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_TestTask8_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_TestTask8_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: 1.1541
|
| 19 |
+
- Qwk: 0.4137
|
| 20 |
+
- Mse: 1.1541
|
| 21 |
+
- Rmse: 1.0743
|
| 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 | 0.0196 | 2 | 4.6665 | 0.0108 | 4.6665 | 2.1602 |
|
| 53 |
+
| No log | 0.0392 | 4 | 3.6593 | 0.0367 | 3.6593 | 1.9129 |
|
| 54 |
+
| No log | 0.0588 | 6 | 2.0428 | 0.0808 | 2.0428 | 1.4293 |
|
| 55 |
+
| No log | 0.0784 | 8 | 0.9602 | 0.1798 | 0.9602 | 0.9799 |
|
| 56 |
+
| No log | 0.0980 | 10 | 0.7992 | 0.1622 | 0.7992 | 0.8940 |
|
| 57 |
+
| No log | 0.1176 | 12 | 0.8159 | 0.1181 | 0.8159 | 0.9033 |
|
| 58 |
+
| No log | 0.1373 | 14 | 0.7635 | 0.3098 | 0.7635 | 0.8738 |
|
| 59 |
+
| No log | 0.1569 | 16 | 0.8561 | 0.3451 | 0.8561 | 0.9253 |
|
| 60 |
+
| No log | 0.1765 | 18 | 0.6892 | 0.3942 | 0.6892 | 0.8302 |
|
| 61 |
+
| No log | 0.1961 | 20 | 0.7363 | 0.4052 | 0.7363 | 0.8581 |
|
| 62 |
+
| No log | 0.2157 | 22 | 0.7910 | 0.2309 | 0.7910 | 0.8894 |
|
| 63 |
+
| No log | 0.2353 | 24 | 0.9228 | 0.0177 | 0.9228 | 0.9606 |
|
| 64 |
+
| No log | 0.2549 | 26 | 0.8609 | 0.0740 | 0.8609 | 0.9279 |
|
| 65 |
+
| No log | 0.2745 | 28 | 0.6962 | 0.2557 | 0.6962 | 0.8344 |
|
| 66 |
+
| No log | 0.2941 | 30 | 0.5877 | 0.4365 | 0.5877 | 0.7666 |
|
| 67 |
+
| No log | 0.3137 | 32 | 0.6307 | 0.4433 | 0.6307 | 0.7942 |
|
| 68 |
+
| No log | 0.3333 | 34 | 0.5963 | 0.4920 | 0.5963 | 0.7722 |
|
| 69 |
+
| No log | 0.3529 | 36 | 0.5625 | 0.5120 | 0.5625 | 0.7500 |
|
| 70 |
+
| No log | 0.3725 | 38 | 0.6726 | 0.4113 | 0.6726 | 0.8201 |
|
| 71 |
+
| No log | 0.3922 | 40 | 0.7038 | 0.3033 | 0.7038 | 0.8389 |
|
| 72 |
+
| No log | 0.4118 | 42 | 0.6342 | 0.3713 | 0.6342 | 0.7963 |
|
| 73 |
+
| No log | 0.4314 | 44 | 0.5829 | 0.4489 | 0.5829 | 0.7635 |
|
| 74 |
+
| No log | 0.4510 | 46 | 0.5868 | 0.4642 | 0.5868 | 0.7660 |
|
| 75 |
+
| No log | 0.4706 | 48 | 0.5946 | 0.4678 | 0.5946 | 0.7711 |
|
| 76 |
+
| No log | 0.4902 | 50 | 0.5810 | 0.4294 | 0.5810 | 0.7622 |
|
| 77 |
+
| No log | 0.5098 | 52 | 0.5345 | 0.4221 | 0.5345 | 0.7311 |
|
| 78 |
+
| No log | 0.5294 | 54 | 0.5094 | 0.4302 | 0.5094 | 0.7137 |
|
| 79 |
+
| No log | 0.5490 | 56 | 0.5386 | 0.4316 | 0.5386 | 0.7339 |
|
| 80 |
+
| No log | 0.5686 | 58 | 0.5933 | 0.4128 | 0.5933 | 0.7703 |
|
| 81 |
+
