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: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask3_vocabulary
|
| 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_TestTask3_vocabulary
|
| 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: 0.5136
|
| 19 |
+
- Qwk: 0.6644
|
| 20 |
+
- Mse: 0.5136
|
| 21 |
+
- Rmse: 0.7166
|
| 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 | 0.0194 | 2 | 4.9158 | -0.0091 | 4.9158 | 2.2172 |
|
| 53 |
+
| No log | 0.0388 | 4 | 3.2213 | 0.0932 | 3.2213 | 1.7948 |
|
| 54 |
+
| No log | 0.0583 | 6 | 2.0330 | 0.0181 | 2.0330 | 1.4258 |
|
| 55 |
+
| No log | 0.0777 | 8 | 1.1038 | 0.1866 | 1.1038 | 1.0506 |
|
| 56 |
+
| No log | 0.0971 | 10 | 0.9256 | 0.0710 | 0.9256 | 0.9621 |
|
| 57 |
+
| No log | 0.1165 | 12 | 0.9407 | 0.1116 | 0.9407 | 0.9699 |
|
| 58 |
+
| No log | 0.1359 | 14 | 0.8663 | 0.1851 | 0.8663 | 0.9308 |
|
| 59 |
+
| No log | 0.1553 | 16 | 0.8053 | 0.1939 | 0.8053 | 0.8974 |
|
| 60 |
+
| No log | 0.1748 | 18 | 0.8264 | 0.2969 | 0.8264 | 0.9091 |
|
| 61 |
+
| No log | 0.1942 | 20 | 0.7996 | 0.3128 | 0.7996 | 0.8942 |
|
| 62 |
+
| No log | 0.2136 | 22 | 0.7672 | 0.3070 | 0.7672 | 0.8759 |
|
| 63 |
+
| No log | 0.2330 | 24 | 0.7423 | 0.3493 | 0.7423 | 0.8615 |
|
| 64 |
+
| No log | 0.2524 | 26 | 0.7053 | 0.3773 | 0.7053 | 0.8398 |
|
| 65 |
+
| No log | 0.2718 | 28 | 0.6931 | 0.4285 | 0.6931 | 0.8325 |
|
| 66 |
+
| No log | 0.2913 | 30 | 0.6954 | 0.4323 | 0.6954 | 0.8339 |
|
| 67 |
+
| No log | 0.3107 | 32 | 0.6209 | 0.5082 | 0.6209 | 0.7880 |
|
| 68 |
+
| No log | 0.3301 | 34 | 0.6336 | 0.5154 | 0.6336 | 0.7960 |
|
| 69 |
+
| No log | 0.3495 | 36 | 0.6071 | 0.5417 | 0.6071 | 0.7792 |
|
| 70 |
+
| No log | 0.3689 | 38 | 0.6171 | 0.5560 | 0.6171 | 0.7856 |
|
| 71 |
+
| No log | 0.3883 | 40 | 0.6871 | 0.5063 | 0.6871 | 0.8289 |
|
| 72 |
+
| No log | 0.4078 | 42 | 0.6788 | 0.5518 | 0.6788 | 0.8239 |
|
| 73 |
+
| No log | 0.4272 | 44 | 0.5825 | 0.5694 | 0.5825 | 0.7632 |
|
| 74 |
+
| No log | 0.4466 | 46 | 0.5647 | 0.5919 | 0.5647 | 0.7515 |
|
| 75 |
+
| No log | 0.4660 | 48 | 0.5922 | 0.5468 | 0.5922 | 0.7695 |
|
| 76 |
+
| No log | 0.4854 | 50 | 0.8638 | 0.5181 | 0.8638 | 0.9294 |
|
| 77 |
+
| No log | 0.5049 | 52 | 0.9877 | 0.4587 | 0.9877 | 0.9938 |
|
| 78 |
+
| No log | 0.5243 | 54 | 0.7382 | 0.5530 | 0.7382 | 0.8592 |
|
| 79 |
+
| No log | 0.5437 | 56 | 0.5330 | 0.6057 | 0.5330 | 0.7301 |
|
| 80 |
+
