Training in progress, step 500
Browse files- README.md +326 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k18_task5_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_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k18_task5_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: 0.6499
|
| 19 |
+
- Qwk: 0.5357
|
| 20 |
+
- Mse: 0.6499
|
| 21 |
+
- Rmse: 0.8062
|
| 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 | 0.0222 | 2 | 3.9129 | 0.0130 | 3.9129 | 1.9781 |
|
| 53 |
+
| No log | 0.0444 | 4 | 2.1232 | 0.0440 | 2.1232 | 1.4571 |
|
| 54 |
+
| No log | 0.0667 | 6 | 1.1945 | 0.1142 | 1.1945 | 1.0929 |
|
| 55 |
+
| No log | 0.0889 | 8 | 1.1280 | 0.1142 | 1.1280 | 1.0621 |
|
| 56 |
+
| No log | 0.1111 | 10 | 0.9840 | 0.4675 | 0.9840 | 0.9920 |
|
| 57 |
+
| No log | 0.1333 | 12 | 1.0354 | 0.2288 | 1.0354 | 1.0176 |
|
| 58 |
+
| No log | 0.1556 | 14 | 1.1461 | 0.0941 | 1.1461 | 1.0706 |
|
| 59 |
+
| No log | 0.1778 | 16 | 1.2118 | 0.1057 | 1.2118 | 1.1008 |
|
| 60 |
+
| No log | 0.2 | 18 | 1.3854 | -0.0411 | 1.3854 | 1.1770 |
|
| 61 |
+
| No log | 0.2222 | 20 | 1.5092 | 0.0 | 1.5092 | 1.2285 |
|
| 62 |
+
| No log | 0.2444 | 22 | 1.5183 | 0.0143 | 1.5183 | 1.2322 |
|
| 63 |
+
| No log | 0.2667 | 24 | 1.4516 | 0.0 | 1.4516 | 1.2048 |
|
| 64 |
+
| No log | 0.2889 | 26 | 1.2695 | 0.0 | 1.2695 | 1.1267 |
|
| 65 |
+
| No log | 0.3111 | 28 | 1.1315 | 0.1324 | 1.1315 | 1.0637 |
|
| 66 |
+
| No log | 0.3333 | 30 | 1.0698 | 0.3037 | 1.0698 | 1.0343 |
|
| 67 |
+
| No log | 0.3556 | 32 | 1.0028 | 0.2740 | 1.0028 | 1.0014 |
|
| 68 |
+
| No log | 0.3778 | 34 | 1.0006 | 0.2615 | 1.0006 | 1.0003 |
|
| 69 |
+
| No log | 0.4 | 36 | 0.9782 | 0.2441 | 0.9782 | 0.9890 |
|
| 70 |
+
| No log | 0.4222 | 38 | 1.0626 | 0.2615 | 1.0626 | 1.0308 |
|
| 71 |
+
| No log | 0.4444 | 40 | 1.0560 | 0.3435 | 1.0560 | 1.0276 |
|
| 72 |
+
| No log | 0.4667 | 42 | 0.9666 | 0.3583 | 0.9666 | 0.9832 |
|
| 73 |
+
| No log | 0.4889 | 44 | 0.8951 | 0.2998 | 0.8951 | 0.9461 |
|
| 74 |
+
| No log | 0.5111 | 46 | 0.8235 | 0.3443 | 0.8235 | 0.9075 |
|
| 75 |
+
| No log | 0.5333 | 48 | 0.7859 | 0.3961 | 0.7859 | 0.8865 |
|
| 76 |
+
| No log | 0.5556 | 50 | 0.7792 | 0.3834 | 0.7792 | 0.8827 |
|
| 77 |
+
| No log | 0.5778 | 52 | 0.8618 | 0.3635 | 0.8618 | 0.9284 |
|
