Training in progress, step 500
Browse files- README.md +328 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,328 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_grammar
|
| 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 |
+
# Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_grammar
|
| 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: 0.7020
|
| 19 |
+
- Qwk: 0.5776
|
| 20 |
+
- Mse: 0.7020
|
| 21 |
+
- Rmse: 0.8379
|
| 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 | 0.0202 | 2 | 4.2066 | 0.0038 | 4.2066 | 2.0510 |
|
| 53 |
+
| No log | 0.0404 | 4 | 3.2857 | 0.0288 | 3.2857 | 1.8126 |
|
| 54 |
+
| No log | 0.0606 | 6 | 2.0350 | 0.0648 | 2.0350 | 1.4265 |
|
| 55 |
+
| No log | 0.0808 | 8 | 0.9950 | 0.1410 | 0.9950 | 0.9975 |
|
| 56 |
+
| No log | 0.1010 | 10 | 0.9184 | 0.0766 | 0.9184 | 0.9583 |
|
| 57 |
+
| No log | 0.1212 | 12 | 0.9905 | 0.0522 | 0.9905 | 0.9952 |
|
| 58 |
+
| No log | 0.1414 | 14 | 0.9266 | 0.0275 | 0.9266 | 0.9626 |
|
| 59 |
+
| No log | 0.1616 | 16 | 0.8571 | 0.0562 | 0.8571 | 0.9258 |
|
| 60 |
+
| No log | 0.1818 | 18 | 0.7856 | 0.2371 | 0.7856 | 0.8863 |
|
| 61 |
+
| No log | 0.2020 | 20 | 0.7807 | 0.4035 | 0.7807 | 0.8836 |
|
| 62 |
+
| No log | 0.2222 | 22 | 0.7716 | 0.4214 | 0.7716 | 0.8784 |
|
| 63 |
+
| No log | 0.2424 | 24 | 0.7313 | 0.4080 | 0.7313 | 0.8551 |
|
| 64 |
+
| No log | 0.2626 | 26 | 0.7380 | 0.2240 | 0.7380 | 0.8591 |
|
| 65 |
+
| No log | 0.2828 | 28 | 0.7991 | 0.1854 | 0.7991 | 0.8939 |
|
| 66 |
+
| No log | 0.3030 | 30 | 0.7612 | 0.2355 | 0.7612 | 0.8725 |
|
| 67 |
+
| No log | 0.3232 | 32 | 0.6563 | 0.3694 | 0.6563 | 0.8101 |
|
| 68 |
+
| No log | 0.3434 | 34 | 0.6203 | 0.4564 | 0.6203 | 0.7876 |
|
| 69 |
+
| No log | 0.3636 | 36 | 0.6120 | 0.4261 | 0.6120 | 0.7823 |
|
| 70 |
+
| No log | 0.3838 | 38 | 0.6648 | 0.3893 | 0.6648 | 0.8154 |
|
| 71 |
+
| No log | 0.4040 | 40 | 0.7147 | 0.3300 | 0.7147 | 0.8454 |
|
| 72 |
+
| No log | 0.4242 | 42 | 0.7589 | 0.3849 | 0.7589 | 0.8712 |
|
| 73 |
+
| No log | 0.4444 | 44 | 0.7400 | 0.4386 | 0.7400 | 0.8603 |
|
| 74 |
+
| No log | 0.4646 | 46 | 0.7547 | 0.4505 | 0.7547 | 0.8687 |
|
| 75 |
+
| No log | 0.4848 | 48 | 0.6243 | 0.4781 | 0.6243 | 0.7901 |
|
| 76 |
+
| No log | 0.5051 | 50 | 0.5571 | 0.5465 | 0.5571 | 0.7464 |
|
| 77 |
+
| No log | 0.5253 | 52 | 0.5483 | 0.5050 | 0.5483 | 0.7404 |
|
| 78 |
+
| No log | 0.5455 | 54 | 0.5732 | 0.4436 | 0.5732 | 0.7571 |
|
| 79 |
+
| No log | 0.5657 | 56 | 0.6846 | 0.3726 | 0.6846 | 0.8274 |
|
| 80 |
+
| No log | 0.5859 | 58 | 0.7354 | 0.2884 | 0.7354 | 0.8576 |
|
| 81 |
+
