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_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k1_task2_organization
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ArabicNewSplits7_B_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k1_task2_organization
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7445
|
| 19 |
+
- Qwk: 0.5680
|
| 20 |
+
- Mse: 0.7445
|
| 21 |
+
- Rmse: 0.8628
|
| 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 | 0.2857 | 2 | 4.0555 | -0.0252 | 4.0555 | 2.0138 |
|
| 53 |
+
| No log | 0.5714 | 4 | 2.0504 | -0.0093 | 2.0504 | 1.4319 |
|
| 54 |
+
| No log | 0.8571 | 6 | 1.5859 | 0.0 | 1.5859 | 1.2593 |
|
| 55 |
+
| No log | 1.1429 | 8 | 1.3477 | 0.0 | 1.3477 | 1.1609 |
|
| 56 |
+
| No log | 1.4286 | 10 | 1.2122 | 0.1482 | 1.2122 | 1.1010 |
|
| 57 |
+
| No log | 1.7143 | 12 | 1.1747 | 0.0628 | 1.1747 | 1.0838 |
|
| 58 |
+
| No log | 2.0 | 14 | 1.1875 | 0.0253 | 1.1875 | 1.0897 |
|
| 59 |
+
| No log | 2.2857 | 16 | 1.1626 | 0.0802 | 1.1626 | 1.0782 |
|
| 60 |
+
| No log | 2.5714 | 18 | 1.1304 | 0.1076 | 1.1304 | 1.0632 |
|
| 61 |
+
| No log | 2.8571 | 20 | 1.1538 | 0.2619 | 1.1538 | 1.0742 |
|
| 62 |
+
| No log | 3.1429 | 22 | 1.1815 | 0.3946 | 1.1815 | 1.0870 |
|
| 63 |
+
| No log | 3.4286 | 24 | 1.1577 | 0.3814 | 1.1577 | 1.0760 |
|
| 64 |
+
| No log | 3.7143 | 26 | 1.1636 | 0.3236 | 1.1636 | 1.0787 |
|
| 65 |
+
| No log | 4.0 | 28 | 1.1850 | 0.2593 | 1.1850 | 1.0886 |
|
| 66 |
+
| No log | 4.2857 | 30 | 1.2010 | 0.2161 | 1.2010 | 1.0959 |
|
| 67 |
+
| No log | 4.5714 | 32 | 1.1126 | 0.3284 | 1.1126 | 1.0548 |
|
| 68 |
+
| No log | 4.8571 | 34 | 1.0029 | 0.3689 | 1.0029 | 1.0014 |
|
| 69 |
+
| No log | 5.1429 | 36 | 0.9798 | 0.3354 | 0.9798 | 0.9899 |
|
| 70 |
+
| No log | 5.4286 | 38 | 0.9566 | 0.3596 | 0.9566 | 0.9781 |
|
| 71 |
+
| No log | 5.7143 | 40 | 1.0254 | 0.3250 | 1.0254 | 1.0126 |
|
| 72 |
+
| No log | 6.0 | 42 | 1.1739 | 0.1920 | 1.1739 | 1.0835 |
|
| 73 |
+
| No log | 6.2857 | 44 | 1.1642 | 0.1920 | 1.1642 | 1.0790 |
|
| 74 |
+
| No log | 6.5714 | 46 | 1.0313 | 0.3424 | 1.0313 | 1.0155 |
|
| 75 |
+
| No log | 6.8571 | 48 | 0.9434 | 0.4374 | 0.9434 | 0.9713 |
|
| 76 |
+
| No log | 7.1429 | 50 | 0.9651 | 0.4250 | 0.9651 | 0.9824 |
|
| 77 |
+
| No log | 7.4286 | 52 | 0.9647 | 0.4496 | 0.9647 | 0.9822 |
|
| 78 |
+
| No log | 7.7143 | 54 | 0.9747 | 0.4045 | 0.9747 | 0.9873 |
|
| 79 |
+
| No log | 8.0 | 56 | 0.9371 | 0.4449 | 0.9371 | 0.9681 |
|