| No log | 0.5882 | 60 | 0.6873 | 0.3909 | 0.6873 | 0.8291 |
|
| 82 |
+
| No log | 0.6078 | 62 | 0.6825 | 0.4340 | 0.6825 | 0.8261 |
|
| 83 |
+
| No log | 0.6275 | 64 | 0.6071 | 0.5436 | 0.6071 | 0.7792 |
|
| 84 |
+
| No log | 0.6471 | 66 | 0.5447 | 0.6146 | 0.5447 | 0.7381 |
|
| 85 |
+
| No log | 0.6667 | 68 | 0.4726 | 0.6243 | 0.4726 | 0.6875 |
|
| 86 |
+
| No log | 0.6863 | 70 | 0.4617 | 0.6475 | 0.4617 | 0.6795 |
|
| 87 |
+
| No log | 0.7059 | 72 | 0.5190 | 0.6321 | 0.5190 | 0.7204 |
|
| 88 |
+
| No log | 0.7255 | 74 | 0.4766 | 0.6629 | 0.4766 | 0.6904 |
|
| 89 |
+
| No log | 0.7451 | 76 | 0.5066 | 0.6681 | 0.5066 | 0.7118 |
|
| 90 |
+
| No log | 0.7647 | 78 | 0.6468 | 0.5397 | 0.6468 | 0.8043 |
|
| 91 |
+
| No log | 0.7843 | 80 | 0.6336 | 0.5465 | 0.6336 | 0.7960 |
|
| 92 |
+
| No log | 0.8039 | 82 | 0.5293 | 0.4872 | 0.5293 | 0.7276 |
|
| 93 |
+
| No log | 0.8235 | 84 | 0.5339 | 0.5680 | 0.5339 | 0.7307 |
|
| 94 |
+
| No log | 0.8431 | 86 | 0.6458 | 0.5156 | 0.6458 | 0.8036 |
|
| 95 |
+
| No log | 0.8627 | 88 | 0.6336 | 0.5204 | 0.6336 | 0.7960 |
|
| 96 |
+
| No log | 0.8824 | 90 | 0.5097 | 0.5856 | 0.5097 | 0.7139 |
|
| 97 |
+
| No log | 0.9020 | 92 | 0.4953 | 0.4911 | 0.4953 | 0.7038 |
|
| 98 |
+
| No log | 0.9216 | 94 | 0.5481 | 0.4987 | 0.5481 | 0.7403 |
|
| 99 |
+
| No log | 0.9412 | 96 | 0.6404 | 0.4835 | 0.6404 | 0.8003 |
|
| 100 |
+
| No log | 0.9608 | 98 | 0.6058 | 0.4651 | 0.6058 | 0.7783 |
|
| 101 |
+
| No log | 0.9804 | 100 | 0.5402 | 0.4272 | 0.5402 | 0.7350 |
|
| 102 |
+
| No log | 1.0 | 102 | 0.5149 | 0.4887 | 0.5149 | 0.7175 |
|
| 103 |
+
| No log | 1.0196 | 104 | 0.4928 | 0.5260 | 0.4928 | 0.7020 |
|
| 104 |
+
| No log | 1.0392 | 106 | 0.4908 | 0.5549 | 0.4908 | 0.7006 |
|
| 105 |
+
| No log | 1.0588 | 108 | 0.5213 | 0.5391 | 0.5213 | 0.7220 |
|
| 106 |
+
| No log | 1.0784 | 110 | 0.5177 | 0.5567 | 0.5177 | 0.7195 |
|
| 107 |
+
| No log | 1.0980 | 112 | 0.4785 | 0.6352 | 0.4785 | 0.6917 |
|
| 108 |
+
| No log | 1.1176 | 114 | 0.4813 | 0.6326 | 0.4813 | 0.6938 |
|
| 109 |
+
| No log | 1.1373 | 116 | 0.4926 | 0.6358 | 0.4926 | 0.7018 |
|
| 110 |
+
| No log | 1.1569 | 118 | 0.5730 | 0.5368 | 0.5730 | 0.7570 |
|
| 111 |
+
| No log | 1.1765 | 120 | 0.5955 | 0.4977 | 0.5955 | 0.7717 |
|
| 112 |
+
| No log | 1.1961 | 122 | 0.5461 | 0.5295 | 0.5461 | 0.7390 |
|
| 113 |
+
| No log | 1.2157 | 124 | 0.4687 | 0.6080 | 0.4687 | 0.6846 |
|
| 114 |
+
| No log | 1.2353 | 126 | 0.4648 | 0.6402 | 0.4648 | 0.6817 |