| 78 |
+
| No log | 0.6 | 54 | 0.7699 | 0.4472 | 0.7699 | 0.8775 |
|
| 79 |
+
| No log | 0.6222 | 56 | 0.7980 | 0.5988 | 0.7980 | 0.8933 |
|
| 80 |
+
| No log | 0.6444 | 58 | 1.0663 | 0.4173 | 1.0663 | 1.0326 |
|
| 81 |
+
| No log | 0.6667 | 60 | 0.8934 | 0.5019 | 0.8934 | 0.9452 |
|
| 82 |
+
| No log | 0.6889 | 62 | 0.7483 | 0.4524 | 0.7483 | 0.8650 |
|
| 83 |
+
| No log | 0.7111 | 64 | 0.6972 | 0.5274 | 0.6972 | 0.8350 |
|
| 84 |
+
| No log | 0.7333 | 66 | 0.6558 | 0.5950 | 0.6558 | 0.8098 |
|
| 85 |
+
| No log | 0.7556 | 68 | 0.6810 | 0.6205 | 0.6810 | 0.8252 |
|
| 86 |
+
| No log | 0.7778 | 70 | 0.7356 | 0.5578 | 0.7356 | 0.8577 |
|
| 87 |
+
| No log | 0.8 | 72 | 0.6904 | 0.6112 | 0.6904 | 0.8309 |
|
| 88 |
+
| No log | 0.8222 | 74 | 0.6401 | 0.5945 | 0.6401 | 0.8000 |
|
| 89 |
+
| No log | 0.8444 | 76 | 0.6112 | 0.5887 | 0.6112 | 0.7818 |
|
| 90 |
+
| No log | 0.8667 | 78 | 0.6017 | 0.6195 | 0.6017 | 0.7757 |
|
| 91 |
+
| No log | 0.8889 | 80 | 0.5960 | 0.6195 | 0.5960 | 0.7720 |
|
| 92 |
+
| No log | 0.9111 | 82 | 0.5867 | 0.6195 | 0.5867 | 0.7660 |
|
| 93 |
+
| No log | 0.9333 | 84 | 0.5971 | 0.5944 | 0.5971 | 0.7727 |
|
| 94 |
+
| No log | 0.9556 | 86 | 0.7895 | 0.5670 | 0.7895 | 0.8886 |
|
| 95 |
+
| No log | 0.9778 | 88 | 0.6908 | 0.5898 | 0.6908 | 0.8311 |
|
| 96 |
+
| No log | 1.0 | 90 | 0.6813 | 0.6272 | 0.6813 | 0.8254 |
|
| 97 |
+
| No log | 1.0222 | 92 | 0.6795 | 0.6377 | 0.6795 | 0.8243 |
|
| 98 |
+
| No log | 1.0444 | 94 | 0.6651 | 0.6377 | 0.6651 | 0.8155 |
|
| 99 |
+
| No log | 1.0667 | 96 | 0.6349 | 0.6233 | 0.6349 | 0.7968 |
|
| 100 |
+
| No log | 1.0889 | 98 | 0.6724 | 0.6609 | 0.6724 | 0.8200 |
|
| 101 |
+
| No log | 1.1111 | 100 | 0.7379 | 0.6160 | 0.7379 | 0.8590 |
|
| 102 |
+
| No log | 1.1333 | 102 | 0.7688 | 0.5067 | 0.7688 | 0.8768 |
|
| 103 |
+
| No log | 1.1556 | 104 | 0.8947 | 0.3525 | 0.8947 | 0.9459 |
|
| 104 |
+
| No log | 1.1778 | 106 | 0.8530 | 0.4192 | 0.8530 | 0.9236 |
|
| 105 |
+
| No log | 1.2 | 108 | 0.7708 | 0.4259 | 0.7708 | 0.8780 |
|
| 106 |
+
| No log | 1.2222 | 110 | 0.7202 | 0.4908 | 0.7202 | 0.8486 |
|
| 107 |
+
| No log | 1.2444 | 112 | 0.6979 | 0.5570 | 0.6979 | 0.8354 |
|
| 108 |
+
| No log | 1.2667 | 114 | 0.6778 | 0.6094 | 0.6778 | 0.8233 |
|
| 109 |
+