| 80 |
+
| No log | 8.2857 | 58 | 0.9299 | 0.4421 | 0.9299 | 0.9643 |
|
| 81 |
+
| No log | 8.5714 | 60 | 1.0875 | 0.5410 | 1.0875 | 1.0428 |
|
| 82 |
+
| No log | 8.8571 | 62 | 1.0729 | 0.5547 | 1.0729 | 1.0358 |
|
| 83 |
+
| No log | 9.1429 | 64 | 0.9115 | 0.4747 | 0.9115 | 0.9547 |
|
| 84 |
+
| No log | 9.4286 | 66 | 1.1126 | 0.3948 | 1.1126 | 1.0548 |
|
| 85 |
+
| No log | 9.7143 | 68 | 1.1174 | 0.3987 | 1.1174 | 1.0571 |
|
| 86 |
+
| No log | 10.0 | 70 | 0.9442 | 0.5094 | 0.9442 | 0.9717 |
|
| 87 |
+
| No log | 10.2857 | 72 | 0.8211 | 0.5851 | 0.8211 | 0.9062 |
|
| 88 |
+
| No log | 10.5714 | 74 | 0.8356 | 0.5849 | 0.8356 | 0.9141 |
|
| 89 |
+
| No log | 10.8571 | 76 | 0.9311 | 0.4854 | 0.9311 | 0.9649 |
|
| 90 |
+
| No log | 11.1429 | 78 | 0.8602 | 0.4812 | 0.8602 | 0.9275 |
|
| 91 |
+
| No log | 11.4286 | 80 | 0.8362 | 0.5504 | 0.8362 | 0.9144 |
|
| 92 |
+
| No log | 11.7143 | 82 | 0.8184 | 0.5040 | 0.8184 | 0.9046 |
|
| 93 |
+
| No log | 12.0 | 84 | 0.9012 | 0.4522 | 0.9012 | 0.9493 |
|
| 94 |
+
| No log | 12.2857 | 86 | 1.0069 | 0.4191 | 1.0069 | 1.0034 |
|
| 95 |
+
| No log | 12.5714 | 88 | 0.9497 | 0.4486 | 0.9497 | 0.9745 |
|
| 96 |
+
| No log | 12.8571 | 90 | 0.8342 | 0.5565 | 0.8342 | 0.9133 |
|
| 97 |
+
| No log | 13.1429 | 92 | 0.8705 | 0.5691 | 0.8705 | 0.9330 |
|
| 98 |
+
| No log | 13.4286 | 94 | 0.8151 | 0.5589 | 0.8151 | 0.9028 |
|
| 99 |
+
| No log | 13.7143 | 96 | 0.9484 | 0.5121 | 0.9484 | 0.9739 |
|
| 100 |
+
| No log | 14.0 | 98 | 1.1771 | 0.4583 | 1.1771 | 1.0849 |
|
| 101 |
+
| No log | 14.2857 | 100 | 1.1042 | 0.4371 | 1.1042 | 1.0508 |
|
| 102 |
+
| No log | 14.5714 | 102 | 0.8718 | 0.5644 | 0.8718 | 0.9337 |
|
| 103 |
+
| No log | 14.8571 | 104 | 0.7723 | 0.6190 | 0.7723 | 0.8788 |
|
| 104 |
+
| No log | 15.1429 | 106 | 0.8174 | 0.6253 | 0.8174 | 0.9041 |
|
| 105 |
+
| No log | 15.4286 | 108 | 0.7559 | 0.6170 | 0.7559 | 0.8694 |
|
| 106 |
+
| No log | 15.7143 | 110 | 0.6732 | 0.5988 | 0.6732 | 0.8205 |
|
| 107 |
+
| No log | 16.0 | 112 | 0.6733 | 0.6328 | 0.6733 | 0.8205 |
|
| 108 |
+
| No log | 16.2857 | 114 | 0.6843 | 0.6205 | 0.6843 | 0.8272 |
|
| 109 |
+
| No log | 16.5714 | 116 | 0.6861 | 0.6119 | 0.6861 | 0.8283 |
|
| 110 |
+
| No log | 16.8571 | 118 | 0.7844 | 0.6302 | 0.7844 | 0.8856 |
|
| 111 |
+
| No log | 17.1429 | 120 | 0.8017 | 0.6177 | 0.8017 | 0.8954 |
|
| 112 |
+
| No log | 17.4286 | 122 | 0.7652 | 0.6059 | 0.7652 | 0.8747 |
|
| 113 |
+