| No log | 0.5631 | 58 | 0.6112 | 0.5057 | 0.6112 | 0.7818 |
|
| 81 |
+
| No log | 0.5825 | 60 | 0.7426 | 0.3704 | 0.7426 | 0.8617 |
|
| 82 |
+
| No log | 0.6019 | 62 | 0.6928 | 0.3671 | 0.6928 | 0.8323 |
|
| 83 |
+
| No log | 0.6214 | 64 | 0.6037 | 0.4514 | 0.6037 | 0.7770 |
|
| 84 |
+
| No log | 0.6408 | 66 | 0.5612 | 0.5421 | 0.5612 | 0.7491 |
|
| 85 |
+
| No log | 0.6602 | 68 | 0.5471 | 0.5701 | 0.5471 | 0.7396 |
|
| 86 |
+
| No log | 0.6796 | 70 | 0.5725 | 0.4782 | 0.5725 | 0.7566 |
|
| 87 |
+
| No log | 0.6990 | 72 | 0.5697 | 0.4861 | 0.5697 | 0.7548 |
|
| 88 |
+
| No log | 0.7184 | 74 | 0.5511 | 0.5503 | 0.5511 | 0.7424 |
|
| 89 |
+
| No log | 0.7379 | 76 | 0.6017 | 0.5792 | 0.6017 | 0.7757 |
|
| 90 |
+
| No log | 0.7573 | 78 | 0.5777 | 0.6096 | 0.5777 | 0.7601 |
|
| 91 |
+
| No log | 0.7767 | 80 | 0.5417 | 0.6301 | 0.5417 | 0.7360 |
|
| 92 |
+
| No log | 0.7961 | 82 | 0.5257 | 0.6334 | 0.5257 | 0.7250 |
|
| 93 |
+
| No log | 0.8155 | 84 | 0.5012 | 0.6310 | 0.5012 | 0.7079 |
|
| 94 |
+
| No log | 0.8350 | 86 | 0.4976 | 0.6246 | 0.4976 | 0.7054 |
|
| 95 |
+
| No log | 0.8544 | 88 | 0.4977 | 0.6193 | 0.4977 | 0.7055 |
|
| 96 |
+
| No log | 0.8738 | 90 | 0.5202 | 0.6239 | 0.5202 | 0.7212 |
|
| 97 |
+
| No log | 0.8932 | 92 | 0.5454 | 0.6332 | 0.5454 | 0.7385 |
|
| 98 |
+
| No log | 0.9126 | 94 | 0.5883 | 0.6282 | 0.5883 | 0.7670 |
|
| 99 |
+
| No log | 0.9320 | 96 | 0.5793 | 0.6322 | 0.5793 | 0.7611 |
|
| 100 |
+
| No log | 0.9515 | 98 | 0.5216 | 0.6243 | 0.5216 | 0.7222 |
|
| 101 |
+
| No log | 0.9709 | 100 | 0.5022 | 0.5369 | 0.5022 | 0.7086 |
|
| 102 |
+
| No log | 0.9903 | 102 | 0.6015 | 0.5407 | 0.6015 | 0.7756 |
|
| 103 |
+
| No log | 1.0097 | 104 | 0.6073 | 0.5271 | 0.6073 | 0.7793 |
|
| 104 |
+
| No log | 1.0291 | 106 | 0.5453 | 0.4956 | 0.5453 | 0.7384 |
|
| 105 |
+
| No log | 1.0485 | 108 | 0.5027 | 0.5272 | 0.5027 | 0.7090 |
|
| 106 |
+
| No log | 1.0680 | 110 | 0.5162 | 0.6383 | 0.5162 | 0.7185 |
|
| 107 |
+
| No log | 1.0874 | 112 | 0.5018 | 0.6401 | 0.5018 | 0.7084 |
|
| 108 |
+
| No log | 1.1068 | 114 | 0.4678 | 0.6687 | 0.4678 | 0.6839 |
|
| 109 |
+
| No log | 1.1262 | 116 | 0.5719 | 0.6737 | 0.5719 | 0.7562 |
|
| 110 |
+
| No log | 1.1456 | 118 | 0.6392 | 0.6595 | 0.6392 | 0.7995 |
|
| 111 |
+
| No log | 1.1650 | 120 | 0.5110 | 0.6874 | 0.5110 | 0.7148 |
|
| 112 |
+
| No log | 1.1845 | 122 | 0.4518 | 0.6910 | 0.4518 | 0.6722 |
|
| 113 |
+
| No log | 1.2039 | 124 | 0.5736 | 0.6334 | 0.5736 | 0.7574 |