|
| 115 |
+
| No log | 1.2549 | 128 | 0.4722 | 0.6382 | 0.4722 | 0.6872 |
|
| 116 |
+
| No log | 1.2745 | 130 | 0.4883 | 0.6479 | 0.4883 | 0.6988 |
|
| 117 |
+
| No log | 1.2941 | 132 | 0.5171 | 0.6730 | 0.5171 | 0.7191 |
|
| 118 |
+
| No log | 1.3137 | 134 | 0.5949 | 0.6131 | 0.5949 | 0.7713 |
|
| 119 |
+
| No log | 1.3333 | 136 | 0.6381 | 0.6094 | 0.6381 | 0.7988 |
|
| 120 |
+
| No log | 1.3529 | 138 | 0.5281 | 0.6637 | 0.5281 | 0.7267 |
|
| 121 |
+
| No log | 1.3725 | 140 | 0.4765 | 0.6983 | 0.4765 | 0.6903 |
|
| 122 |
+
| No log | 1.3922 | 142 | 0.5037 | 0.6542 | 0.5037 | 0.7097 |
|
| 123 |
+
| No log | 1.4118 | 144 | 0.5388 | 0.6385 | 0.5388 | 0.7341 |
|
| 124 |
+
| No log | 1.4314 | 146 | 0.5120 | 0.6027 | 0.5120 | 0.7155 |
|
| 125 |
+
| No log | 1.4510 | 148 | 0.4459 | 0.6334 | 0.4459 | 0.6677 |
|
| 126 |
+
| No log | 1.4706 | 150 | 0.4478 | 0.5996 | 0.4478 | 0.6692 |
|
| 127 |
+
| No log | 1.4902 | 152 | 0.4943 | 0.5984 | 0.4943 | 0.7030 |
|
| 128 |
+
| No log | 1.5098 | 154 | 0.5852 | 0.5646 | 0.5852 | 0.7650 |
|
| 129 |
+
| No log | 1.5294 | 156 | 0.6282 | 0.5216 | 0.6282 | 0.7926 |
|
| 130 |
+
| No log | 1.5490 | 158 | 0.6769 | 0.5158 | 0.6769 | 0.8227 |
|
| 131 |
+
| No log | 1.5686 | 160 | 0.5846 | 0.5780 | 0.5846 | 0.7646 |
|
| 132 |
+
| No log | 1.5882 | 162 | 0.4731 | 0.6097 | 0.4731 | 0.6878 |
|
| 133 |
+
| No log | 1.6078 | 164 | 0.4387 | 0.6364 | 0.4387 | 0.6623 |
|
| 134 |
+
| No log | 1.6275 | 166 | 0.4226 | 0.6399 | 0.4226 | 0.6501 |
|
| 135 |
+
| No log | 1.6471 | 168 | 0.4096 | 0.6776 | 0.4096 | 0.6400 |
|
| 136 |
+
| No log | 1.6667 | 170 | 0.5214 | 0.6180 | 0.5214 | 0.7221 |
|
| 137 |
+
| No log | 1.6863 | 172 | 0.7892 | 0.4572 | 0.7892 | 0.8884 |
|
| 138 |
+
| No log | 1.7059 | 174 | 0.8675 | 0.4051 | 0.8675 | 0.9314 |
|
| 139 |
+
| No log | 1.7255 | 176 | 0.8054 | 0.4451 | 0.8054 | 0.8975 |
|
| 140 |
+
| No log | 1.7451 | 178 | 0.7479 | 0.3709 | 0.7479 | 0.8648 |
|
| 141 |
+
| No log | 1.7647 | 180 | 0.6472 | 0.3935 | 0.6472 | 0.8045 |
|
| 142 |
+
| No log | 1.7843 | 182 | 0.6338 | 0.4099 | 0.6338 | 0.7961 |
|
| 143 |
+
| No log | 1.8039 | 184 | 0.6872 | 0.4359 | 0.6872 | 0.8290 |
|
| 144 |
+
| No log | 1.8235 | 186 | 0.6785 | 0.4427 | 0.6785 | 0.8237 |
|
| 145 |
+
| No log | 1.8431 | 188 | 0.6442 | 0.4487 | 0.6442 | 0.8026 |
|
| 146 |
+
| No log | 1.8627 | 190 | 0.5911 | 0.4535 | 0.5911 | 0.7688 |
|
| 147 |
+