| No log | 17.7143 | 124 | 0.6993 | 0.5746 | 0.6993 | 0.8362 |
|
| 114 |
+
| No log | 18.0 | 126 | 0.7137 | 0.6172 | 0.7137 | 0.8448 |
|
| 115 |
+
| No log | 18.2857 | 128 | 0.7228 | 0.5703 | 0.7228 | 0.8502 |
|
| 116 |
+
| No log | 18.5714 | 130 | 0.7136 | 0.6088 | 0.7136 | 0.8447 |
|
| 117 |
+
| No log | 18.8571 | 132 | 0.7476 | 0.6237 | 0.7476 | 0.8646 |
|
| 118 |
+
| No log | 19.1429 | 134 | 0.8117 | 0.6149 | 0.8117 | 0.9009 |
|
| 119 |
+
| No log | 19.4286 | 136 | 0.8186 | 0.6362 | 0.8186 | 0.9048 |
|
| 120 |
+
| No log | 19.7143 | 138 | 0.7649 | 0.6207 | 0.7649 | 0.8746 |
|
| 121 |
+
| No log | 20.0 | 140 | 0.7076 | 0.5846 | 0.7076 | 0.8412 |
|
| 122 |
+
| No log | 20.2857 | 142 | 0.7571 | 0.5843 | 0.7571 | 0.8701 |
|
| 123 |
+
| No log | 20.5714 | 144 | 0.7471 | 0.5843 | 0.7471 | 0.8643 |
|
| 124 |
+
| No log | 20.8571 | 146 | 0.7076 | 0.5997 | 0.7076 | 0.8412 |
|
| 125 |
+
| No log | 21.1429 | 148 | 0.8835 | 0.6195 | 0.8835 | 0.9400 |
|
| 126 |
+
| No log | 21.4286 | 150 | 1.0829 | 0.6342 | 1.0829 | 1.0406 |
|
| 127 |
+
| No log | 21.7143 | 152 | 1.0683 | 0.6104 | 1.0683 | 1.0336 |
|
| 128 |
+
| No log | 22.0 | 154 | 0.8606 | 0.6131 | 0.8606 | 0.9277 |
|
| 129 |
+
| No log | 22.2857 | 156 | 0.7156 | 0.6130 | 0.7156 | 0.8459 |
|
| 130 |
+
| No log | 22.5714 | 158 | 0.7194 | 0.5946 | 0.7195 | 0.8482 |
|
| 131 |
+
| No log | 22.8571 | 160 | 0.7086 | 0.6002 | 0.7086 | 0.8418 |
|
| 132 |
+
| No log | 23.1429 | 162 | 0.7019 | 0.6237 | 0.7019 | 0.8378 |
|
| 133 |
+
| No log | 23.4286 | 164 | 0.7739 | 0.6784 | 0.7739 | 0.8797 |
|
| 134 |
+
| No log | 23.7143 | 166 | 0.7687 | 0.6335 | 0.7687 | 0.8767 |
|
| 135 |
+
| No log | 24.0 | 168 | 0.7101 | 0.5966 | 0.7101 | 0.8427 |
|
| 136 |
+
| No log | 24.2857 | 170 | 0.7353 | 0.5607 | 0.7353 | 0.8575 |
|
| 137 |
+
| No log | 24.5714 | 172 | 0.8027 | 0.5763 | 0.8027 | 0.8959 |
|
| 138 |
+
| No log | 24.8571 | 174 | 0.7940 | 0.5848 | 0.7940 | 0.8911 |
|
| 139 |
+
| No log | 25.1429 | 176 | 0.7426 | 0.5455 | 0.7426 | 0.8617 |
|
| 140 |
+
| No log | 25.4286 | 178 | 0.7336 | 0.6128 | 0.7336 | 0.8565 |
|
| 141 |
+
| No log | 25.7143 | 180 | 0.7384 | 0.5997 | 0.7384 | 0.8593 |
|
| 142 |
+
| No log | 26.0 | 182 | 0.7241 | 0.5997 | 0.7241 | 0.8509 |
|
| 143 |
+
| No log | 26.2857 | 184 | 0.7124 | 0.5719 | 0.7124 | 0.8441 |
|
| 144 |
+
| No log | 26.5714 | 186 | 0.7602 | 0.5912 | 0.7602 | 0.8719 |
|
| 145 |
+
| No log | 26.8571 | 188 | 0.7728 | 0.5912 | 0.7728 | 0.8791 |
|
| 146 |
+