|
| 114 |
+
| No log | 1.2233 | 126 | 0.7401 | 0.5260 | 0.7401 | 0.8603 |
|
| 115 |
+
| No log | 1.2427 | 128 | 0.7479 | 0.4511 | 0.7479 | 0.8648 |
|
| 116 |
+
| No log | 1.2621 | 130 | 0.6988 | 0.4070 | 0.6988 | 0.8360 |
|
| 117 |
+
| No log | 1.2816 | 132 | 0.6364 | 0.5184 | 0.6364 | 0.7978 |
|
| 118 |
+
| No log | 1.3010 | 134 | 0.6632 | 0.5312 | 0.6632 | 0.8144 |
|
| 119 |
+
| No log | 1.3204 | 136 | 0.6888 | 0.5408 | 0.6888 | 0.8299 |
|
| 120 |
+
| No log | 1.3398 | 138 | 0.7346 | 0.5499 | 0.7346 | 0.8571 |
|
| 121 |
+
| No log | 1.3592 | 140 | 0.5580 | 0.6149 | 0.5580 | 0.7470 |
|
| 122 |
+
| No log | 1.3786 | 142 | 0.4819 | 0.5670 | 0.4819 | 0.6942 |
|
| 123 |
+
| No log | 1.3981 | 144 | 0.4842 | 0.5933 | 0.4842 | 0.6958 |
|
| 124 |
+
| No log | 1.4175 | 146 | 0.4877 | 0.6253 | 0.4877 | 0.6984 |
|
| 125 |
+
| No log | 1.4369 | 148 | 0.4455 | 0.6811 | 0.4455 | 0.6674 |
|
| 126 |
+
| No log | 1.4563 | 150 | 0.4991 | 0.6746 | 0.4991 | 0.7065 |
|
| 127 |
+
| No log | 1.4757 | 152 | 0.5378 | 0.6631 | 0.5378 | 0.7333 |
|
| 128 |
+
| No log | 1.4951 | 154 | 0.5041 | 0.6624 | 0.5041 | 0.7100 |
|
| 129 |
+
| No log | 1.5146 | 156 | 0.5315 | 0.6538 | 0.5315 | 0.7290 |
|
| 130 |
+
| No log | 1.5340 | 158 | 0.8432 | 0.5746 | 0.8432 | 0.9183 |
|
| 131 |
+
| No log | 1.5534 | 160 | 0.9750 | 0.5291 | 0.9750 | 0.9874 |
|
| 132 |
+
| No log | 1.5728 | 162 | 0.8029 | 0.5764 | 0.8029 | 0.8960 |
|
| 133 |
+
| No log | 1.5922 | 164 | 0.5667 | 0.6145 | 0.5667 | 0.7528 |
|
| 134 |
+
| No log | 1.6117 | 166 | 0.4620 | 0.6285 | 0.4620 | 0.6797 |
|
| 135 |
+
| No log | 1.6311 | 168 | 0.4502 | 0.6411 | 0.4502 | 0.6710 |
|
| 136 |
+
| No log | 1.6505 | 170 | 0.4514 | 0.6537 | 0.4514 | 0.6718 |
|
| 137 |
+
| No log | 1.6699 | 172 | 0.5017 | 0.6646 | 0.5017 | 0.7083 |
|
| 138 |
+
| No log | 1.6893 | 174 | 0.4956 | 0.6543 | 0.4956 | 0.7040 |
|
| 139 |
+
| No log | 1.7087 | 176 | 0.5726 | 0.6613 | 0.5726 | 0.7567 |
|
| 140 |
+
| No log | 1.7282 | 178 | 0.5427 | 0.6668 | 0.5427 | 0.7367 |
|
| 141 |
+
| No log | 1.7476 | 180 | 0.4456 | 0.6179 | 0.4456 | 0.6675 |
|
| 142 |
+
| No log | 1.7670 | 182 | 0.4521 | 0.6308 | 0.4521 | 0.6724 |
|
| 143 |
+
| No log | 1.7864 | 184 | 0.4376 | 0.6492 | 0.4376 | 0.6615 |
|
| 144 |
+
| No log | 1.8058 | 186 | 0.4791 | 0.6844 | 0.4791 | 0.6922 |
|
| 145 |
+
| No log | 1.8252 | 188 | 0.4932 | 0.6869 | 0.4932 | 0.7023 |
|
| 146 |
+