| No log | 1.8824 | 192 | 0.5084 | 0.5201 | 0.5084 | 0.7130 |
|
| 148 |
+
| No log | 1.9020 | 194 | 0.4296 | 0.6170 | 0.4296 | 0.6555 |
|
| 149 |
+
| No log | 1.9216 | 196 | 0.4087 | 0.6970 | 0.4087 | 0.6393 |
|
| 150 |
+
| No log | 1.9412 | 198 | 0.4103 | 0.7251 | 0.4103 | 0.6406 |
|
| 151 |
+
| No log | 1.9608 | 200 | 0.4104 | 0.7009 | 0.4104 | 0.6406 |
|
| 152 |
+
| No log | 1.9804 | 202 | 0.4596 | 0.6691 | 0.4596 | 0.6780 |
|
| 153 |
+
| No log | 2.0 | 204 | 0.4952 | 0.6559 | 0.4952 | 0.7037 |
|
| 154 |
+
| No log | 2.0196 | 206 | 0.4846 | 0.6652 | 0.4846 | 0.6961 |
|
| 155 |
+
| No log | 2.0392 | 208 | 0.4455 | 0.6767 | 0.4455 | 0.6675 |
|
| 156 |
+
| No log | 2.0588 | 210 | 0.4160 | 0.6898 | 0.4160 | 0.6450 |
|
| 157 |
+
| No log | 2.0784 | 212 | 0.4571 | 0.6640 | 0.4571 | 0.6761 |
|
| 158 |
+
| No log | 2.0980 | 214 | 0.5360 | 0.6358 | 0.5360 | 0.7321 |
|
| 159 |
+
| No log | 2.1176 | 216 | 0.5001 | 0.6520 | 0.5001 | 0.7072 |
|
| 160 |
+
| No log | 2.1373 | 218 | 0.4078 | 0.6697 | 0.4078 | 0.6386 |
|
| 161 |
+
| No log | 2.1569 | 220 | 0.4165 | 0.6410 | 0.4165 | 0.6454 |
|
| 162 |
+
| No log | 2.1765 | 222 | 0.4463 | 0.6157 | 0.4463 | 0.6681 |
|
| 163 |
+
| No log | 2.1961 | 224 | 0.4716 | 0.6056 | 0.4716 | 0.6867 |
|
| 164 |
+
| No log | 2.2157 | 226 | 0.4912 | 0.6084 | 0.4912 | 0.7009 |
|
| 165 |
+
| No log | 2.2353 | 228 | 0.4759 | 0.6127 | 0.4759 | 0.6899 |
|
| 166 |
+
| No log | 2.2549 | 230 | 0.4367 | 0.6317 | 0.4367 | 0.6608 |
|
| 167 |
+
| No log | 2.2745 | 232 | 0.4361 | 0.6747 | 0.4361 | 0.6604 |
|
| 168 |
+
| No log | 2.2941 | 234 | 0.5510 | 0.6428 | 0.5510 | 0.7423 |
|
| 169 |
+
| No log | 2.3137 | 236 | 0.6165 | 0.5801 | 0.6165 | 0.7852 |
|
| 170 |
+
| No log | 2.3333 | 238 | 0.5309 | 0.6651 | 0.5309 | 0.7286 |
|
| 171 |
+
| No log | 2.3529 | 240 | 0.4283 | 0.7254 | 0.4283 | 0.6544 |
|
| 172 |
+
| No log | 2.3725 | 242 | 0.3972 | 0.7336 | 0.3972 | 0.6303 |
|
| 173 |
+
| No log | 2.3922 | 244 | 0.3931 | 0.7157 | 0.3931 | 0.6270 |
|
| 174 |
+
| No log | 2.4118 | 246 | 0.3958 | 0.7307 | 0.3958 | 0.6291 |
|
| 175 |
+
| No log | 2.4314 | 248 | 0.4252 | 0.7417 | 0.4252 | 0.6521 |
|
| 176 |
+
| No log | 2.4510 | 250 | 0.4369 | 0.7405 | 0.4369 | 0.6610 |
|
| 177 |
+
| No log | 2.4706 | 252 | 0.4154 | 0.6969 | 0.4154 | 0.6445 |
|
| 178 |
+
| No log | 2.4902 | 254 | 0.4035 | 0.6824 | 0.4035 | 0.6352 |
|
| 179 |
+
| No log | 2.5098 | 256 | 0.4216 | 0.6594 | 0.4216 | 0.6493 |