| No log | 27.1429 | 190 | 0.7228 | 0.5830 | 0.7228 | 0.8502 |
|
| 147 |
+
| No log | 27.4286 | 192 | 0.7045 | 0.6056 | 0.7045 | 0.8394 |
|
| 148 |
+
| No log | 27.7143 | 194 | 0.7445 | 0.6001 | 0.7445 | 0.8628 |
|
| 149 |
+
| No log | 28.0 | 196 | 0.7400 | 0.6148 | 0.7400 | 0.8602 |
|
| 150 |
+
| No log | 28.2857 | 198 | 0.7118 | 0.5875 | 0.7118 | 0.8437 |
|
| 151 |
+
| No log | 28.5714 | 200 | 0.7010 | 0.6108 | 0.7010 | 0.8373 |
|
| 152 |
+
| No log | 28.8571 | 202 | 0.7027 | 0.6023 | 0.7027 | 0.8382 |
|
| 153 |
+
| No log | 29.1429 | 204 | 0.7084 | 0.5861 | 0.7084 | 0.8417 |
|
| 154 |
+
| No log | 29.4286 | 206 | 0.7154 | 0.6450 | 0.7154 | 0.8458 |
|
| 155 |
+
| No log | 29.7143 | 208 | 0.7219 | 0.6211 | 0.7219 | 0.8496 |
|
| 156 |
+
| No log | 30.0 | 210 | 0.7392 | 0.5902 | 0.7392 | 0.8598 |
|
| 157 |
+
| No log | 30.2857 | 212 | 0.7563 | 0.6067 | 0.7563 | 0.8696 |
|
| 158 |
+
| No log | 30.5714 | 214 | 0.7480 | 0.5875 | 0.7480 | 0.8649 |
|
| 159 |
+
| No log | 30.8571 | 216 | 0.7291 | 0.5902 | 0.7291 | 0.8539 |
|
| 160 |
+
| No log | 31.1429 | 218 | 0.7223 | 0.6211 | 0.7223 | 0.8499 |
|
| 161 |
+
| No log | 31.4286 | 220 | 0.7266 | 0.6211 | 0.7266 | 0.8524 |
|
| 162 |
+
| No log | 31.7143 | 222 | 0.7309 | 0.6224 | 0.7309 | 0.8549 |
|
| 163 |
+
| No log | 32.0 | 224 | 0.7303 | 0.6224 | 0.7303 | 0.8546 |
|
| 164 |
+
| No log | 32.2857 | 226 | 0.7253 | 0.6224 | 0.7253 | 0.8517 |
|
| 165 |
+
| No log | 32.5714 | 228 | 0.7267 | 0.6224 | 0.7267 | 0.8524 |
|
| 166 |
+
| No log | 32.8571 | 230 | 0.7414 | 0.6517 | 0.7414 | 0.8611 |
|
| 167 |
+
| No log | 33.1429 | 232 | 0.7368 | 0.6097 | 0.7368 | 0.8584 |
|
| 168 |
+
| No log | 33.4286 | 234 | 0.7483 | 0.5208 | 0.7483 | 0.8651 |
|
| 169 |
+
| No log | 33.7143 | 236 | 0.7701 | 0.4830 | 0.7701 | 0.8775 |
|
| 170 |
+
| No log | 34.0 | 238 | 0.7865 | 0.4948 | 0.7865 | 0.8868 |
|
| 171 |
+
| No log | 34.2857 | 240 | 0.7626 | 0.5407 | 0.7626 | 0.8732 |
|
| 172 |
+
| No log | 34.5714 | 242 | 0.7625 | 0.5407 | 0.7625 | 0.8732 |
|
| 173 |
+
| No log | 34.8571 | 244 | 0.7469 | 0.5382 | 0.7469 | 0.8643 |
|
| 174 |
+
| No log | 35.1429 | 246 | 0.7548 | 0.6119 | 0.7548 | 0.8688 |
|
| 175 |
+
| No log | 35.4286 | 248 | 0.7773 | 0.6119 | 0.7773 | 0.8816 |
|
| 176 |
+
| No log | 35.7143 | 250 | 0.7736 | 0.5621 | 0.7736 | 0.8795 |
|
| 177 |
+
| No log | 36.0 | 252 | 0.7881 | 0.5451 | 0.7881 | 0.8877 |
|
| 178 |
+
| No log | 36.2857 | 254 | 0.8029 | 0.5240 | 0.8029 | 0.8961 |
|
| 179 |
+