| No log | 0.6061 | 60 | 0.7393 | 0.2819 | 0.7393 | 0.8598 |
|
| 82 |
+
| No log | 0.6263 | 62 | 0.7009 | 0.2671 | 0.7009 | 0.8372 |
|
| 83 |
+
| No log | 0.6465 | 64 | 0.6829 | 0.2664 | 0.6829 | 0.8264 |
|
| 84 |
+
| No log | 0.6667 | 66 | 0.6413 | 0.3386 | 0.6413 | 0.8008 |
|
| 85 |
+
| No log | 0.6869 | 68 | 0.6192 | 0.3976 | 0.6192 | 0.7869 |
|
| 86 |
+
| No log | 0.7071 | 70 | 0.6957 | 0.4284 | 0.6957 | 0.8341 |
|
| 87 |
+
| No log | 0.7273 | 72 | 0.7624 | 0.4444 | 0.7624 | 0.8732 |
|
| 88 |
+
| No log | 0.7475 | 74 | 0.7196 | 0.4976 | 0.7196 | 0.8483 |
|
| 89 |
+
| No log | 0.7677 | 76 | 0.6587 | 0.5412 | 0.6587 | 0.8116 |
|
| 90 |
+
| No log | 0.7879 | 78 | 0.5828 | 0.5778 | 0.5828 | 0.7634 |
|
| 91 |
+
| No log | 0.8081 | 80 | 0.5187 | 0.5728 | 0.5187 | 0.7202 |
|
| 92 |
+
| No log | 0.8283 | 82 | 0.4990 | 0.5873 | 0.4990 | 0.7064 |
|
| 93 |
+
| No log | 0.8485 | 84 | 0.5424 | 0.5804 | 0.5424 | 0.7365 |
|
| 94 |
+
| No log | 0.8687 | 86 | 0.5306 | 0.6152 | 0.5306 | 0.7284 |
|
| 95 |
+
| No log | 0.8889 | 88 | 0.5059 | 0.6329 | 0.5059 | 0.7113 |
|
| 96 |
+
| No log | 0.9091 | 90 | 0.5636 | 0.5765 | 0.5636 | 0.7508 |
|
| 97 |
+
| No log | 0.9293 | 92 | 0.6334 | 0.4352 | 0.6334 | 0.7959 |
|
| 98 |
+
| No log | 0.9495 | 94 | 0.6473 | 0.4051 | 0.6473 | 0.8045 |
|
| 99 |
+
| No log | 0.9697 | 96 | 0.6179 | 0.4591 | 0.6179 | 0.7861 |
|
| 100 |
+
| No log | 0.9899 | 98 | 0.6062 | 0.5154 | 0.6062 | 0.7786 |
|
| 101 |
+
| No log | 1.0101 | 100 | 0.5195 | 0.5603 | 0.5195 | 0.7208 |
|
| 102 |
+
| No log | 1.0303 | 102 | 0.5444 | 0.6026 | 0.5444 | 0.7378 |
|
| 103 |
+
| No log | 1.0505 | 104 | 0.6167 | 0.5782 | 0.6167 | 0.7853 |
|
| 104 |
+
| No log | 1.0707 | 106 | 0.6387 | 0.5454 | 0.6387 | 0.7992 |
|
| 105 |
+
| No log | 1.0909 | 108 | 0.6018 | 0.5139 | 0.6018 | 0.7758 |
|
| 106 |
+
| No log | 1.1111 | 110 | 0.6058 | 0.5100 | 0.6058 | 0.7783 |
|
| 107 |
+
| No log | 1.1313 | 112 | 0.6145 | 0.5171 | 0.6145 | 0.7839 |
|
| 108 |
+
| No log | 1.1515 | 114 | 0.5663 | 0.5897 | 0.5663 | 0.7525 |
|
| 109 |
+
| No log | 1.1717 | 116 | 0.5918 | 0.6043 | 0.5918 | 0.7693 |
|
| 110 |
+
| No log | 1.1919 | 118 | 0.5579 | 0.6265 | 0.5579 | 0.7469 |
|
| 111 |
+
| No log | 1.2121 | 120 | 0.5488 | 0.6271 | 0.5488 | 0.7408 |
|
| 112 |
+
| No log | 1.2323 | 122 | 0.5306 | 0.5846 | 0.5306 | 0.7284 |
|
| 113 |
+
| No log | 1.2525 | 124 | 0.5882 | 0.5149 | 0.5882 | 0.7669 |
|
| 114 |
+
| No log | 1.2727 | 126 | 0.6887 | 0.3758 | 0.6887 | 0.8299 |
|
| 115 |
+
| No log | 1.2929 | 128 | 0.7031 | 0.3342 | 0.7031 | 0.8385 |
|
| 116 |
+
| No log | 1.3131 | 130 | 0.6847 | 0.3359 | 0.6847 | 0.8275 |