|
| 180 |
+
| No log | 2.5294 | 258 | 0.4781 | 0.6175 | 0.4781 | 0.6915 |
|
| 181 |
+
| No log | 2.5490 | 260 | 0.6034 | 0.5766 | 0.6034 | 0.7768 |
|
| 182 |
+
| No log | 2.5686 | 262 | 0.6523 | 0.5303 | 0.6523 | 0.8077 |
|
| 183 |
+
| No log | 2.5882 | 264 | 0.5875 | 0.6323 | 0.5875 | 0.7665 |
|
| 184 |
+
| No log | 2.6078 | 266 | 0.5240 | 0.6382 | 0.5240 | 0.7239 |
|
| 185 |
+
| No log | 2.6275 | 268 | 0.5511 | 0.6434 | 0.5511 | 0.7424 |
|
| 186 |
+
| No log | 2.6471 | 270 | 0.5077 | 0.6356 | 0.5077 | 0.7126 |
|
| 187 |
+
| No log | 2.6667 | 272 | 0.4701 | 0.6288 | 0.4701 | 0.6856 |
|
| 188 |
+
| No log | 2.6863 | 274 | 0.5019 | 0.6250 | 0.5019 | 0.7084 |
|
| 189 |
+
| No log | 2.7059 | 276 | 0.5210 | 0.6129 | 0.5210 | 0.7218 |
|
| 190 |
+
| No log | 2.7255 | 278 | 0.4912 | 0.6352 | 0.4912 | 0.7008 |
|
| 191 |
+
| No log | 2.7451 | 280 | 0.4607 | 0.6381 | 0.4607 | 0.6787 |
|
| 192 |
+
| No log | 2.7647 | 282 | 0.4367 | 0.6455 | 0.4367 | 0.6609 |
|
| 193 |
+
| No log | 2.7843 | 284 | 0.4137 | 0.6385 | 0.4137 | 0.6432 |
|
| 194 |
+
| No log | 2.8039 | 286 | 0.4050 | 0.6669 | 0.4050 | 0.6364 |
|
| 195 |
+
| No log | 2.8235 | 288 | 0.4054 | 0.6565 | 0.4054 | 0.6367 |
|
| 196 |
+
| No log | 2.8431 | 290 | 0.4656 | 0.6768 | 0.4656 | 0.6823 |
|
| 197 |
+
| No log | 2.8627 | 292 | 0.6891 | 0.5419 | 0.6891 | 0.8301 |
|
| 198 |
+
| No log | 2.8824 | 294 | 0.8701 | 0.4711 | 0.8701 | 0.9328 |
|
| 199 |
+
| No log | 2.9020 | 296 | 0.8427 | 0.4836 | 0.8427 | 0.9180 |
|
| 200 |
+
| No log | 2.9216 | 298 | 0.6257 | 0.6071 | 0.6257 | 0.7910 |
|
| 201 |
+
| No log | 2.9412 | 300 | 0.4503 | 0.6795 | 0.4503 | 0.6711 |
|
| 202 |
+
| No log | 2.9608 | 302 | 0.4708 | 0.6801 | 0.4708 | 0.6861 |
|
| 203 |
+
| No log | 2.9804 | 304 | 0.4785 | 0.6750 | 0.4785 | 0.6917 |
|
| 204 |
+
| No log | 3.0 | 306 | 0.4060 | 0.6479 | 0.4060 | 0.6372 |
|
| 205 |
+
| No log | 3.0196 | 308 | 0.4294 | 0.6488 | 0.4294 | 0.6553 |
|
| 206 |
+
| No log | 3.0392 | 310 | 0.5220 | 0.5757 | 0.5220 | 0.7225 |
|
| 207 |
+
| No log | 3.0588 | 312 | 0.6074 | 0.4948 | 0.6074 | 0.7794 |
|
| 208 |
+
| No log | 3.0784 | 314 | 0.5872 | 0.4947 | 0.5872 | 0.7663 |
|
| 209 |
+
| No log | 3.0980 | 316 | 0.5101 | 0.5969 | 0.5101 | 0.7142 |
|
| 210 |
+
| No log | 3.1176 | 318 | 0.4545 | 0.6390 | 0.4545 | 0.6741 |
|
| 211 |
+
| No log | 3.1373 | 320 | 0.4097 | 0.6949 | 0.4097 | 0.6400 |
|
| 212 |
+
| No log | 3.1569 | 322 | 0.4174 | 0.7326 | 0.4174 | 0.6460 |