| No log | 1.8447 | 190 | 0.4504 | 0.7032 | 0.4504 | 0.6711 |
|
| 147 |
+
| No log | 1.8641 | 192 | 0.4387 | 0.6782 | 0.4387 | 0.6623 |
|
| 148 |
+
| No log | 1.8835 | 194 | 0.4527 | 0.6805 | 0.4527 | 0.6728 |
|
| 149 |
+
| No log | 1.9029 | 196 | 0.4341 | 0.7007 | 0.4341 | 0.6589 |
|
| 150 |
+
| No log | 1.9223 | 198 | 0.4334 | 0.7079 | 0.4334 | 0.6584 |
|
| 151 |
+
| No log | 1.9417 | 200 | 0.4344 | 0.6754 | 0.4344 | 0.6591 |
|
| 152 |
+
| No log | 1.9612 | 202 | 0.4820 | 0.6238 | 0.4820 | 0.6943 |
|
| 153 |
+
| No log | 1.9806 | 204 | 0.6403 | 0.5502 | 0.6403 | 0.8002 |
|
| 154 |
+
| No log | 2.0 | 206 | 0.7482 | 0.5094 | 0.7482 | 0.8650 |
|
| 155 |
+
| No log | 2.0194 | 208 | 0.6766 | 0.5351 | 0.6766 | 0.8226 |
|
| 156 |
+
| No log | 2.0388 | 210 | 0.5399 | 0.5662 | 0.5399 | 0.7348 |
|
| 157 |
+
| No log | 2.0583 | 212 | 0.4729 | 0.6033 | 0.4729 | 0.6877 |
|
| 158 |
+
| No log | 2.0777 | 214 | 0.4753 | 0.6498 | 0.4753 | 0.6894 |
|
| 159 |
+
| No log | 2.0971 | 216 | 0.4935 | 0.6812 | 0.4935 | 0.7025 |
|
| 160 |
+
| No log | 2.1165 | 218 | 0.4484 | 0.6921 | 0.4484 | 0.6696 |
|
| 161 |
+
| No log | 2.1359 | 220 | 0.4512 | 0.7137 | 0.4512 | 0.6717 |
|
| 162 |
+
| No log | 2.1553 | 222 | 0.4981 | 0.6833 | 0.4981 | 0.7058 |
|
| 163 |
+
| No log | 2.1748 | 224 | 0.4509 | 0.7280 | 0.4509 | 0.6715 |
|
| 164 |
+
| No log | 2.1942 | 226 | 0.4422 | 0.6828 | 0.4422 | 0.6650 |
|
| 165 |
+
| No log | 2.2136 | 228 | 0.4465 | 0.6921 | 0.4465 | 0.6682 |
|
| 166 |
+
| No log | 2.2330 | 230 | 0.4568 | 0.7052 | 0.4568 | 0.6759 |
|
| 167 |
+
| No log | 2.2524 | 232 | 0.4713 | 0.7026 | 0.4713 | 0.6865 |
|
| 168 |
+
| No log | 2.2718 | 234 | 0.4380 | 0.7073 | 0.4380 | 0.6618 |
|
| 169 |
+
| No log | 2.2913 | 236 | 0.4423 | 0.6995 | 0.4423 | 0.6651 |
|
| 170 |
+
| No log | 2.3107 | 238 | 0.5015 | 0.6832 | 0.5015 | 0.7082 |
|
| 171 |
+
| No log | 2.3301 | 240 | 0.4571 | 0.7076 | 0.4571 | 0.6761 |
|
| 172 |
+
| No log | 2.3495 | 242 | 0.4426 | 0.7089 | 0.4426 | 0.6653 |
|
| 173 |
+
| No log | 2.3689 | 244 | 0.5016 | 0.6710 | 0.5016 | 0.7083 |
|
| 174 |
+
| No log | 2.3883 | 246 | 0.5221 | 0.6646 | 0.5221 | 0.7225 |
|
| 175 |
+
| No log | 2.4078 | 248 | 0.4532 | 0.6910 | 0.4532 | 0.6732 |
|
| 176 |
+
| No log | 2.4272 | 250 | 0.4721 | 0.6533 | 0.4721 | 0.6871 |
|
| 177 |
+
| No log | 2.4466 | 252 | 0.6486 | 0.5666 | 0.6486 | 0.8054 |
|
| 178 |
+
| No log | 2.4660 | 254 | 0.7267 | 0.5592 | 0.7267 | 0.8525 |
|
| 179 |
+
