | 0.6528 | 0.8079 |
|
| 201 |
+
| No log | 3.9474 | 300 | 0.6606 | 0.5151 | 0.6606 | 0.8128 |
|
| 202 |
+
| No log | 3.9737 | 302 | 0.6650 | 0.4866 | 0.6650 | 0.8155 |
|
| 203 |
+
| No log | 4.0 | 304 | 0.6695 | 0.3995 | 0.6695 | 0.8182 |
|
| 204 |
+
| No log | 4.0263 | 306 | 0.7186 | 0.4806 | 0.7186 | 0.8477 |
|
| 205 |
+
| No log | 4.0526 | 308 | 0.8018 | 0.4133 | 0.8018 | 0.8954 |
|
| 206 |
+
| No log | 4.0789 | 310 | 0.7610 | 0.3913 | 0.7610 | 0.8723 |
|
| 207 |
+
| No log | 4.1053 | 312 | 0.6496 | 0.4350 | 0.6496 | 0.8060 |
|
| 208 |
+
| No log | 4.1316 | 314 | 0.5988 | 0.4100 | 0.5988 | 0.7738 |
|
| 209 |
+
| No log | 4.1579 | 316 | 0.5960 | 0.4847 | 0.5960 | 0.7720 |
|
| 210 |
+
| No log | 4.1842 | 318 | 0.6311 | 0.4740 | 0.6311 | 0.7944 |
|
| 211 |
+
| No log | 4.2105 | 320 | 0.7645 | 0.4592 | 0.7645 | 0.8743 |
|
| 212 |
+
| No log | 4.2368 | 322 | 0.7586 | 0.4353 | 0.7586 | 0.8710 |
|
| 213 |
+
| No log | 4.2632 | 324 | 0.7563 | 0.4353 | 0.7563 | 0.8697 |
|
| 214 |
+
| No log | 4.2895 | 326 | 0.6796 | 0.4484 | 0.6796 | 0.8244 |
|
| 215 |
+
| No log | 4.3158 | 328 | 0.6442 | 0.4847 | 0.6442 | 0.8026 |
|
| 216 |
+
| No log | 4.3421 | 330 | 0.6319 | 0.5158 | 0.6319 | 0.7949 |
|
| 217 |
+
| No log | 4.3684 | 332 | 0.6469 | 0.4924 | 0.6469 | 0.8043 |
|
| 218 |
+
| No log | 4.3947 | 334 | 0.7260 | 0.4340 | 0.7260 | 0.8520 |
|
| 219 |
+
| No log | 4.4211 | 336 | 0.6978 | 0.4340 | 0.6978 | 0.8353 |
|
| 220 |
+
| No log | 4.4474 | 338 | 0.6670 | 0.4340 | 0.6670 | 0.8167 |
|
| 221 |
+
| No log | 4.4737 | 340 | 0.6492 | 0.4997 | 0.6492 | 0.8057 |
|
| 222 |
+
| No log | 4.5 | 342 | 0.6302 | 0.4374 | 0.6302 | 0.7938 |
|
| 223 |
+
| No log | 4.5263 | 344 | 0.6162 | 0.4441 | 0.6162 | 0.7850 |
|
| 224 |
+
| No log | 4.5526 | 346 | 0.6593 | 0.4261 | 0.6593 | 0.8120 |
|
| 225 |
+
| No log | 4.5789 | 348 | 0.6187 | 0.3561 | 0.6187 | 0.7866 |
|
| 226 |
+
| No log | 4.6053 | 350 | 0.6348 | 0.4473 | 0.6348 | 0.7967 |
|
| 227 |
+
| No log | 4.6316 | 352 | 0.6931 | 0.4606 | 0.6931 | 0.8325 |
|
| 228 |
+
| No log | 4.6579 | 354 | 0.7134 | 0.4745 | 0.7134 | 0.8446 |
|
| 229 |
+
| No log | 4.6842 | 356 | 0.6835 | 0.3746 | 0.6835 | 0.8268 |
|
| 230 |
+
| No log | 4.7105 | 358 | 0.6543 | 0.3746 | 0.6543 | 0.8089 |
|
| 231 |
+
| No log | 4.7368 | 360 | 0.6581 | 0.3836 | 0.6581 | 0.8113 |
|
| 232 |
+
| No log | 4.7632 | 362 | 0.6902 | 0.4636 | 0.6902 | 0.8308 |
|
| 233 |
+
| No log | 4.7895 | 364 | 0.6918 | 0.4406 | 0.6918 | 0.8317 |
|
| 234 |
+
| No log | 4.8158 | 366 | 0.6493 | 0.3792 | 0.6493 | 0.8058 |
|
| 235 |
+
| No log | 4.8421 | 368 | 0.7505 | 0.4212 | 0.7505 | 0.8663 |
|
| 236 |
+
| No log | 4.8684 | 370 | 0.8333 | 0.4666 | 0.8333 | 0.9128 |
|
| 237 |
+