|
| 213 |
+
| No log | 3.1765 | 324 | 0.4067 | 0.7318 | 0.4067 | 0.6377 |
|
| 214 |
+
| No log | 3.1961 | 326 | 0.4165 | 0.7270 | 0.4165 | 0.6454 |
|
| 215 |
+
| No log | 3.2157 | 328 | 0.4501 | 0.7125 | 0.4501 | 0.6709 |
|
| 216 |
+
| No log | 3.2353 | 330 | 0.4437 | 0.7116 | 0.4437 | 0.6661 |
|
| 217 |
+
| No log | 3.2549 | 332 | 0.4234 | 0.7192 | 0.4234 | 0.6507 |
|
| 218 |
+
| No log | 3.2745 | 334 | 0.4619 | 0.6944 | 0.4619 | 0.6797 |
|
| 219 |
+
| No log | 3.2941 | 336 | 0.5880 | 0.6181 | 0.5880 | 0.7668 |
|
| 220 |
+
| No log | 3.3137 | 338 | 0.7674 | 0.5219 | 0.7674 | 0.8760 |
|
| 221 |
+
| No log | 3.3333 | 340 | 0.7755 | 0.5307 | 0.7755 | 0.8806 |
|
| 222 |
+
| No log | 3.3529 | 342 | 0.5740 | 0.6826 | 0.5740 | 0.7576 |
|
| 223 |
+
| No log | 3.3725 | 344 | 0.4168 | 0.7197 | 0.4168 | 0.6456 |
|
| 224 |
+
| No log | 3.3922 | 346 | 0.4122 | 0.7047 | 0.4122 | 0.6420 |
|
| 225 |
+
| No log | 3.4118 | 348 | 0.4041 | 0.7148 | 0.4041 | 0.6357 |
|
| 226 |
+
| No log | 3.4314 | 350 | 0.4547 | 0.7029 | 0.4547 | 0.6743 |
|
| 227 |
+
| No log | 3.4510 | 352 | 0.7426 | 0.5516 | 0.7426 | 0.8617 |
|
| 228 |
+
| No log | 3.4706 | 354 | 0.8988 | 0.4434 | 0.8988 | 0.9480 |
|
| 229 |
+
| No log | 3.4902 | 356 | 0.8012 | 0.4653 | 0.8012 | 0.8951 |
|
| 230 |
+
| No log | 3.5098 | 358 | 0.6497 | 0.5098 | 0.6497 | 0.8061 |
|
| 231 |
+
| No log | 3.5294 | 360 | 0.5067 | 0.5717 | 0.5067 | 0.7119 |
|
| 232 |
+
| No log | 3.5490 | 362 | 0.4191 | 0.6337 | 0.4191 | 0.6474 |
|
| 233 |
+
| No log | 3.5686 | 364 | 0.3769 | 0.6874 | 0.3769 | 0.6139 |
|
| 234 |
+
| No log | 3.5882 | 366 | 0.4186 | 0.7377 | 0.4186 | 0.6470 |
|
| 235 |
+
| No log | 3.6078 | 368 | 0.4372 | 0.7375 | 0.4372 | 0.6612 |
|
| 236 |
+
| No log | 3.6275 | 370 | 0.4703 | 0.7065 | 0.4703 | 0.6858 |
|
| 237 |
+
| No log | 3.6471 | 372 | 0.5848 | 0.6301 | 0.5848 | 0.7647 |
|
| 238 |
+
| No log | 3.6667 | 374 | 0.6585 | 0.5570 | 0.6585 | 0.8115 |
|
| 239 |
+
| No log | 3.6863 | 376 | 0.6498 | 0.5366 | 0.6498 | 0.8061 |
|
| 240 |
+
| No log | 3.7059 | 378 | 0.5813 | 0.5361 | 0.5813 | 0.7624 |
|
| 241 |
+
| No log | 3.7255 | 380 | 0.5038 | 0.6183 | 0.5038 | 0.7098 |
|
| 242 |
+
| No log | 3.7451 | 382 | 0.4479 | 0.6634 | 0.4479 | 0.6692 |
|
| 243 |
+
| No log | 3.7647 | 384 | 0.4120 | 0.7157 | 0.4120 | 0.6419 |
|
| 244 |
+
| No log | 3.7843 | 386 | 0.4097 | 0.7078 | 0.4097 | 0.6401 |
|
| 245 |
+