| No log | 2.4854 | 256 | 0.6393 | 0.5366 | 0.6393 | 0.7996 |
|
| 180 |
+
| No log | 2.5049 | 258 | 0.5174 | 0.5748 | 0.5174 | 0.7193 |
|
| 181 |
+
| No log | 2.5243 | 260 | 0.4680 | 0.5898 | 0.4680 | 0.6841 |
|
| 182 |
+
| No log | 2.5437 | 262 | 0.4921 | 0.6295 | 0.4921 | 0.7015 |
|
| 183 |
+
| No log | 2.5631 | 264 | 0.4745 | 0.6493 | 0.4745 | 0.6889 |
|
| 184 |
+
| No log | 2.5825 | 266 | 0.5415 | 0.6504 | 0.5415 | 0.7359 |
|
| 185 |
+
| No log | 2.6019 | 268 | 0.7579 | 0.5523 | 0.7579 | 0.8706 |
|
| 186 |
+
| No log | 2.6214 | 270 | 0.6364 | 0.5884 | 0.6364 | 0.7977 |
|
| 187 |
+
| No log | 2.6408 | 272 | 0.4756 | 0.6946 | 0.4756 | 0.6896 |
|
| 188 |
+
| No log | 2.6602 | 274 | 0.6544 | 0.6441 | 0.6544 | 0.8089 |
|
| 189 |
+
| No log | 2.6796 | 276 | 0.6753 | 0.6463 | 0.6753 | 0.8218 |
|
| 190 |
+
| No log | 2.6990 | 278 | 0.5889 | 0.6859 | 0.5889 | 0.7674 |
|
| 191 |
+
| No log | 2.7184 | 280 | 0.5004 | 0.6511 | 0.5004 | 0.7074 |
|
| 192 |
+
| No log | 2.7379 | 282 | 0.4758 | 0.6684 | 0.4758 | 0.6897 |
|
| 193 |
+
| No log | 2.7573 | 284 | 0.4707 | 0.6658 | 0.4707 | 0.6861 |
|
| 194 |
+
| No log | 2.7767 | 286 | 0.4598 | 0.6704 | 0.4598 | 0.6781 |
|
| 195 |
+
| No log | 2.7961 | 288 | 0.4535 | 0.6700 | 0.4535 | 0.6734 |
|
| 196 |
+
| No log | 2.8155 | 290 | 0.4598 | 0.6771 | 0.4598 | 0.6781 |
|
| 197 |
+
| No log | 2.8350 | 292 | 0.4619 | 0.6816 | 0.4619 | 0.6796 |
|
| 198 |
+
| No log | 2.8544 | 294 | 0.4753 | 0.6952 | 0.4753 | 0.6895 |
|
| 199 |
+
| No log | 2.8738 | 296 | 0.5110 | 0.7294 | 0.5110 | 0.7148 |
|
| 200 |
+
| No log | 2.8932 | 298 | 0.5886 | 0.7283 | 0.5886 | 0.7672 |
|
| 201 |
+
| No log | 2.9126 | 300 | 0.6281 | 0.6810 | 0.6281 | 0.7925 |
|
| 202 |
+
| No log | 2.9320 | 302 | 0.5759 | 0.6927 | 0.5759 | 0.7589 |
|
| 203 |
+
| No log | 2.9515 | 304 | 0.5321 | 0.6928 | 0.5321 | 0.7295 |
|
| 204 |
+
| No log | 2.9709 | 306 | 0.4946 | 0.6939 | 0.4946 | 0.7033 |
|
| 205 |
+
| No log | 2.9903 | 308 | 0.4623 | 0.6665 | 0.4623 | 0.6799 |
|
| 206 |
+
| No log | 3.0097 | 310 | 0.4413 | 0.6529 | 0.4413 | 0.6643 |
|
| 207 |
+
| No log | 3.0291 | 312 | 0.4423 | 0.6564 | 0.4423 | 0.6650 |
|
| 208 |
+
| No log | 3.0485 | 314 | 0.4552 | 0.6402 | 0.4552 | 0.6747 |
|
| 209 |
+
| No log | 3.0680 | 316 | 0.4748 | 0.6249 | 0.4748 | 0.6890 |
|
| 210 |
+
| No log | 3.0874 | 318 | 0.4493 | 0.6587 | 0.4493 | 0.6703 |
|
| 211 |
+
| No log | 3.1068 | 320 | 0.4759 | 0.6797 | 0.4759 | 0.6899 |
|
| 212 |
+