| No log | 4.8947 | 372 | 0.8131 | 0.4666 | 0.8131 | 0.9017 |
|
| 238 |
+
| No log | 4.9211 | 374 | 0.7406 | 0.4759 | 0.7406 | 0.8606 |
|
| 239 |
+
| No log | 4.9474 | 376 | 0.6439 | 0.4207 | 0.6439 | 0.8025 |
|
| 240 |
+
| No log | 4.9737 | 378 | 0.5808 | 0.4322 | 0.5808 | 0.7621 |
|
| 241 |
+
| No log | 5.0 | 380 | 0.5650 | 0.4495 | 0.5650 | 0.7516 |
|
| 242 |
+
| No log | 5.0263 | 382 | 0.5728 | 0.5352 | 0.5728 | 0.7568 |
|
| 243 |
+
| No log | 5.0526 | 384 | 0.5635 | 0.5352 | 0.5635 | 0.7507 |
|
| 244 |
+
| No log | 5.0789 | 386 | 0.5627 | 0.5352 | 0.5627 | 0.7502 |
|
| 245 |
+
| No log | 5.1053 | 388 | 0.5680 | 0.5533 | 0.5680 | 0.7537 |
|
| 246 |
+
| No log | 5.1316 | 390 | 0.5777 | 0.5533 | 0.5777 | 0.7600 |
|
| 247 |
+
| No log | 5.1579 | 392 | 0.5724 | 0.4432 | 0.5724 | 0.7566 |
|
| 248 |
+
| No log | 5.1842 | 394 | 0.5840 | 0.4819 | 0.5840 | 0.7642 |
|
| 249 |
+
| No log | 5.2105 | 396 | 0.6108 | 0.4562 | 0.6108 | 0.7816 |
|
| 250 |
+
| No log | 5.2368 | 398 | 0.6046 | 0.4336 | 0.6046 | 0.7775 |
|
| 251 |
+
| No log | 5.2632 | 400 | 0.6038 | 0.4582 | 0.6038 | 0.7770 |
|
| 252 |
+
| No log | 5.2895 | 402 | 0.5943 | 0.4322 | 0.5943 | 0.7709 |
|
| 253 |
+
| No log | 5.3158 | 404 | 0.5987 | 0.4248 | 0.5987 | 0.7738 |
|
| 254 |
+
| No log | 5.3421 | 406 | 0.6103 | 0.4467 | 0.6103 | 0.7812 |
|
| 255 |
+
| No log | 5.3684 | 408 | 0.6348 | 0.4428 | 0.6348 | 0.7968 |
|
| 256 |
+
| No log | 5.3947 | 410 | 0.7223 | 0.4997 | 0.7223 | 0.8499 |
|
| 257 |
+
| No log | 5.4211 | 412 | 0.8629 | 0.3988 | 0.8629 | 0.9289 |
|
| 258 |
+
| No log | 5.4474 | 414 | 0.8628 | 0.4142 | 0.8628 | 0.9289 |
|
| 259 |
+
| No log | 5.4737 | 416 | 0.7662 | 0.4606 | 0.7662 | 0.8753 |
|
| 260 |
+
| No log | 5.5 | 418 | 0.6653 | 0.4413 | 0.6653 | 0.8157 |
|
| 261 |
+
| No log | 5.5263 | 420 | 0.6244 | 0.4342 | 0.6244 | 0.7902 |
|
| 262 |
+
| No log | 5.5526 | 422 | 0.6360 | 0.4813 | 0.6360 | 0.7975 |
|
| 263 |
+
| No log | 5.5789 | 424 | 0.6703 | 0.4624 | 0.6703 | 0.8187 |
|
| 264 |
+
| No log | 5.6053 | 426 | 0.7906 | 0.4107 | 0.7906 | 0.8891 |
|
| 265 |
+
| No log | 5.6316 | 428 | 0.7763 | 0.3802 | 0.7763 | 0.8811 |
|
| 266 |
+
| No log | 5.6579 | 430 | 0.6694 | 0.4413 | 0.6694 | 0.8182 |
|
| 267 |
+
| No log | 5.6842 | 432 | 0.6721 | 0.4353 | 0.6721 | 0.8198 |
|
| 268 |
+
| No log | 5.7105 | 434 | 0.7596 | 0.3892 | 0.7596 | 0.8716 |
|
| 269 |
+
| No log | 5.7368 | 436 | 0.7111 | 0.4482 | 0.7111 | 0.8433 |
|
| 270 |
+
| No log | 5.7632 | 438 | 0.6228 | 0.4753 | 0.6228 | 0.7892 |
|
| 271 |
+
| No log | 5.7895 | 440 | 0.6569 | 0.4260 | 0.6569 | 0.8105 |
|
| 272 |
+
| No log | 5.8158 | 442 | 0.6676 | 0.4522 | 0.6676 | 0.8171 |
|
| 273 |
+
| No log | 5.8421 | 444 | 0.6305 | 0.3937 | 0.6305 | 0.7941 |