| No log | 3.8039 | 388 | 0.4032 | 0.7149 | 0.4032 | 0.6350 |
|
| 246 |
+
| No log | 3.8235 | 390 | 0.4106 | 0.7075 | 0.4106 | 0.6408 |
|
| 247 |
+
| No log | 3.8431 | 392 | 0.4225 | 0.6922 | 0.4225 | 0.6500 |
|
| 248 |
+
| No log | 3.8627 | 394 | 0.4001 | 0.6806 | 0.4001 | 0.6325 |
|
| 249 |
+
| No log | 3.8824 | 396 | 0.4227 | 0.6597 | 0.4227 | 0.6501 |
|
| 250 |
+
| No log | 3.9020 | 398 | 0.4176 | 0.6684 | 0.4176 | 0.6462 |
|
| 251 |
+
| No log | 3.9216 | 400 | 0.4039 | 0.6408 | 0.4039 | 0.6355 |
|
| 252 |
+
| No log | 3.9412 | 402 | 0.4125 | 0.6865 | 0.4125 | 0.6422 |
|
| 253 |
+
| No log | 3.9608 | 404 | 0.4811 | 0.6565 | 0.4811 | 0.6936 |
|
| 254 |
+
| No log | 3.9804 | 406 | 0.4876 | 0.6609 | 0.4876 | 0.6983 |
|
| 255 |
+
| No log | 4.0 | 408 | 0.5054 | 0.6407 | 0.5054 | 0.7109 |
|
| 256 |
+
| No log | 4.0196 | 410 | 0.6054 | 0.6025 | 0.6054 | 0.7781 |
|
| 257 |
+
| No log | 4.0392 | 412 | 0.7235 | 0.5638 | 0.7235 | 0.8506 |
|
| 258 |
+
| No log | 4.0588 | 414 | 0.6509 | 0.5759 | 0.6509 | 0.8068 |
|
| 259 |
+
| No log | 4.0784 | 416 | 0.4875 | 0.6375 | 0.4875 | 0.6982 |
|
| 260 |
+
| No log | 4.0980 | 418 | 0.4572 | 0.5912 | 0.4572 | 0.6761 |
|
| 261 |
+
| No log | 4.1176 | 420 | 0.4301 | 0.6375 | 0.4301 | 0.6558 |
|
| 262 |
+
| No log | 4.1373 | 422 | 0.4545 | 0.6781 | 0.4545 | 0.6741 |
|
| 263 |
+
| No log | 4.1569 | 424 | 0.6376 | 0.6241 | 0.6376 | 0.7985 |
|
| 264 |
+
| No log | 4.1765 | 426 | 0.6940 | 0.5995 | 0.6940 | 0.8331 |
|
| 265 |
+
| No log | 4.1961 | 428 | 0.5903 | 0.6331 | 0.5903 | 0.7683 |
|
| 266 |
+
| No log | 4.2157 | 430 | 0.4306 | 0.7018 | 0.4306 | 0.6562 |
|
| 267 |
+
| No log | 4.2353 | 432 | 0.4065 | 0.7273 | 0.4065 | 0.6376 |
|
| 268 |
+
| No log | 4.2549 | 434 | 0.4378 | 0.6886 | 0.4378 | 0.6617 |
|
| 269 |
+
| No log | 4.2745 | 436 | 0.4704 | 0.6384 | 0.4704 | 0.6859 |
|
| 270 |
+
| No log | 4.2941 | 438 | 0.4140 | 0.6299 | 0.4140 | 0.6435 |
|
| 271 |
+
| No log | 4.3137 | 440 | 0.4161 | 0.6109 | 0.4161 | 0.6450 |
|
| 272 |
+
| No log | 4.3333 | 442 | 0.4137 | 0.6108 | 0.4137 | 0.6432 |
|
| 273 |
+
| No log | 4.3529 | 444 | 0.4340 | 0.6292 | 0.4340 | 0.6588 |
|
| 274 |
+
| No log | 4.3725 | 446 | 0.4270 | 0.6492 | 0.4270 | 0.6534 |
|
| 275 |
+
| No log | 4.3922 | 448 | 0.4554 | 0.6702 | 0.4554 | 0.6749 |
|
| 276 |
+
| No log | 4.4118 | 450 | 0.4837 | 0.6932 | 0.4837 | 0.6955 |
|
| 277 |
+
| No log | 4.4314 | 452 | 0.4349 | 0.6984 | 0.4349 | 0.6594 |