| No log | 1.2889 | 116 | 0.7159 | 0.6520 | 0.7159 | 0.8461 |
|
| 110 |
+
| No log | 1.3111 | 118 | 0.7287 | 0.6584 | 0.7287 | 0.8537 |
|
| 111 |
+
| No log | 1.3333 | 120 | 0.6594 | 0.6564 | 0.6594 | 0.8120 |
|
| 112 |
+
| No log | 1.3556 | 122 | 0.6749 | 0.5995 | 0.6749 | 0.8215 |
|
| 113 |
+
| No log | 1.3778 | 124 | 0.6412 | 0.6275 | 0.6412 | 0.8007 |
|
| 114 |
+
| No log | 1.4 | 126 | 0.6384 | 0.6617 | 0.6384 | 0.7990 |
|
| 115 |
+
| No log | 1.4222 | 128 | 0.6954 | 0.6386 | 0.6954 | 0.8339 |
|
| 116 |
+
| No log | 1.4444 | 130 | 0.6776 | 0.6319 | 0.6776 | 0.8232 |
|
| 117 |
+
| No log | 1.4667 | 132 | 0.6506 | 0.6328 | 0.6506 | 0.8066 |
|
| 118 |
+
| No log | 1.4889 | 134 | 0.6502 | 0.5909 | 0.6502 | 0.8063 |
|
| 119 |
+
| No log | 1.5111 | 136 | 0.6504 | 0.6058 | 0.6504 | 0.8065 |
|
| 120 |
+
| No log | 1.5333 | 138 | 0.6502 | 0.5909 | 0.6502 | 0.8063 |
|
| 121 |
+
| No log | 1.5556 | 140 | 0.6697 | 0.5704 | 0.6697 | 0.8184 |
|
| 122 |
+
| No log | 1.5778 | 142 | 0.7963 | 0.5247 | 0.7963 | 0.8924 |
|
| 123 |
+
| No log | 1.6 | 144 | 0.7244 | 0.6125 | 0.7244 | 0.8511 |
|
| 124 |
+
| No log | 1.6222 | 146 | 0.6569 | 0.6051 | 0.6569 | 0.8105 |
|
| 125 |
+
| No log | 1.6444 | 148 | 0.6785 | 0.6459 | 0.6785 | 0.8237 |
|
| 126 |
+
| No log | 1.6667 | 150 | 0.6827 | 0.6169 | 0.6827 | 0.8263 |
|
| 127 |
+
| No log | 1.6889 | 152 | 0.6790 | 0.5657 | 0.6790 | 0.8240 |
|
| 128 |
+
| No log | 1.7111 | 154 | 0.6906 | 0.5675 | 0.6906 | 0.8310 |
|
| 129 |
+
| No log | 1.7333 | 156 | 0.6888 | 0.5675 | 0.6888 | 0.8299 |
|
| 130 |
+
| No log | 1.7556 | 158 | 0.6694 | 0.6626 | 0.6694 | 0.8181 |
|
| 131 |
+
| No log | 1.7778 | 160 | 0.6941 | 0.6421 | 0.6941 | 0.8331 |
|
| 132 |
+
| No log | 1.8 | 162 | 0.6749 | 0.6642 | 0.6749 | 0.8215 |
|
| 133 |
+
| No log | 1.8222 | 164 | 0.6778 | 0.6148 | 0.6778 | 0.8233 |
|
| 134 |
+
| No log | 1.8444 | 166 | 0.6701 | 0.6186 | 0.6701 | 0.8186 |
|
| 135 |
+
| No log | 1.8667 | 168 | 0.6812 | 0.6446 | 0.6812 | 0.8253 |
|
| 136 |
+
| No log | 1.8889 | 170 | 0.6657 | 0.6066 | 0.6657 | 0.8159 |
|
| 137 |
+
| No log | 1.9111 | 172 | 0.6945 | 0.6060 | 0.6945 | 0.8334 |
|
| 138 |
+
| No log | 1.9333 | 174 | 0.6870 | 0.5681 | 0.6870 | 0.8288 |
|
| 139 |
+
| No log | 1.9556 | 176 | 0.6591 | 0.5301 | 0.6591 | 0.8119 |
|
| 140 |
+