|
| 274 |
+
| No log | 5.8684 | 446 | 0.6095 | 0.4201 | 0.6095 | 0.7807 |
|
| 275 |
+
| No log | 5.8947 | 448 | 0.6058 | 0.4380 | 0.6058 | 0.7783 |
|
| 276 |
+
| No log | 5.9211 | 450 | 0.6060 | 0.3937 | 0.6060 | 0.7785 |
|
| 277 |
+
| No log | 5.9474 | 452 | 0.6079 | 0.3937 | 0.6079 | 0.7797 |
|
| 278 |
+
| No log | 5.9737 | 454 | 0.6088 | 0.4434 | 0.6088 | 0.7803 |
|
| 279 |
+
| No log | 6.0 | 456 | 0.6103 | 0.4562 | 0.6103 | 0.7812 |
|
| 280 |
+
| No log | 6.0263 | 458 | 0.6487 | 0.4301 | 0.6487 | 0.8054 |
|
| 281 |
+
| No log | 6.0526 | 460 | 0.7537 | 0.4353 | 0.7537 | 0.8681 |
|
| 282 |
+
| No log | 6.0789 | 462 | 0.7224 | 0.4557 | 0.7224 | 0.8500 |
|
| 283 |
+
| No log | 6.1053 | 464 | 0.6558 | 0.5288 | 0.6558 | 0.8098 |
|
| 284 |
+
| No log | 6.1316 | 466 | 0.6924 | 0.4833 | 0.6924 | 0.8321 |
|
| 285 |
+
| No log | 6.1579 | 468 | 0.6822 | 0.5533 | 0.6822 | 0.8259 |
|
| 286 |
+
| No log | 6.1842 | 470 | 0.6740 | 0.5515 | 0.6740 | 0.8210 |
|
| 287 |
+
| No log | 6.2105 | 472 | 0.7025 | 0.5119 | 0.7025 | 0.8382 |
|
| 288 |
+
| No log | 6.2368 | 474 | 0.7232 | 0.4627 | 0.7232 | 0.8504 |
|
| 289 |
+
| No log | 6.2632 | 476 | 0.6779 | 0.4912 | 0.6779 | 0.8234 |
|
| 290 |
+
| No log | 6.2895 | 478 | 0.6550 | 0.5320 | 0.6550 | 0.8093 |
|
| 291 |
+
| No log | 6.3158 | 480 | 0.6640 | 0.4912 | 0.6640 | 0.8149 |
|
| 292 |
+
| No log | 6.3421 | 482 | 0.6712 | 0.4954 | 0.6712 | 0.8193 |
|
| 293 |
+
| No log | 6.3684 | 484 | 0.6687 | 0.4954 | 0.6687 | 0.8178 |
|
| 294 |
+
| No log | 6.3947 | 486 | 0.6367 | 0.5447 | 0.6367 | 0.7979 |
|
| 295 |
+
| No log | 6.4211 | 488 | 0.6261 | 0.4697 | 0.6261 | 0.7912 |
|
| 296 |
+
| No log | 6.4474 | 490 | 0.6519 | 0.5352 | 0.6519 | 0.8074 |
|
| 297 |
+
| No log | 6.4737 | 492 | 0.6397 | 0.4752 | 0.6397 | 0.7998 |
|
| 298 |
+
| No log | 6.5 | 494 | 0.6139 | 0.4397 | 0.6139 | 0.7835 |
|
| 299 |
+
| No log | 6.5263 | 496 | 0.6978 | 0.4606 | 0.6978 | 0.8353 |
|
| 300 |
+
| No log | 6.5526 | 498 | 0.7128 | 0.4243 | 0.7128 | 0.8443 |
|
| 301 |
+
| 0.383 | 6.5789 | 500 | 0.6488 | 0.4929 | 0.6488 | 0.8055 |
|
| 302 |
+
| 0.383 | 6.6053 | 502 | 0.6218 | 0.3769 | 0.6218 | 0.7885 |
|
| 303 |
+
| 0.383 | 6.6316 | 504 | 0.6247 | 0.3530 | 0.6247 | 0.7904 |
|
| 304 |
+
| 0.383 | 6.6579 | 506 | 0.6325 | 0.3792 | 0.6325 | 0.7953 |
|
| 305 |
+
| 0.383 | 6.6842 | 508 | 0.6560 | 0.4478 | 0.6560 | 0.8100 |
|
| 306 |
+
| 0.383 | 6.7105 | 510 | 0.6954 | 0.4408 | 0.6954 | 0.8339 |
|
| 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 sha256:0768b6245ac36859eae137ff9c80a35b6ca546f8d7a8dbf6004c9200726f4df6
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9bea0c5dd3e060ccd0eaa84037ac264d5b44f55d1d11d075a04351548c1a04
|
| 3 |
+
size 5304
|