| No log | 3.1262 | 322 | 0.6334 | 0.6429 | 0.6334 | 0.7959 |
|
| 213 |
+
| No log | 3.1456 | 324 | 0.6790 | 0.6251 | 0.6790 | 0.8240 |
|
| 214 |
+
| No log | 3.1650 | 326 | 0.5726 | 0.6531 | 0.5726 | 0.7567 |
|
| 215 |
+
| No log | 3.1845 | 328 | 0.4479 | 0.6946 | 0.4479 | 0.6693 |
|
| 216 |
+
| No log | 3.2039 | 330 | 0.4758 | 0.6608 | 0.4758 | 0.6898 |
|
| 217 |
+
| No log | 3.2233 | 332 | 0.6186 | 0.6172 | 0.6186 | 0.7865 |
|
| 218 |
+
| No log | 3.2427 | 334 | 0.6132 | 0.6076 | 0.6132 | 0.7831 |
|
| 219 |
+
| No log | 3.2621 | 336 | 0.4894 | 0.6193 | 0.4894 | 0.6995 |
|
| 220 |
+
| No log | 3.2816 | 338 | 0.4431 | 0.6353 | 0.4431 | 0.6657 |
|
| 221 |
+
| No log | 3.3010 | 340 | 0.5654 | 0.6369 | 0.5654 | 0.7520 |
|
| 222 |
+
| No log | 3.3204 | 342 | 0.6348 | 0.6453 | 0.6348 | 0.7967 |
|
| 223 |
+
| No log | 3.3398 | 344 | 0.5883 | 0.6557 | 0.5883 | 0.7670 |
|
| 224 |
+
| No log | 3.3592 | 346 | 0.4703 | 0.6463 | 0.4703 | 0.6858 |
|
| 225 |
+
| No log | 3.3786 | 348 | 0.4393 | 0.6828 | 0.4393 | 0.6628 |
|
| 226 |
+
| No log | 3.3981 | 350 | 0.4852 | 0.6869 | 0.4852 | 0.6966 |
|
| 227 |
+
| No log | 3.4175 | 352 | 0.5126 | 0.6638 | 0.5126 | 0.7159 |
|
| 228 |
+
| No log | 3.4369 | 354 | 0.5311 | 0.6397 | 0.5311 | 0.7287 |
|
| 229 |
+
| No log | 3.4563 | 356 | 0.5566 | 0.6511 | 0.5566 | 0.7461 |
|
| 230 |
+
| No log | 3.4757 | 358 | 0.5242 | 0.6643 | 0.5242 | 0.7240 |
|
| 231 |
+
| No log | 3.4951 | 360 | 0.4942 | 0.6423 | 0.4942 | 0.7030 |
|
| 232 |
+
| No log | 3.5146 | 362 | 0.4559 | 0.6490 | 0.4559 | 0.6752 |
|
| 233 |
+
| No log | 3.5340 | 364 | 0.4363 | 0.6517 | 0.4363 | 0.6605 |
|
| 234 |
+
| No log | 3.5534 | 366 | 0.4395 | 0.6276 | 0.4395 | 0.6629 |
|
| 235 |
+
| No log | 3.5728 | 368 | 0.4524 | 0.6144 | 0.4524 | 0.6726 |
|
| 236 |
+
| No log | 3.5922 | 370 | 0.4660 | 0.5916 | 0.4660 | 0.6826 |
|
| 237 |
+
| No log | 3.6117 | 372 | 0.4527 | 0.6080 | 0.4527 | 0.6729 |
|
| 238 |
+
| No log | 3.6311 | 374 | 0.4321 | 0.6594 | 0.4321 | 0.6574 |
|
| 239 |
+
| No log | 3.6505 | 376 | 0.4373 | 0.7015 | 0.4373 | 0.6613 |
|
| 240 |
+
| No log | 3.6699 | 378 | 0.4596 | 0.7031 | 0.4596 | 0.6779 |
|
| 241 |
+
| No log | 3.6893 | 380 | 0.4920 | 0.7384 | 0.4920 | 0.7014 |
|
| 242 |
+
| No log | 3.7087 | 382 | 0.4819 | 0.7333 | 0.4819 | 0.6942 |
|
| 243 |
+
| No log | 3.7282 | 384 | 0.4468 | 0.7142 | 0.4468 | 0.6684 |
|
| 244 |
+
| No log | 3.7476 | 386 | 0.4363 | 0.7110 | 0.4363 | 0.6606 |