|
| 117 |
+
| No log | 1.3333 | 132 | 0.6488 | 0.4184 | 0.6488 | 0.8055 |
|
| 118 |
+
| No log | 1.3535 | 134 | 0.6094 | 0.4793 | 0.6094 | 0.7807 |
|
| 119 |
+
| No log | 1.3737 | 136 | 0.6229 | 0.5115 | 0.6229 | 0.7893 |
|
| 120 |
+
| No log | 1.3939 | 138 | 0.5725 | 0.5374 | 0.5725 | 0.7566 |
|
| 121 |
+
| No log | 1.4141 | 140 | 0.5884 | 0.5436 | 0.5884 | 0.7671 |
|
| 122 |
+
| No log | 1.4343 | 142 | 0.5793 | 0.5602 | 0.5793 | 0.7611 |
|
| 123 |
+
| No log | 1.4545 | 144 | 0.6110 | 0.5772 | 0.6110 | 0.7817 |
|
| 124 |
+
| No log | 1.4747 | 146 | 0.6035 | 0.5849 | 0.6035 | 0.7769 |
|
| 125 |
+
| No log | 1.4949 | 148 | 0.5221 | 0.5972 | 0.5221 | 0.7226 |
|
| 126 |
+
| No log | 1.5152 | 150 | 0.5574 | 0.5888 | 0.5574 | 0.7466 |
|
| 127 |
+
| No log | 1.5354 | 152 | 0.6931 | 0.4962 | 0.6931 | 0.8325 |
|
| 128 |
+
| No log | 1.5556 | 154 | 0.8766 | 0.3737 | 0.8766 | 0.9363 |
|
| 129 |
+
| No log | 1.5758 | 156 | 0.9278 | 0.3457 | 0.9278 | 0.9632 |
|
| 130 |
+
| No log | 1.5960 | 158 | 0.8315 | 0.4112 | 0.8315 | 0.9119 |
|
| 131 |
+
| No log | 1.6162 | 160 | 0.6595 | 0.5450 | 0.6595 | 0.8121 |
|
| 132 |
+
| No log | 1.6364 | 162 | 0.5592 | 0.5899 | 0.5592 | 0.7478 |
|
| 133 |
+
| No log | 1.6566 | 164 | 0.5162 | 0.6132 | 0.5162 | 0.7185 |
|
| 134 |
+
| No log | 1.6768 | 166 | 0.4919 | 0.6083 | 0.4919 | 0.7013 |
|
| 135 |
+
| No log | 1.6970 | 168 | 0.4874 | 0.6210 | 0.4874 | 0.6982 |
|
| 136 |
+
| No log | 1.7172 | 170 | 0.5376 | 0.6129 | 0.5376 | 0.7332 |
|
| 137 |
+
| No log | 1.7374 | 172 | 0.5294 | 0.6173 | 0.5294 | 0.7276 |
|
| 138 |
+
| No log | 1.7576 | 174 | 0.5825 | 0.5844 | 0.5825 | 0.7632 |
|
| 139 |
+
| No log | 1.7778 | 176 | 0.6408 | 0.5601 | 0.6408 | 0.8005 |
|
| 140 |
+
| No log | 1.7980 | 178 | 0.6486 | 0.5541 | 0.6486 | 0.8054 |
|
| 141 |
+
| No log | 1.8182 | 180 | 0.5467 | 0.6066 | 0.5467 | 0.7394 |
|
| 142 |
+
| No log | 1.8384 | 182 | 0.4932 | 0.5659 | 0.4932 | 0.7023 |
|
| 143 |
+
| No log | 1.8586 | 184 | 0.5009 | 0.5497 | 0.5009 | 0.7077 |
|
| 144 |
+
| No log | 1.8788 | 186 | 0.5570 | 0.5711 | 0.5570 | 0.7463 |
|
| 145 |
+
| No log | 1.8990 | 188 | 0.5645 | 0.5529 | 0.5645 | 0.7513 |
|
| 146 |
+
| No log | 1.9192 | 190 | 0.5285 | 0.6103 | 0.5285 | 0.7270 |
|
| 147 |
+
| No log | 1.9394 | 192 | 0.5198 | 0.6293 | 0.5198 | 0.7210 |
|
| 148 |
+
| No log | 1.9596 | 194 | 0.4829 | 0.6476 | 0.4829 | 0.6949 |
|
| 149 |
+
| No log | 1.9798 | 196 | 0.4656 | 0.6819 | 0.4656 | 0.6824 |
|
| 150 |
+
| No log | 2.0 | 198 | 0.4903 | 0.6451 | 0.4903 | 0.7002 |
|
| 151 |
+
| No log | 2.0202 | 200 | 0.6542 | 0.5854 | 0.6542 | 0.8088 |