| No log | 36.5714 | 256 | 0.8263 | 0.5656 | 0.8263 | 0.9090 |
|
| 180 |
+
| No log | 36.8571 | 258 | 0.8272 | 0.5740 | 0.8272 | 0.9095 |
|
| 181 |
+
| No log | 37.1429 | 260 | 0.8019 | 0.5760 | 0.8019 | 0.8955 |
|
| 182 |
+
| No log | 37.4286 | 262 | 0.7790 | 0.5430 | 0.7790 | 0.8826 |
|
| 183 |
+
| No log | 37.7143 | 264 | 0.7672 | 0.5064 | 0.7672 | 0.8759 |
|
| 184 |
+
| No log | 38.0 | 266 | 0.7656 | 0.5497 | 0.7656 | 0.8750 |
|
| 185 |
+
| No log | 38.2857 | 268 | 0.7544 | 0.5190 | 0.7544 | 0.8685 |
|
| 186 |
+
| No log | 38.5714 | 270 | 0.7514 | 0.5497 | 0.7514 | 0.8668 |
|
| 187 |
+
| No log | 38.8571 | 272 | 0.7383 | 0.5861 | 0.7383 | 0.8592 |
|
| 188 |
+
| No log | 39.1429 | 274 | 0.7328 | 0.5727 | 0.7328 | 0.8560 |
|
| 189 |
+
| No log | 39.4286 | 276 | 0.7268 | 0.5430 | 0.7268 | 0.8526 |
|
| 190 |
+
| No log | 39.7143 | 278 | 0.7362 | 0.5738 | 0.7362 | 0.8580 |
|
| 191 |
+
| No log | 40.0 | 280 | 0.7490 | 0.6098 | 0.7490 | 0.8655 |
|
| 192 |
+
| No log | 40.2857 | 282 | 0.7411 | 0.5634 | 0.7411 | 0.8609 |
|
| 193 |
+
| No log | 40.5714 | 284 | 0.7284 | 0.5862 | 0.7284 | 0.8534 |
|
| 194 |
+
| No log | 40.8571 | 286 | 0.7448 | 0.5667 | 0.7448 | 0.8630 |
|
| 195 |
+
| No log | 41.1429 | 288 | 0.7529 | 0.5691 | 0.7529 | 0.8677 |
|
| 196 |
+
| No log | 41.4286 | 290 | 0.7574 | 0.5691 | 0.7574 | 0.8703 |
|
| 197 |
+
| No log | 41.7143 | 292 | 0.7361 | 0.5583 | 0.7361 | 0.8580 |
|
| 198 |
+
| No log | 42.0 | 294 | 0.7367 | 0.5879 | 0.7367 | 0.8583 |
|
| 199 |
+
| No log | 42.2857 | 296 | 0.7934 | 0.6404 | 0.7934 | 0.8907 |
|
| 200 |
+
| No log | 42.5714 | 298 | 0.8047 | 0.6315 | 0.8047 | 0.8971 |
|
| 201 |
+
| No log | 42.8571 | 300 | 0.7593 | 0.6283 | 0.7593 | 0.8714 |
|
| 202 |
+
| No log | 43.1429 | 302 | 0.7304 | 0.5556 | 0.7304 | 0.8546 |
|
| 203 |
+
| No log | 43.4286 | 304 | 0.7725 | 0.5291 | 0.7725 | 0.8789 |
|
| 204 |
+
| No log | 43.7143 | 306 | 0.8063 | 0.5021 | 0.8063 | 0.8979 |
|
| 205 |
+
| No log | 44.0 | 308 | 0.7815 | 0.5367 | 0.7815 | 0.8840 |
|
| 206 |
+
| No log | 44.2857 | 310 | 0.7617 | 0.5451 | 0.7617 | 0.8727 |
|
| 207 |
+
| No log | 44.5714 | 312 | 0.7727 | 0.5824 | 0.7727 | 0.8790 |
|
| 208 |
+
| No log | 44.8571 | 314 | 0.7862 | 0.6183 | 0.7862 | 0.8867 |
|
| 209 |
+
| No log | 45.1429 | 316 | 0.7701 | 0.5819 | 0.7701 | 0.8776 |
|
| 210 |
+
| No log | 45.4286 | 318 | 0.7685 | 0.5537 | 0.7685 | 0.8766 |
|
| 211 |
+
| No log | 45.7143 | 320 | 0.8007 | 0.5883 | 0.8007 | 0.8948 |