| No log | 1.9778 | 178 | 0.6805 | 0.5953 | 0.6805 | 0.8250 |
|
| 141 |
+
| No log | 2.0 | 180 | 0.7243 | 0.5891 | 0.7243 | 0.8511 |
|
| 142 |
+
| No log | 2.0222 | 182 | 0.7141 | 0.6190 | 0.7141 | 0.8450 |
|
| 143 |
+
| No log | 2.0444 | 184 | 0.6087 | 0.7035 | 0.6087 | 0.7802 |
|
| 144 |
+
| No log | 2.0667 | 186 | 0.6039 | 0.6546 | 0.6039 | 0.7771 |
|
| 145 |
+
| No log | 2.0889 | 188 | 0.6024 | 0.6627 | 0.6024 | 0.7761 |
|
| 146 |
+
| No log | 2.1111 | 190 | 0.6056 | 0.6782 | 0.6056 | 0.7782 |
|
| 147 |
+
| No log | 2.1333 | 192 | 0.6452 | 0.5888 | 0.6452 | 0.8032 |
|
| 148 |
+
| No log | 2.1556 | 194 | 0.6287 | 0.6249 | 0.6287 | 0.7929 |
|
| 149 |
+
| No log | 2.1778 | 196 | 0.6199 | 0.6664 | 0.6199 | 0.7874 |
|
| 150 |
+
| No log | 2.2 | 198 | 0.6274 | 0.6114 | 0.6274 | 0.7921 |
|
| 151 |
+
| No log | 2.2222 | 200 | 0.6410 | 0.6076 | 0.6410 | 0.8006 |
|
| 152 |
+
| No log | 2.2444 | 202 | 0.6901 | 0.6198 | 0.6901 | 0.8307 |
|
| 153 |
+
| No log | 2.2667 | 204 | 0.6669 | 0.6333 | 0.6669 | 0.8166 |
|
| 154 |
+
| No log | 2.2889 | 206 | 0.6813 | 0.6006 | 0.6813 | 0.8254 |
|
| 155 |
+
| No log | 2.3111 | 208 | 0.6754 | 0.6102 | 0.6754 | 0.8219 |
|
| 156 |
+
| No log | 2.3333 | 210 | 0.6610 | 0.6102 | 0.6610 | 0.8130 |
|
| 157 |
+
| No log | 2.3556 | 212 | 0.6545 | 0.5969 | 0.6545 | 0.8090 |
|
| 158 |
+
| No log | 2.3778 | 214 | 0.6343 | 0.6157 | 0.6343 | 0.7964 |
|
| 159 |
+
| No log | 2.4 | 216 | 0.6108 | 0.6455 | 0.6108 | 0.7816 |
|
| 160 |
+
| No log | 2.4222 | 218 | 0.6398 | 0.6929 | 0.6398 | 0.7999 |
|
| 161 |
+
| No log | 2.4444 | 220 | 0.6337 | 0.5747 | 0.6337 | 0.7961 |
|
| 162 |
+
| No log | 2.4667 | 222 | 0.6524 | 0.5522 | 0.6524 | 0.8077 |
|
| 163 |
+
| No log | 2.4889 | 224 | 0.7284 | 0.5916 | 0.7284 | 0.8535 |
|
| 164 |
+
| No log | 2.5111 | 226 | 0.7048 | 0.6343 | 0.7048 | 0.8395 |
|
| 165 |
+
| No log | 2.5333 | 228 | 0.6163 | 0.5724 | 0.6163 | 0.7851 |
|
| 166 |
+
| No log | 2.5556 | 230 | 0.6005 | 0.5606 | 0.6005 | 0.7749 |
|
| 167 |
+
| No log | 2.5778 | 232 | 0.5939 | 0.6764 | 0.5939 | 0.7706 |
|
| 168 |
+
| No log | 2.6 | 234 | 0.7110 | 0.6114 | 0.7110 | 0.8432 |
|
| 169 |
+
| No log | 2.6222 | 236 | 0.8189 | 0.5573 | 0.8189 | 0.9049 |
|
| 170 |
+
| No log | 2.6444 | 238 | 0.7402 | 0.5928 | 0.7402 | 0.8603 |
|
| 171 |
+