|
| 152 |
+
| No log | 2.0404 | 202 | 0.9370 | 0.4282 | 0.9370 | 0.9680 |
|
| 153 |
+
| No log | 2.0606 | 204 | 0.9795 | 0.3803 | 0.9795 | 0.9897 |
|
| 154 |
+
| No log | 2.0808 | 206 | 0.8086 | 0.4539 | 0.8086 | 0.8992 |
|
| 155 |
+
| No log | 2.1010 | 208 | 0.6387 | 0.4980 | 0.6387 | 0.7992 |
|
| 156 |
+
| No log | 2.1212 | 210 | 0.6249 | 0.3747 | 0.6249 | 0.7905 |
|
| 157 |
+
| No log | 2.1414 | 212 | 0.6017 | 0.4178 | 0.6017 | 0.7757 |
|
| 158 |
+
| No log | 2.1616 | 214 | 0.5658 | 0.5272 | 0.5658 | 0.7522 |
|
| 159 |
+
| No log | 2.1818 | 216 | 0.5495 | 0.5450 | 0.5495 | 0.7413 |
|
| 160 |
+
| No log | 2.2020 | 218 | 0.6072 | 0.5463 | 0.6072 | 0.7792 |
|
| 161 |
+
| No log | 2.2222 | 220 | 0.7074 | 0.5095 | 0.7074 | 0.8411 |
|
| 162 |
+
| No log | 2.2424 | 222 | 0.7652 | 0.5510 | 0.7652 | 0.8748 |
|
| 163 |
+
| No log | 2.2626 | 224 | 0.6011 | 0.6199 | 0.6011 | 0.7753 |
|
| 164 |
+
| No log | 2.2828 | 226 | 0.4625 | 0.6990 | 0.4625 | 0.6801 |
|
| 165 |
+
| No log | 2.3030 | 228 | 0.4502 | 0.7017 | 0.4502 | 0.6709 |
|
| 166 |
+
| No log | 2.3232 | 230 | 0.4626 | 0.6927 | 0.4626 | 0.6802 |
|
| 167 |
+
| No log | 2.3434 | 232 | 0.5433 | 0.6160 | 0.5433 | 0.7371 |
|
| 168 |
+
| No log | 2.3636 | 234 | 0.6130 | 0.6334 | 0.6130 | 0.7829 |
|
| 169 |
+
| No log | 2.3838 | 236 | 0.5587 | 0.6341 | 0.5587 | 0.7475 |
|
| 170 |
+
| No log | 2.4040 | 238 | 0.5849 | 0.5685 | 0.5849 | 0.7648 |
|
| 171 |
+
| No log | 2.4242 | 240 | 0.6319 | 0.5214 | 0.6319 | 0.7949 |
|
| 172 |
+
| No log | 2.4444 | 242 | 0.5846 | 0.5527 | 0.5846 | 0.7646 |
|
| 173 |
+
| No log | 2.4646 | 244 | 0.5707 | 0.5550 | 0.5707 | 0.7555 |
|
| 174 |
+
| No log | 2.4848 | 246 | 0.6578 | 0.5161 | 0.6578 | 0.8111 |
|
| 175 |
+
| No log | 2.5051 | 248 | 0.6705 | 0.5192 | 0.6705 | 0.8188 |
|
| 176 |
+
| No log | 2.5253 | 250 | 0.6691 | 0.5263 | 0.6691 | 0.8180 |
|
| 177 |
+
| No log | 2.5455 | 252 | 0.5750 | 0.6165 | 0.5750 | 0.7583 |
|
| 178 |
+
| No log | 2.5657 | 254 | 0.5381 | 0.6535 | 0.5381 | 0.7336 |
|
| 179 |
+
| No log | 2.5859 | 256 | 0.5521 | 0.6378 | 0.5521 | 0.7430 |
|
| 180 |
+
| No log | 2.6061 | 258 | 0.5875 | 0.6426 | 0.5875 | 0.7665 |
|
| 181 |
+
| No log | 2.6263 | 260 | 0.5384 | 0.6689 | 0.5384 | 0.7338 |
|
| 182 |
+
| No log | 2.6465 | 262 | 0.5567 | 0.6528 | 0.5567 | 0.7461 |
|
| 183 |
+
| No log | 2.6667 | 264 | 0.6365 | 0.6244 | 0.6365 | 0.7978 |
|
| 184 |
+
| No log | 2.6869 | 266 | 0.6049 | 0.6395 | 0.6049 | 0.7777 |
|
| 185 |
+
| No log | 2.7071 | 268 | 0.5318 | 0.6332 | 0.5318 | 0.7292 |
|
| 186 |
+
| No log | 2.7273 | 270 | 0.5009 | 0.6499 | 0.5009 | 0.7077 |