|
| 278 |
+
| No log | 4.4510 | 454 | 0.4324 | 0.7469 | 0.4324 | 0.6575 |
|
| 279 |
+
| No log | 4.4706 | 456 | 0.5200 | 0.6761 | 0.5200 | 0.7211 |
|
| 280 |
+
| No log | 4.4902 | 458 | 0.6330 | 0.6053 | 0.6330 | 0.7956 |
|
| 281 |
+
| No log | 4.5098 | 460 | 0.5442 | 0.6572 | 0.5442 | 0.7377 |
|
| 282 |
+
| No log | 4.5294 | 462 | 0.4984 | 0.6777 | 0.4984 | 0.7060 |
|
| 283 |
+
| No log | 4.5490 | 464 | 0.4089 | 0.7200 | 0.4089 | 0.6394 |
|
| 284 |
+
| No log | 4.5686 | 466 | 0.3918 | 0.6788 | 0.3918 | 0.6260 |
|
| 285 |
+
| No log | 4.5882 | 468 | 0.4436 | 0.6895 | 0.4436 | 0.6660 |
|
| 286 |
+
| No log | 4.6078 | 470 | 0.4651 | 0.6849 | 0.4651 | 0.6820 |
|
| 287 |
+
| No log | 4.6275 | 472 | 0.4733 | 0.6846 | 0.4733 | 0.6880 |
|
| 288 |
+
| No log | 4.6471 | 474 | 0.4265 | 0.6936 | 0.4265 | 0.6531 |
|
| 289 |
+
| No log | 4.6667 | 476 | 0.4392 | 0.6880 | 0.4392 | 0.6627 |
|
| 290 |
+
| No log | 4.6863 | 478 | 0.4242 | 0.6985 | 0.4242 | 0.6513 |
|
| 291 |
+
| No log | 4.7059 | 480 | 0.3954 | 0.7178 | 0.3954 | 0.6288 |
|
| 292 |
+
| No log | 4.7255 | 482 | 0.4074 | 0.6795 | 0.4074 | 0.6383 |
|
| 293 |
+
| No log | 4.7451 | 484 | 0.4319 | 0.6026 | 0.4319 | 0.6572 |
|
| 294 |
+
| No log | 4.7647 | 486 | 0.4385 | 0.6151 | 0.4385 | 0.6622 |
|
| 295 |
+
| No log | 4.7843 | 488 | 0.4686 | 0.6215 | 0.4686 | 0.6845 |
|
| 296 |
+
| No log | 4.8039 | 490 | 0.4545 | 0.6573 | 0.4545 | 0.6742 |
|
| 297 |
+
| No log | 4.8235 | 492 | 0.4573 | 0.6754 | 0.4573 | 0.6763 |
|
| 298 |
+
| No log | 4.8431 | 494 | 0.5645 | 0.6575 | 0.5645 | 0.7514 |
|
| 299 |
+
| No log | 4.8627 | 496 | 0.6008 | 0.6470 | 0.6008 | 0.7751 |
|
| 300 |
+
| No log | 4.8824 | 498 | 0.5220 | 0.6913 | 0.5220 | 0.7225 |
|
| 301 |
+
| 0.5195 | 4.9020 | 500 | 0.4284 | 0.7482 | 0.4284 | 0.6545 |
|
| 302 |
+
| 0.5195 | 4.9216 | 502 | 0.4141 | 0.7477 | 0.4141 | 0.6435 |
|
| 303 |
+
| 0.5195 | 4.9412 | 504 | 0.4159 | 0.7254 | 0.4159 | 0.6449 |
|
| 304 |
+
| 0.5195 | 4.9608 | 506 | 0.6276 | 0.6328 | 0.6276 | 0.7922 |
|
| 305 |
+
| 0.5195 | 4.9804 | 508 | 1.0729 | 0.4353 | 1.0729 | 1.0358 |
|
| 306 |
+
| 0.5195 | 5.0 | 510 | 1.1541 | 0.4137 | 1.1541 | 1.0743 |
|
| 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 sha256:746451290682c9265dd6e7813d4914005d4dae8f85b843ba85df772119f08abd
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc2fbb45f59c8417eb7dee38be99629ce270fd24d917bd00a701e9b04bc0620
|
| 3 |
+
size 5240
|