|
| 245 |
+
| No log | 3.7670 | 388 | 0.4644 | 0.6779 | 0.4644 | 0.6814 |
|
| 246 |
+
| No log | 3.7864 | 390 | 0.6443 | 0.5920 | 0.6443 | 0.8027 |
|
| 247 |
+
| No log | 3.8058 | 392 | 0.7543 | 0.5308 | 0.7543 | 0.8685 |
|
| 248 |
+
| No log | 3.8252 | 394 | 0.6539 | 0.5566 | 0.6539 | 0.8086 |
|
| 249 |
+
| No log | 3.8447 | 396 | 0.5486 | 0.6128 | 0.5486 | 0.7406 |
|
| 250 |
+
| No log | 3.8641 | 398 | 0.4718 | 0.6205 | 0.4718 | 0.6869 |
|
| 251 |
+
| No log | 3.8835 | 400 | 0.4829 | 0.6177 | 0.4829 | 0.6949 |
|
| 252 |
+
| No log | 3.9029 | 402 | 0.4548 | 0.6646 | 0.4548 | 0.6744 |
|
| 253 |
+
| No log | 3.9223 | 404 | 0.4366 | 0.6724 | 0.4366 | 0.6607 |
|
| 254 |
+
| No log | 3.9417 | 406 | 0.5033 | 0.6967 | 0.5033 | 0.7095 |
|
| 255 |
+
| No log | 3.9612 | 408 | 0.4971 | 0.6966 | 0.4971 | 0.7051 |
|
| 256 |
+
| No log | 3.9806 | 410 | 0.4849 | 0.7252 | 0.4849 | 0.6964 |
|
| 257 |
+
| No log | 4.0 | 412 | 0.4537 | 0.7171 | 0.4537 | 0.6736 |
|
| 258 |
+
| No log | 4.0194 | 414 | 0.4608 | 0.7148 | 0.4608 | 0.6788 |
|
| 259 |
+
| No log | 4.0388 | 416 | 0.4373 | 0.7196 | 0.4373 | 0.6613 |
|
| 260 |
+
| No log | 4.0583 | 418 | 0.4400 | 0.6962 | 0.4400 | 0.6633 |
|
| 261 |
+
| No log | 4.0777 | 420 | 0.4351 | 0.7043 | 0.4351 | 0.6596 |
|
| 262 |
+
| No log | 4.0971 | 422 | 0.4215 | 0.6971 | 0.4215 | 0.6492 |
|
| 263 |
+
| No log | 4.1165 | 424 | 0.4488 | 0.6892 | 0.4488 | 0.6699 |
|
| 264 |
+
| No log | 4.1359 | 426 | 0.4257 | 0.6739 | 0.4257 | 0.6524 |
|
| 265 |
+
| No log | 4.1553 | 428 | 0.4830 | 0.6629 | 0.4830 | 0.6949 |
|
| 266 |
+
| No log | 4.1748 | 430 | 0.5567 | 0.6497 | 0.5567 | 0.7461 |
|
| 267 |
+
| No log | 4.1942 | 432 | 0.5436 | 0.6922 | 0.5436 | 0.7373 |
|
| 268 |
+
| No log | 4.2136 | 434 | 0.4617 | 0.7004 | 0.4617 | 0.6795 |
|
| 269 |
+
| No log | 4.2330 | 436 | 0.4309 | 0.7176 | 0.4309 | 0.6564 |
|
| 270 |
+
| No log | 4.2524 | 438 | 0.4357 | 0.7464 | 0.4357 | 0.6601 |
|
| 271 |
+
| No log | 4.2718 | 440 | 0.4719 | 0.7410 | 0.4719 | 0.6869 |
|
| 272 |
+
| No log | 4.2913 | 442 | 0.6162 | 0.6809 | 0.6162 | 0.7850 |
|
| 273 |
+
| No log | 4.3107 | 444 | 0.5812 | 0.6872 | 0.5812 | 0.7624 |
|
| 274 |
+
| No log | 4.3301 | 446 | 0.4493 | 0.7030 | 0.4493 | 0.6703 |
|
| 275 |
+
| No log | 4.3495 | 448 | 0.4252 | 0.6785 | 0.4252 | 0.6521 |
|
| 276 |
+
| No log | 4.3689 | 450 | 0.4876 | 0.6191 | 0.4876 | 0.6983 |
|
| 277 |
+
| No log | 4.3883 | 452 | 0.4719 | 0.6192 | 0.4719 | 0.6869 |