|
| 187 |
+
| No log | 2.7475 | 272 | 0.4521 | 0.6789 | 0.4521 | 0.6724 |
|
| 188 |
+
| No log | 2.7677 | 274 | 0.4517 | 0.6767 | 0.4517 | 0.6721 |
|
| 189 |
+
| No log | 2.7879 | 276 | 0.4567 | 0.6305 | 0.4567 | 0.6758 |
|
| 190 |
+
| No log | 2.8081 | 278 | 0.5514 | 0.5972 | 0.5514 | 0.7425 |
|
| 191 |
+
| No log | 2.8283 | 280 | 0.5712 | 0.5554 | 0.5712 | 0.7558 |
|
| 192 |
+
| No log | 2.8485 | 282 | 0.6003 | 0.5204 | 0.6003 | 0.7748 |
|
| 193 |
+
| No log | 2.8687 | 284 | 0.5597 | 0.5314 | 0.5597 | 0.7481 |
|
| 194 |
+
| No log | 2.8889 | 286 | 0.4874 | 0.5603 | 0.4874 | 0.6981 |
|
| 195 |
+
| No log | 2.9091 | 288 | 0.4776 | 0.5872 | 0.4776 | 0.6911 |
|
| 196 |
+
| No log | 2.9293 | 290 | 0.5148 | 0.5877 | 0.5148 | 0.7175 |
|
| 197 |
+
| No log | 2.9495 | 292 | 0.5315 | 0.6353 | 0.5315 | 0.7291 |
|
| 198 |
+
| No log | 2.9697 | 294 | 0.5408 | 0.6570 | 0.5408 | 0.7354 |
|
| 199 |
+
| No log | 2.9899 | 296 | 0.5767 | 0.6181 | 0.5767 | 0.7594 |
|
| 200 |
+
| No log | 3.0101 | 298 | 0.5392 | 0.6491 | 0.5392 | 0.7343 |
|
| 201 |
+
| No log | 3.0303 | 300 | 0.5811 | 0.6222 | 0.5811 | 0.7623 |
|
| 202 |
+
| No log | 3.0505 | 302 | 0.6494 | 0.6149 | 0.6494 | 0.8058 |
|
| 203 |
+
| No log | 3.0707 | 304 | 0.7728 | 0.5570 | 0.7728 | 0.8791 |
|
| 204 |
+
| No log | 3.0909 | 306 | 0.6290 | 0.6177 | 0.6290 | 0.7931 |
|
| 205 |
+
| No log | 3.1111 | 308 | 0.4726 | 0.6381 | 0.4726 | 0.6874 |
|
| 206 |
+
| No log | 3.1313 | 310 | 0.4705 | 0.6312 | 0.4705 | 0.6859 |
|
| 207 |
+
| No log | 3.1515 | 312 | 0.5633 | 0.6059 | 0.5633 | 0.7505 |
|
| 208 |
+
| No log | 3.1717 | 314 | 0.7147 | 0.5681 | 0.7147 | 0.8454 |
|
| 209 |
+
| No log | 3.1919 | 316 | 0.6940 | 0.5653 | 0.6940 | 0.8330 |
|
| 210 |
+
| No log | 3.2121 | 318 | 0.5949 | 0.6013 | 0.5949 | 0.7713 |
|
| 211 |
+
| No log | 3.2323 | 320 | 0.6116 | 0.6103 | 0.6116 | 0.7821 |
|
| 212 |
+
| No log | 3.2525 | 322 | 0.5518 | 0.6217 | 0.5518 | 0.7428 |
|
| 213 |
+
| No log | 3.2727 | 324 | 0.6266 | 0.6149 | 0.6266 | 0.7916 |
|
| 214 |
+
| No log | 3.2929 | 326 | 0.6321 | 0.6090 | 0.6321 | 0.7950 |
|
| 215 |
+
| No log | 3.3131 | 328 | 0.4804 | 0.6478 | 0.4804 | 0.6931 |
|
| 216 |
+
| No log | 3.3333 | 330 | 0.4556 | 0.6723 | 0.4556 | 0.6750 |
|
| 217 |
+
| No log | 3.3535 | 332 | 0.4632 | 0.6821 | 0.4632 | 0.6806 |
|
| 218 |
+
| No log | 3.3737 | 334 | 0.5296 | 0.6356 | 0.5296 | 0.7277 |
|
| 219 |
+
| No log | 3.3939 | 336 | 0.7352 | 0.5966 | 0.7352 | 0.8574 |
|
| 220 |
+
| No log | 3.4141 | 338 | 0.8905 | 0.5470 | 0.8905 | 0.9437 |
|
| 221 |
+
| No log | 3.4343 | 340 | 0.7908 | 0.5789 | 0.7908 | 0.8893 |