| No log | 2.6667 | 240 | 0.6469 | 0.6976 | 0.6469 | 0.8043 |
|
| 172 |
+
| No log | 2.6889 | 242 | 0.6015 | 0.6936 | 0.6015 | 0.7756 |
|
| 173 |
+
| No log | 2.7111 | 244 | 0.6028 | 0.6114 | 0.6028 | 0.7764 |
|
| 174 |
+
| No log | 2.7333 | 246 | 0.6028 | 0.6239 | 0.6028 | 0.7764 |
|
| 175 |
+
| No log | 2.7556 | 248 | 0.5953 | 0.6347 | 0.5953 | 0.7716 |
|
| 176 |
+
| No log | 2.7778 | 250 | 0.6294 | 0.6464 | 0.6294 | 0.7933 |
|
| 177 |
+
| No log | 2.8 | 252 | 0.6041 | 0.6361 | 0.6041 | 0.7773 |
|
| 178 |
+
| No log | 2.8222 | 254 | 0.5982 | 0.6547 | 0.5982 | 0.7734 |
|
| 179 |
+
| No log | 2.8444 | 256 | 0.5877 | 0.6564 | 0.5877 | 0.7666 |
|
| 180 |
+
| No log | 2.8667 | 258 | 0.6752 | 0.5586 | 0.6752 | 0.8217 |
|
| 181 |
+
| No log | 2.8889 | 260 | 0.6537 | 0.5107 | 0.6537 | 0.8085 |
|
| 182 |
+
| No log | 2.9111 | 262 | 0.6520 | 0.6371 | 0.6520 | 0.8074 |
|
| 183 |
+
| No log | 2.9333 | 264 | 0.7166 | 0.6230 | 0.7166 | 0.8465 |
|
| 184 |
+
| No log | 2.9556 | 266 | 0.7061 | 0.6429 | 0.7061 | 0.8403 |
|
| 185 |
+
| No log | 2.9778 | 268 | 0.6516 | 0.6157 | 0.6516 | 0.8072 |
|
| 186 |
+
| No log | 3.0 | 270 | 0.7446 | 0.5782 | 0.7446 | 0.8629 |
|
| 187 |
+
| No log | 3.0222 | 272 | 0.7622 | 0.5364 | 0.7622 | 0.8731 |
|
| 188 |
+
| No log | 3.0444 | 274 | 0.6769 | 0.5530 | 0.6769 | 0.8228 |
|
| 189 |
+
| No log | 3.0667 | 276 | 0.6856 | 0.6073 | 0.6856 | 0.8280 |
|
| 190 |
+
| No log | 3.0889 | 278 | 0.9294 | 0.4854 | 0.9294 | 0.9640 |
|
| 191 |
+
| No log | 3.1111 | 280 | 1.0083 | 0.4555 | 1.0083 | 1.0041 |
|
| 192 |
+
| No log | 3.1333 | 282 | 0.9526 | 0.4946 | 0.9526 | 0.9760 |
|
| 193 |
+
| No log | 3.1556 | 284 | 0.7931 | 0.4818 | 0.7931 | 0.8905 |
|
| 194 |
+
| No log | 3.1778 | 286 | 0.7013 | 0.4398 | 0.7013 | 0.8374 |
|
| 195 |
+
| No log | 3.2 | 288 | 0.6846 | 0.5089 | 0.6846 | 0.8274 |
|
| 196 |
+
| No log | 3.2222 | 290 | 0.6428 | 0.5089 | 0.6428 | 0.8018 |
|
| 197 |
+
| No log | 3.2444 | 292 | 0.6031 | 0.6207 | 0.6031 | 0.7766 |
|
| 198 |
+
| No log | 3.2667 | 294 | 0.6736 | 0.6529 | 0.6736 | 0.8208 |
|
| 199 |
+
| No log | 3.2889 | 296 | 0.7026 | 0.6520 | 0.7026 | 0.8382 |
|
| 200 |
+
| No log | 3.3111 | 298 | 0.6401 | 0.6429 | 0.6401 | 0.8000 |
|
| 201 |
+
| No log | 3.3333 | 300 | 0.5998 | 0.6113 | 0.5998 | 0.7745 |
|