|
| 278 |
+
| No log | 4.4078 | 454 | 0.4536 | 0.6234 | 0.4536 | 0.6735 |
|
| 279 |
+
| No log | 4.4272 | 456 | 0.4521 | 0.6246 | 0.4521 | 0.6724 |
|
| 280 |
+
| No log | 4.4466 | 458 | 0.4544 | 0.6726 | 0.4544 | 0.6741 |
|
| 281 |
+
| No log | 4.4660 | 460 | 0.5109 | 0.6737 | 0.5109 | 0.7147 |
|
| 282 |
+
| No log | 4.4854 | 462 | 0.4862 | 0.6985 | 0.4862 | 0.6973 |
|
| 283 |
+
| No log | 4.5049 | 464 | 0.4656 | 0.7203 | 0.4656 | 0.6824 |
|
| 284 |
+
| No log | 4.5243 | 466 | 0.5105 | 0.6985 | 0.5105 | 0.7145 |
|
| 285 |
+
| No log | 4.5437 | 468 | 0.5725 | 0.6689 | 0.5725 | 0.7566 |
|
| 286 |
+
| No log | 4.5631 | 470 | 0.5264 | 0.6979 | 0.5264 | 0.7255 |
|
| 287 |
+
| No log | 4.5825 | 472 | 0.5143 | 0.7240 | 0.5143 | 0.7172 |
|
| 288 |
+
| No log | 4.6019 | 474 | 0.5417 | 0.6965 | 0.5417 | 0.7360 |
|
| 289 |
+
| No log | 4.6214 | 476 | 0.5395 | 0.6831 | 0.5395 | 0.7345 |
|
| 290 |
+
| No log | 4.6408 | 478 | 0.4970 | 0.6756 | 0.4970 | 0.7049 |
|
| 291 |
+
| No log | 4.6602 | 480 | 0.4897 | 0.6814 | 0.4897 | 0.6998 |
|
| 292 |
+
| No log | 4.6796 | 482 | 0.4669 | 0.6759 | 0.4669 | 0.6833 |
|
| 293 |
+
| No log | 4.6990 | 484 | 0.4537 | 0.7009 | 0.4537 | 0.6736 |
|
| 294 |
+
| No log | 4.7184 | 486 | 0.4829 | 0.7341 | 0.4829 | 0.6949 |
|
| 295 |
+
| No log | 4.7379 | 488 | 0.5553 | 0.7076 | 0.5553 | 0.7452 |
|
| 296 |
+
| No log | 4.7573 | 490 | 0.5574 | 0.7205 | 0.5574 | 0.7466 |
|
| 297 |
+
| No log | 4.7767 | 492 | 0.5143 | 0.7137 | 0.5143 | 0.7171 |
|
| 298 |
+
| No log | 4.7961 | 494 | 0.4803 | 0.7105 | 0.4803 | 0.6930 |
|
| 299 |
+
| No log | 4.8155 | 496 | 0.4504 | 0.7153 | 0.4504 | 0.6711 |
|
| 300 |
+
| No log | 4.8350 | 498 | 0.4429 | 0.7014 | 0.4429 | 0.6655 |
|
| 301 |
+
| 0.5147 | 4.8544 | 500 | 0.4354 | 0.6832 | 0.4354 | 0.6598 |
|
| 302 |
+
| 0.5147 | 4.8738 | 502 | 0.4604 | 0.6595 | 0.4604 | 0.6785 |
|
| 303 |
+
| 0.5147 | 4.8932 | 504 | 0.4565 | 0.6583 | 0.4565 | 0.6756 |
|
| 304 |
+
| 0.5147 | 4.9126 | 506 | 0.4307 | 0.6805 | 0.4307 | 0.6563 |
|
| 305 |
+
| 0.5147 | 4.9320 | 508 | 0.4725 | 0.6711 | 0.4725 | 0.6874 |
|
| 306 |
+
| 0.5147 | 4.9515 | 510 | 0.5136 | 0.6644 | 0.5136 | 0.7166 |
|
| 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 sha256:058d2ea0d7c189090f9dbcecb8dd6ce93875b446e83703bfe9b731e053267b87
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9030f682c666f7884b0e5402ab5593fda3e6e5d673488fb4018f0e7986b7a241
|
| 3 |
+
size 5240
|