|
| 222 |
+
| No log | 3.4545 | 342 | 0.5379 | 0.6503 | 0.5379 | 0.7334 |
|
| 223 |
+
| No log | 3.4747 | 344 | 0.4489 | 0.6784 | 0.4489 | 0.6700 |
|
| 224 |
+
| No log | 3.4949 | 346 | 0.4371 | 0.6873 | 0.4371 | 0.6611 |
|
| 225 |
+
| No log | 3.5152 | 348 | 0.4566 | 0.6300 | 0.4566 | 0.6757 |
|
| 226 |
+
| No log | 3.5354 | 350 | 0.6308 | 0.5805 | 0.6308 | 0.7942 |
|
| 227 |
+
| No log | 3.5556 | 352 | 0.7288 | 0.5195 | 0.7288 | 0.8537 |
|
| 228 |
+
| No log | 3.5758 | 354 | 0.6718 | 0.5069 | 0.6718 | 0.8196 |
|
| 229 |
+
| No log | 3.5960 | 356 | 0.6201 | 0.5429 | 0.6201 | 0.7875 |
|
| 230 |
+
| No log | 3.6162 | 358 | 0.6016 | 0.5482 | 0.6016 | 0.7756 |
|
| 231 |
+
| No log | 3.6364 | 360 | 0.5238 | 0.5826 | 0.5238 | 0.7237 |
|
| 232 |
+
| No log | 3.6566 | 362 | 0.5146 | 0.6072 | 0.5146 | 0.7173 |
|
| 233 |
+
| No log | 3.6768 | 364 | 0.5746 | 0.5899 | 0.5746 | 0.7580 |
|
| 234 |
+
| No log | 3.6970 | 366 | 0.5142 | 0.6444 | 0.5142 | 0.7171 |
|
| 235 |
+
| No log | 3.7172 | 368 | 0.5550 | 0.5994 | 0.5550 | 0.7450 |
|
| 236 |
+
| No log | 3.7374 | 370 | 0.5792 | 0.6170 | 0.5792 | 0.7611 |
|
| 237 |
+
| No log | 3.7576 | 372 | 0.5286 | 0.6537 | 0.5286 | 0.7271 |
|
| 238 |
+
| No log | 3.7778 | 374 | 0.6107 | 0.6087 | 0.6107 | 0.7815 |
|
| 239 |
+
| No log | 3.7980 | 376 | 0.5670 | 0.6538 | 0.5670 | 0.7530 |
|
| 240 |
+
| No log | 3.8182 | 378 | 0.4911 | 0.6540 | 0.4911 | 0.7008 |
|
| 241 |
+
| No log | 3.8384 | 380 | 0.5064 | 0.6157 | 0.5064 | 0.7116 |
|
| 242 |
+
| No log | 3.8586 | 382 | 0.5421 | 0.6426 | 0.5421 | 0.7363 |
|
| 243 |
+
| No log | 3.8788 | 384 | 0.8343 | 0.5155 | 0.8343 | 0.9134 |
|
| 244 |
+
| No log | 3.8990 | 386 | 0.9728 | 0.4728 | 0.9728 | 0.9863 |
|
| 245 |
+
| No log | 3.9192 | 388 | 0.8744 | 0.5059 | 0.8744 | 0.9351 |
|
| 246 |
+
| No log | 3.9394 | 390 | 0.6642 | 0.5804 | 0.6642 | 0.8150 |
|
| 247 |
+
| No log | 3.9596 | 392 | 0.4827 | 0.6463 | 0.4827 | 0.6948 |
|
| 248 |
+
| No log | 3.9798 | 394 | 0.4235 | 0.6538 | 0.4235 | 0.6507 |
|
| 249 |
+
| No log | 4.0 | 396 | 0.4296 | 0.6585 | 0.4296 | 0.6554 |
|
| 250 |
+
| No log | 4.0202 | 398 | 0.5509 | 0.6652 | 0.5509 | 0.7422 |
|
| 251 |
+
| No log | 4.0404 | 400 | 0.7656 | 0.5426 | 0.7656 | 0.8750 |
|
| 252 |
+
| No log | 4.0606 | 402 | 0.7309 | 0.5628 | 0.7309 | 0.8550 |
|
| 253 |
+
| No log | 4.0808 | 404 | 0.5898 | 0.6501 | 0.5898 | 0.7680 |
|
| 254 |
+
| No log | 4.1010 | 406 | 0.4672 | 0.6852 | 0.4672 | 0.6835 |
|
| 255 |
+
| No log | 4.1212 | 408 | 0.4301 | 0.6559 | 0.4301 | 0.6558 |
|
| 256 |
+
| No log | 4.1414 | 410 | 0.4217 | 0.6511 | 0.4217 | 0.6494 |