| 202 |
+
| No log | 3.3556 | 302 | 0.6027 | 0.6154 | 0.6027 | 0.7763 |
|
| 203 |
+
| No log | 3.3778 | 304 | 0.6083 | 0.6219 | 0.6083 | 0.7799 |
|
| 204 |
+
| No log | 3.4 | 306 | 0.6577 | 0.6071 | 0.6577 | 0.8110 |
|
| 205 |
+
| No log | 3.4222 | 308 | 0.7743 | 0.5447 | 0.7743 | 0.8800 |
|
| 206 |
+
| No log | 3.4444 | 310 | 0.8144 | 0.5102 | 0.8144 | 0.9025 |
|
| 207 |
+
| No log | 3.4667 | 312 | 0.7696 | 0.5800 | 0.7696 | 0.8773 |
|
| 208 |
+
| No log | 3.4889 | 314 | 0.6801 | 0.6367 | 0.6801 | 0.8247 |
|
| 209 |
+
| No log | 3.5111 | 316 | 0.5893 | 0.6177 | 0.5893 | 0.7676 |
|
| 210 |
+
| No log | 3.5333 | 318 | 0.5714 | 0.6479 | 0.5714 | 0.7559 |
|
| 211 |
+
| No log | 3.5556 | 320 | 0.5657 | 0.6479 | 0.5657 | 0.7521 |
|
| 212 |
+
| No log | 3.5778 | 322 | 0.5440 | 0.6988 | 0.5440 | 0.7375 |
|
| 213 |
+
| No log | 3.6 | 324 | 0.5798 | 0.6900 | 0.5798 | 0.7614 |
|
| 214 |
+
| No log | 3.6222 | 326 | 0.6771 | 0.5915 | 0.6771 | 0.8228 |
|
| 215 |
+
| No log | 3.6444 | 328 | 0.7343 | 0.5882 | 0.7343 | 0.8569 |
|
| 216 |
+
| No log | 3.6667 | 330 | 0.6886 | 0.6141 | 0.6886 | 0.8298 |
|
| 217 |
+
| No log | 3.6889 | 332 | 0.6233 | 0.6188 | 0.6233 | 0.7895 |
|
| 218 |
+
| No log | 3.7111 | 334 | 0.6181 | 0.5171 | 0.6181 | 0.7862 |
|
| 219 |
+
| No log | 3.7333 | 336 | 0.6464 | 0.4829 | 0.6464 | 0.8040 |
|
| 220 |
+
| No log | 3.7556 | 338 | 0.6576 | 0.4966 | 0.6576 | 0.8110 |
|
| 221 |
+
| No log | 3.7778 | 340 | 0.6538 | 0.5093 | 0.6538 | 0.8086 |
|
| 222 |
+
| No log | 3.8 | 342 | 0.6352 | 0.4557 | 0.6352 | 0.7970 |
|
| 223 |
+
| No log | 3.8222 | 344 | 0.6511 | 0.5002 | 0.6511 | 0.8069 |
|
| 224 |
+
| No log | 3.8444 | 346 | 0.6910 | 0.5858 | 0.6910 | 0.8313 |
|
| 225 |
+
| No log | 3.8667 | 348 | 0.7334 | 0.6117 | 0.7334 | 0.8564 |
|
| 226 |
+
| No log | 3.8889 | 350 | 0.6780 | 0.5763 | 0.6780 | 0.8234 |
|
| 227 |
+
| No log | 3.9111 | 352 | 0.6398 | 0.5498 | 0.6398 | 0.7999 |
|
| 228 |
+
| No log | 3.9333 | 354 | 0.6473 | 0.5386 | 0.6473 | 0.8045 |
|
| 229 |
+
| No log | 3.9556 | 356 | 0.6506 | 0.5498 | 0.6506 | 0.8066 |
|
| 230 |
+
| No log | 3.9778 | 358 | 0.6467 | 0.5917 | 0.6467 | 0.8042 |
|
| 231 |
+
| No log | 4.0 | 360 | 0.6409 | 0.5386 | 0.6409 | 0.8006 |
|
| 232 |
+
| No log | 4.0222 | 362 | 0.6279 | 0.5917 | 0.6279 | 0.7924 |