|
| 212 |
+
| No log | 46.0 | 322 | 0.8084 | 0.5883 | 0.8084 | 0.8991 |
|
| 213 |
+
| No log | 46.2857 | 324 | 0.7874 | 0.5833 | 0.7874 | 0.8873 |
|
| 214 |
+
| No log | 46.5714 | 326 | 0.7716 | 0.5223 | 0.7716 | 0.8784 |
|
| 215 |
+
| No log | 46.8571 | 328 | 0.7713 | 0.5633 | 0.7713 | 0.8782 |
|
| 216 |
+
| No log | 47.1429 | 330 | 0.7760 | 0.5633 | 0.7760 | 0.8809 |
|
| 217 |
+
| No log | 47.4286 | 332 | 0.7814 | 0.5819 | 0.7814 | 0.8840 |
|
| 218 |
+
| No log | 47.7143 | 334 | 0.7594 | 0.5657 | 0.7594 | 0.8714 |
|
| 219 |
+
| No log | 48.0 | 336 | 0.7500 | 0.5753 | 0.7500 | 0.8660 |
|
| 220 |
+
| No log | 48.2857 | 338 | 0.7527 | 0.5753 | 0.7527 | 0.8676 |
|
| 221 |
+
| No log | 48.5714 | 340 | 0.7641 | 0.5776 | 0.7641 | 0.8741 |
|
| 222 |
+
| No log | 48.8571 | 342 | 0.7712 | 0.5776 | 0.7712 | 0.8782 |
|
| 223 |
+
| No log | 49.1429 | 344 | 0.7621 | 0.5750 | 0.7621 | 0.8730 |
|
| 224 |
+
| No log | 49.4286 | 346 | 0.7669 | 0.5750 | 0.7669 | 0.8757 |
|
| 225 |
+
| No log | 49.7143 | 348 | 0.7667 | 0.5750 | 0.7667 | 0.8756 |
|
| 226 |
+
| No log | 50.0 | 350 | 0.7581 | 0.5727 | 0.7581 | 0.8707 |
|
| 227 |
+
| No log | 50.2857 | 352 | 0.7552 | 0.5727 | 0.7552 | 0.8690 |
|
| 228 |
+
| No log | 50.5714 | 354 | 0.7537 | 0.5944 | 0.7537 | 0.8682 |
|
| 229 |
+
| No log | 50.8571 | 356 | 0.7489 | 0.5944 | 0.7489 | 0.8654 |
|
| 230 |
+
| No log | 51.1429 | 358 | 0.7441 | 0.5944 | 0.7441 | 0.8626 |
|
| 231 |
+
| No log | 51.4286 | 360 | 0.7490 | 0.5531 | 0.7490 | 0.8655 |
|
| 232 |
+
| No log | 51.7143 | 362 | 0.7432 | 0.5633 | 0.7432 | 0.8621 |
|
| 233 |
+
| No log | 52.0 | 364 | 0.7289 | 0.5841 | 0.7289 | 0.8537 |
|
| 234 |
+
| No log | 52.2857 | 366 | 0.7204 | 0.6065 | 0.7204 | 0.8488 |
|
| 235 |
+
| No log | 52.5714 | 368 | 0.7188 | 0.5171 | 0.7188 | 0.8478 |
|
| 236 |
+
| No log | 52.8571 | 370 | 0.7333 | 0.5429 | 0.7333 | 0.8563 |
|
| 237 |
+
| No log | 53.1429 | 372 | 0.7365 | 0.5429 | 0.7365 | 0.8582 |
|
| 238 |
+
| No log | 53.4286 | 374 | 0.7349 | 0.5583 | 0.7349 | 0.8573 |
|
| 239 |
+
| No log | 53.7143 | 376 | 0.7350 | 0.5706 | 0.7350 | 0.8573 |
|
| 240 |
+
| No log | 54.0 | 378 | 0.7484 | 0.5819 | 0.7484 | 0.8651 |
|
| 241 |
+
| No log | 54.2857 | 380 | 0.7609 | 0.5819 | 0.7609 | 0.8723 |
|
| 242 |
+
| No log | 54.5714 | 382 | 0.7618 | 0.6088 | 0.7618 | 0.8728 |
|
| 243 |
+
| No log | 54.8571 | 384 | 0.7490 | 0.5657 | 0.7490 | 0.8654 |
|
| 244 |
+
| No log | 55.1429 | 386 | 0.7490 | 0.5930 | 0.7490 | 0.8654 |