|
| 257 |
+
| No log | 4.1616 | 412 | 0.4331 | 0.6558 | 0.4331 | 0.6581 |
|
| 258 |
+
| No log | 4.1818 | 414 | 0.4998 | 0.6675 | 0.4998 | 0.7070 |
|
| 259 |
+
| No log | 4.2020 | 416 | 0.5652 | 0.6198 | 0.5652 | 0.7518 |
|
| 260 |
+
| No log | 4.2222 | 418 | 0.5533 | 0.6238 | 0.5533 | 0.7439 |
|
| 261 |
+
| No log | 4.2424 | 420 | 0.5296 | 0.6398 | 0.5296 | 0.7278 |
|
| 262 |
+
| No log | 4.2626 | 422 | 0.5728 | 0.6058 | 0.5728 | 0.7568 |
|
| 263 |
+
| No log | 4.2828 | 424 | 0.5494 | 0.6564 | 0.5494 | 0.7412 |
|
| 264 |
+
| No log | 4.3030 | 426 | 0.5678 | 0.6702 | 0.5678 | 0.7535 |
|
| 265 |
+
| No log | 4.3232 | 428 | 0.5620 | 0.6625 | 0.5620 | 0.7497 |
|
| 266 |
+
| No log | 4.3434 | 430 | 0.5900 | 0.6660 | 0.5900 | 0.7681 |
|
| 267 |
+
| No log | 4.3636 | 432 | 0.5394 | 0.6861 | 0.5394 | 0.7345 |
|
| 268 |
+
| No log | 4.3838 | 434 | 0.6717 | 0.6214 | 0.6717 | 0.8196 |
|
| 269 |
+
| No log | 4.4040 | 436 | 0.6642 | 0.6046 | 0.6642 | 0.8150 |
|
| 270 |
+
| No log | 4.4242 | 438 | 0.6688 | 0.5791 | 0.6688 | 0.8178 |
|
| 271 |
+
| No log | 4.4444 | 440 | 0.5311 | 0.6257 | 0.5311 | 0.7287 |
|
| 272 |
+
| No log | 4.4646 | 442 | 0.5138 | 0.6227 | 0.5138 | 0.7168 |
|
| 273 |
+
| No log | 4.4848 | 444 | 0.5267 | 0.6122 | 0.5267 | 0.7257 |
|
| 274 |
+
| No log | 4.5051 | 446 | 0.4676 | 0.6500 | 0.4676 | 0.6838 |
|
| 275 |
+
| No log | 4.5253 | 448 | 0.4944 | 0.6452 | 0.4944 | 0.7031 |
|
| 276 |
+
| No log | 4.5455 | 450 | 0.5701 | 0.6263 | 0.5701 | 0.7551 |
|
| 277 |
+
| No log | 4.5657 | 452 | 0.6354 | 0.6357 | 0.6354 | 0.7971 |
|
| 278 |
+
| No log | 4.5859 | 454 | 0.5396 | 0.6652 | 0.5396 | 0.7346 |
|
| 279 |
+
| No log | 4.6061 | 456 | 0.4810 | 0.6748 | 0.4810 | 0.6935 |
|
| 280 |
+
| No log | 4.6263 | 458 | 0.4722 | 0.6822 | 0.4722 | 0.6871 |
|
| 281 |
+
| No log | 4.6465 | 460 | 0.5397 | 0.6720 | 0.5397 | 0.7346 |
|
| 282 |
+
| No log | 4.6667 | 462 | 0.7453 | 0.6161 | 0.7453 | 0.8633 |
|
| 283 |
+
| No log | 4.6869 | 464 | 0.6480 | 0.6782 | 0.6480 | 0.8050 |
|
| 284 |
+
| No log | 4.7071 | 466 | 0.5671 | 0.6811 | 0.5671 | 0.7531 |
|
| 285 |
+
| No log | 4.7273 | 468 | 0.4734 | 0.6839 | 0.4734 | 0.6880 |
|
| 286 |
+
| No log | 4.7475 | 470 | 0.4815 | 0.6809 | 0.4815 | 0.6939 |
|
| 287 |
+
| No log | 4.7677 | 472 | 0.6504 | 0.6285 | 0.6504 | 0.8065 |
|
| 288 |
+
| No log | 4.7879 | 474 | 1.0527 | 0.4400 | 1.0527 | 1.0260 |
|
| 289 |
+
| No log | 4.8081 | 476 | 1.1043 | 0.4269 | 1.1043 | 1.0509 |
|
| 290 |
+
| No log | 4.8283 | 478 | 0.8676 | 0.5068 | 0.8676 | 0.9314 |
|
| 291 |
+
| No log | 4.8485 | 480 | 0.6248 | 0.6051 | 0.6248 | 0.7904 |