|
| 233 |
+
| No log | 4.0444 | 364 | 0.6234 | 0.5724 | 0.6234 | 0.7896 |
|
| 234 |
+
| No log | 4.0667 | 366 | 0.6203 | 0.5833 | 0.6203 | 0.7876 |
|
| 235 |
+
| No log | 4.0889 | 368 | 0.6364 | 0.5798 | 0.6364 | 0.7977 |
|
| 236 |
+
| No log | 4.1111 | 370 | 0.6559 | 0.5798 | 0.6559 | 0.8099 |
|
| 237 |
+
| No log | 4.1333 | 372 | 0.6519 | 0.5710 | 0.6519 | 0.8074 |
|
| 238 |
+
| No log | 4.1556 | 374 | 0.6683 | 0.5937 | 0.6683 | 0.8175 |
|
| 239 |
+
| No log | 4.1778 | 376 | 0.7240 | 0.5579 | 0.7240 | 0.8509 |
|
| 240 |
+
| No log | 4.2 | 378 | 0.7673 | 0.5219 | 0.7673 | 0.8760 |
|
| 241 |
+
| No log | 4.2222 | 380 | 0.7239 | 0.5242 | 0.7239 | 0.8508 |
|
| 242 |
+
| No log | 4.2444 | 382 | 0.6325 | 0.5894 | 0.6325 | 0.7953 |
|
| 243 |
+
| No log | 4.2667 | 384 | 0.6216 | 0.5523 | 0.6216 | 0.7884 |
|
| 244 |
+
| No log | 4.2889 | 386 | 0.6423 | 0.5548 | 0.6423 | 0.8014 |
|
| 245 |
+
| No log | 4.3111 | 388 | 0.6323 | 0.5402 | 0.6323 | 0.7952 |
|
| 246 |
+
| No log | 4.3333 | 390 | 0.6650 | 0.6051 | 0.6650 | 0.8155 |
|
| 247 |
+
| No log | 4.3556 | 392 | 0.7243 | 0.5598 | 0.7243 | 0.8511 |
|
| 248 |
+
| No log | 4.3778 | 394 | 0.7022 | 0.6090 | 0.7022 | 0.8380 |
|
| 249 |
+
| No log | 4.4 | 396 | 0.6746 | 0.6221 | 0.6746 | 0.8214 |
|
| 250 |
+
| No log | 4.4222 | 398 | 0.6440 | 0.6460 | 0.6440 | 0.8025 |
|
| 251 |
+
| No log | 4.4444 | 400 | 0.6530 | 0.6221 | 0.6530 | 0.8081 |
|
| 252 |
+
| No log | 4.4667 | 402 | 0.7122 | 0.6032 | 0.7122 | 0.8439 |
|
| 253 |
+
| No log | 4.4889 | 404 | 0.7668 | 0.5543 | 0.7668 | 0.8757 |
|
| 254 |
+
| No log | 4.5111 | 406 | 0.7645 | 0.5655 | 0.7645 | 0.8743 |
|
| 255 |
+
| No log | 4.5333 | 408 | 0.6726 | 0.6221 | 0.6726 | 0.8201 |
|
| 256 |
+
| No log | 4.5556 | 410 | 0.6309 | 0.6165 | 0.6309 | 0.7943 |
|
| 257 |
+
| No log | 4.5778 | 412 | 0.6344 | 0.5644 | 0.6344 | 0.7965 |
|
| 258 |
+
| No log | 4.6 | 414 | 0.6426 | 0.5472 | 0.6426 | 0.8016 |
|
| 259 |
+
| No log | 4.6222 | 416 | 0.6923 | 0.5981 | 0.6923 | 0.8321 |
|
| 260 |
+
| No log | 4.6444 | 418 | 0.7239 | 0.5739 | 0.7239 | 0.8508 |
|
| 261 |
+
| No log | 4.6667 | 420 | 0.6931 | 0.6009 | 0.6931 | 0.8325 |
|
| 262 |
+
| No log | 4.6889 | 422 | 0.6541 | 0.5709 | 0.6541 | 0.8088 |
|
| 263 |
+
| No log | 4.7111 | 424 | 0.6233 | 0.6311 | 0.6233 | 0.7895 |