|
| 245 |
+
| No log | 55.4286 | 388 | 0.7511 | 0.5930 | 0.7511 | 0.8667 |
|
| 246 |
+
| No log | 55.7143 | 390 | 0.7509 | 0.5930 | 0.7509 | 0.8666 |
|
| 247 |
+
| No log | 56.0 | 392 | 0.7506 | 0.5819 | 0.7506 | 0.8663 |
|
| 248 |
+
| No log | 56.2857 | 394 | 0.7578 | 0.5819 | 0.7578 | 0.8705 |
|
| 249 |
+
| No log | 56.5714 | 396 | 0.7616 | 0.5819 | 0.7616 | 0.8727 |
|
| 250 |
+
| No log | 56.8571 | 398 | 0.7693 | 0.5715 | 0.7693 | 0.8771 |
|
| 251 |
+
| No log | 57.1429 | 400 | 0.7731 | 0.5715 | 0.7731 | 0.8793 |
|
| 252 |
+
| No log | 57.4286 | 402 | 0.7773 | 0.5362 | 0.7773 | 0.8817 |
|
| 253 |
+
| No log | 57.7143 | 404 | 0.7847 | 0.5106 | 0.7847 | 0.8858 |
|
| 254 |
+
| No log | 58.0 | 406 | 0.7915 | 0.5342 | 0.7915 | 0.8897 |
|
| 255 |
+
| No log | 58.2857 | 408 | 0.7955 | 0.5342 | 0.7955 | 0.8919 |
|
| 256 |
+
| No log | 58.5714 | 410 | 0.7986 | 0.5257 | 0.7986 | 0.8936 |
|
| 257 |
+
| No log | 58.8571 | 412 | 0.7960 | 0.5367 | 0.7960 | 0.8922 |
|
| 258 |
+
| No log | 59.1429 | 414 | 0.7928 | 0.5183 | 0.7928 | 0.8904 |
|
| 259 |
+
| No log | 59.4286 | 416 | 0.7962 | 0.5200 | 0.7962 | 0.8923 |
|
| 260 |
+
| No log | 59.7143 | 418 | 0.7885 | 0.5367 | 0.7885 | 0.8880 |
|
| 261 |
+
| No log | 60.0 | 420 | 0.7804 | 0.4953 | 0.7804 | 0.8834 |
|
| 262 |
+
| No log | 60.2857 | 422 | 0.7702 | 0.4938 | 0.7702 | 0.8776 |
|
| 263 |
+
| No log | 60.5714 | 424 | 0.7717 | 0.5367 | 0.7717 | 0.8785 |
|
| 264 |
+
| No log | 60.8571 | 426 | 0.7952 | 0.5433 | 0.7952 | 0.8918 |
|
| 265 |
+
| No log | 61.1429 | 428 | 0.8025 | 0.5433 | 0.8025 | 0.8958 |
|
| 266 |
+
| No log | 61.4286 | 430 | 0.7891 | 0.5412 | 0.7891 | 0.8883 |
|
| 267 |
+
| No log | 61.7143 | 432 | 0.7702 | 0.5183 | 0.7702 | 0.8776 |
|
| 268 |
+
| No log | 62.0 | 434 | 0.7544 | 0.5106 | 0.7544 | 0.8686 |
|
| 269 |
+
| No log | 62.2857 | 436 | 0.7517 | 0.5465 | 0.7517 | 0.8670 |
|
| 270 |
+
| No log | 62.5714 | 438 | 0.7544 | 0.6098 | 0.7544 | 0.8686 |
|
| 271 |
+
| No log | 62.8571 | 440 | 0.7511 | 0.6255 | 0.7511 | 0.8667 |
|
| 272 |
+
| No log | 63.1429 | 442 | 0.7468 | 0.6255 | 0.7468 | 0.8642 |
|
| 273 |
+
| No log | 63.4286 | 444 | 0.7375 | 0.6098 | 0.7375 | 0.8588 |
|
| 274 |
+
| No log | 63.7143 | 446 | 0.7320 | 0.6098 | 0.7320 | 0.8555 |
|
| 275 |
+
| No log | 64.0 | 448 | 0.7329 | 0.5824 | 0.7329 | 0.8561 |
|
| 276 |
+
| No log | 64.2857 | 450 | 0.7376 | 0.5824 | 0.7376 | 0.8588 |
|
| 277 |
+
| No log | 64.5714 | 452 | 0.7409 | 0.5977 | 0.7409 | 0.8608 |