|
| 292 |
+
| No log | 4.8687 | 482 | 0.4809 | 0.6318 | 0.4809 | 0.6935 |
|
| 293 |
+
| No log | 4.8889 | 484 | 0.4613 | 0.6299 | 0.4613 | 0.6792 |
|
| 294 |
+
| No log | 4.9091 | 486 | 0.4615 | 0.6418 | 0.4615 | 0.6793 |
|
| 295 |
+
| No log | 4.9293 | 488 | 0.5440 | 0.6771 | 0.5440 | 0.7376 |
|
| 296 |
+
| No log | 4.9495 | 490 | 0.7241 | 0.5682 | 0.7241 | 0.8509 |
|
| 297 |
+
| No log | 4.9697 | 492 | 0.7479 | 0.5578 | 0.7479 | 0.8648 |
|
| 298 |
+
| No log | 4.9899 | 494 | 0.6394 | 0.6305 | 0.6394 | 0.7996 |
|
| 299 |
+
| No log | 5.0101 | 496 | 0.5398 | 0.6820 | 0.5398 | 0.7347 |
|
| 300 |
+
| No log | 5.0303 | 498 | 0.4562 | 0.6784 | 0.4562 | 0.6754 |
|
| 301 |
+
| 0.516 | 5.0505 | 500 | 0.5035 | 0.6809 | 0.5035 | 0.7096 |
|
| 302 |
+
| 0.516 | 5.0707 | 502 | 0.6625 | 0.6183 | 0.6625 | 0.8140 |
|
| 303 |
+
| 0.516 | 5.0909 | 504 | 0.6130 | 0.6255 | 0.6130 | 0.7829 |
|
| 304 |
+
| 0.516 | 5.1111 | 506 | 0.5895 | 0.6355 | 0.5895 | 0.7678 |
|
| 305 |
+
| 0.516 | 5.1313 | 508 | 0.5015 | 0.6608 | 0.5015 | 0.7082 |
|
| 306 |
+
| 0.516 | 5.1515 | 510 | 0.5201 | 0.6833 | 0.5201 | 0.7212 |
|
| 307 |
+
| 0.516 | 5.1717 | 512 | 0.5335 | 0.6565 | 0.5335 | 0.7304 |
|
| 308 |
+
| 0.516 | 5.1919 | 514 | 0.6211 | 0.6531 | 0.6211 | 0.7881 |
|
| 309 |
+
| 0.516 | 5.2121 | 516 | 0.5957 | 0.6673 | 0.5957 | 0.7718 |
|
| 310 |
+
| 0.516 | 5.2323 | 518 | 0.5805 | 0.6872 | 0.5805 | 0.7619 |
|
| 311 |
+
| 0.516 | 5.2525 | 520 | 0.6756 | 0.6723 | 0.6756 | 0.8219 |
|
| 312 |
+
| 0.516 | 5.2727 | 522 | 0.5668 | 0.6843 | 0.5668 | 0.7529 |
|
| 313 |
+
| 0.516 | 5.2929 | 524 | 0.4896 | 0.6958 | 0.4896 | 0.6997 |
|
| 314 |
+
| 0.516 | 5.3131 | 526 | 0.4672 | 0.6915 | 0.4672 | 0.6835 |
|
| 315 |
+
| 0.516 | 5.3333 | 528 | 0.4374 | 0.6900 | 0.4374 | 0.6613 |
|
| 316 |
+
| 0.516 | 5.3535 | 530 | 0.4624 | 0.6725 | 0.4624 | 0.6800 |
|
| 317 |
+
| 0.516 | 5.3737 | 532 | 0.5545 | 0.6402 | 0.5545 | 0.7447 |
|
| 318 |
+
| 0.516 | 5.3939 | 534 | 0.6613 | 0.5787 | 0.6613 | 0.8132 |
|
| 319 |
+
| 0.516 | 5.4141 | 536 | 0.8373 | 0.5098 | 0.8373 | 0.9151 |
|
| 320 |
+
| 0.516 | 5.4343 | 538 | 0.7020 | 0.5776 | 0.7020 | 0.8379 |
|
| 321 |
+
|
| 322 |
+
|
| 323 |
+
### Framework versions
|
| 324 |
+
|
| 325 |
+
- Transformers 4.44.2
|
| 326 |
+
- Pytorch 2.4.0+cu118
|
| 327 |
+
- Datasets 2.21.0
|
| 328 |
+
- 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 sha256:399b23da672c947f56b285e8e1c41cdbfb5efe4318fdc4591a6800df6f4b342d
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b0ded030968736a57648e973e7ba836ff79e3dfb609b6878cd7ea871b0160cf
|
| 3 |
+
size 5240
|