|
| 278 |
+
| No log | 64.8571 | 454 | 0.7438 | 0.5977 | 0.7438 | 0.8624 |
|
| 279 |
+
| No log | 65.1429 | 456 | 0.7386 | 0.5819 | 0.7386 | 0.8594 |
|
| 280 |
+
| No log | 65.4286 | 458 | 0.7357 | 0.6017 | 0.7357 | 0.8577 |
|
| 281 |
+
| No log | 65.7143 | 460 | 0.7493 | 0.5476 | 0.7493 | 0.8656 |
|
| 282 |
+
| No log | 66.0 | 462 | 0.7717 | 0.5412 | 0.7717 | 0.8785 |
|
| 283 |
+
| No log | 66.2857 | 464 | 0.7819 | 0.5412 | 0.7819 | 0.8842 |
|
| 284 |
+
| No log | 66.5714 | 466 | 0.7760 | 0.5392 | 0.7760 | 0.8809 |
|
| 285 |
+
| No log | 66.8571 | 468 | 0.7717 | 0.5539 | 0.7717 | 0.8784 |
|
| 286 |
+
| No log | 67.1429 | 470 | 0.7656 | 0.5884 | 0.7656 | 0.8750 |
|
| 287 |
+
| No log | 67.4286 | 472 | 0.7635 | 0.5884 | 0.7635 | 0.8738 |
|
| 288 |
+
| No log | 67.7143 | 474 | 0.7560 | 0.5884 | 0.7560 | 0.8695 |
|
| 289 |
+
| No log | 68.0 | 476 | 0.7496 | 0.5965 | 0.7496 | 0.8658 |
|
| 290 |
+
| No log | 68.2857 | 478 | 0.7516 | 0.5917 | 0.7516 | 0.8670 |
|
| 291 |
+
| No log | 68.5714 | 480 | 0.7530 | 0.5715 | 0.7530 | 0.8678 |
|
| 292 |
+
| No log | 68.8571 | 482 | 0.7475 | 0.5819 | 0.7475 | 0.8646 |
|
| 293 |
+
| No log | 69.1429 | 484 | 0.7461 | 0.5951 | 0.7461 | 0.8638 |
|
| 294 |
+
| No log | 69.4286 | 486 | 0.7495 | 0.5727 | 0.7495 | 0.8657 |
|
| 295 |
+
| No log | 69.7143 | 488 | 0.7575 | 0.5412 | 0.7575 | 0.8703 |
|
| 296 |
+
| No log | 70.0 | 490 | 0.7615 | 0.5412 | 0.7615 | 0.8726 |
|
| 297 |
+
| No log | 70.2857 | 492 | 0.7560 | 0.5833 | 0.7560 | 0.8695 |
|
| 298 |
+
| No log | 70.5714 | 494 | 0.7507 | 0.5972 | 0.7507 | 0.8664 |
|
| 299 |
+
| No log | 70.8571 | 496 | 0.7597 | 0.5930 | 0.7597 | 0.8716 |
|
| 300 |
+
| No log | 71.1429 | 498 | 0.7906 | 0.6222 | 0.7906 | 0.8891 |
|
| 301 |
+
| 0.2712 | 71.4286 | 500 | 0.8106 | 0.6335 | 0.8106 | 0.9003 |
|
| 302 |
+
| 0.2712 | 71.7143 | 502 | 0.8150 | 0.6335 | 0.8150 | 0.9027 |
|
| 303 |
+
| 0.2712 | 72.0 | 504 | 0.8017 | 0.6335 | 0.8017 | 0.8954 |
|
| 304 |
+
| 0.2712 | 72.2857 | 506 | 0.7759 | 0.6014 | 0.7759 | 0.8808 |
|
| 305 |
+
| 0.2712 | 72.5714 | 508 | 0.7516 | 0.5873 | 0.7516 | 0.8670 |
|
| 306 |
+
| 0.2712 | 72.8571 | 510 | 0.7445 | 0.5680 | 0.7445 | 0.8628 |
|
| 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:f6cd2fdabe76fd597104596218ac4d2ba8312502885429bab52d70416f41e813
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7cc7f5669a88166e601f9589f4f4a8b3eea22ea673128979f888be2c1910470
|
| 3 |
+
size 5368
|