|
| 264 |
+
| No log | 4.7333 | 426 | 0.6215 | 0.6177 | 0.6215 | 0.7884 |
|
| 265 |
+
| No log | 4.7556 | 428 | 0.6347 | 0.6500 | 0.6347 | 0.7967 |
|
| 266 |
+
| No log | 4.7778 | 430 | 0.6234 | 0.6102 | 0.6234 | 0.7896 |
|
| 267 |
+
| No log | 4.8 | 432 | 0.6385 | 0.6102 | 0.6385 | 0.7990 |
|
| 268 |
+
| No log | 4.8222 | 434 | 0.6404 | 0.6073 | 0.6404 | 0.8002 |
|
| 269 |
+
| No log | 4.8444 | 436 | 0.6246 | 0.6102 | 0.6246 | 0.7903 |
|
| 270 |
+
| No log | 4.8667 | 438 | 0.6327 | 0.6073 | 0.6327 | 0.7954 |
|
| 271 |
+
| No log | 4.8889 | 440 | 0.6654 | 0.6188 | 0.6654 | 0.8157 |
|
| 272 |
+
| No log | 4.9111 | 442 | 0.6582 | 0.5975 | 0.6582 | 0.8113 |
|
| 273 |
+
| No log | 4.9333 | 444 | 0.6433 | 0.5894 | 0.6433 | 0.8021 |
|
| 274 |
+
| No log | 4.9556 | 446 | 0.6356 | 0.5288 | 0.6356 | 0.7973 |
|
| 275 |
+
| No log | 4.9778 | 448 | 0.6394 | 0.5288 | 0.6394 | 0.7996 |
|
| 276 |
+
| No log | 5.0 | 450 | 0.6496 | 0.6014 | 0.6496 | 0.8060 |
|
| 277 |
+
| No log | 5.0222 | 452 | 0.6752 | 0.5729 | 0.6752 | 0.8217 |
|
| 278 |
+
| No log | 5.0444 | 454 | 0.6659 | 0.5729 | 0.6659 | 0.8160 |
|
| 279 |
+
| No log | 5.0667 | 456 | 0.6460 | 0.5688 | 0.6460 | 0.8037 |
|
| 280 |
+
| No log | 5.0889 | 458 | 0.6551 | 0.5490 | 0.6551 | 0.8094 |
|
| 281 |
+
| No log | 5.1111 | 460 | 0.6683 | 0.5010 | 0.6683 | 0.8175 |
|
| 282 |
+
| No log | 5.1333 | 462 | 0.6960 | 0.5634 | 0.6960 | 0.8343 |
|
| 283 |
+
| No log | 5.1556 | 464 | 0.6955 | 0.5614 | 0.6955 | 0.8339 |
|
| 284 |
+
| No log | 5.1778 | 466 | 0.6553 | 0.5597 | 0.6553 | 0.8095 |
|
| 285 |
+
| No log | 5.2 | 468 | 0.6333 | 0.5040 | 0.6333 | 0.7958 |
|
| 286 |
+
| No log | 5.2222 | 470 | 0.6253 | 0.6084 | 0.6253 | 0.7908 |
|
| 287 |
+
| No log | 5.2444 | 472 | 0.6295 | 0.6014 | 0.6295 | 0.7934 |
|
| 288 |
+
| No log | 5.2667 | 474 | 0.6351 | 0.6386 | 0.6351 | 0.7969 |
|
| 289 |
+
| No log | 5.2889 | 476 | 0.6218 | 0.6386 | 0.6218 | 0.7885 |
|
| 290 |
+
| No log | 5.3111 | 478 | 0.5967 | 0.6597 | 0.5967 | 0.7725 |
|
| 291 |
+
| No log | 5.3333 | 480 | 0.5941 | 0.6517 | 0.5941 | 0.7708 |
|
| 292 |
+
| No log | 5.3556 | 482 | 0.6042 | 0.6185 | 0.6042 | 0.7773 |
|
| 293 |
+
| No log | 5.3778 | 484 | 0.5874 | 0.6805 | 0.5874 | 0.7664 |
|
| 294 |
+
| No log | 5.4 | 486 | 0.6161 | 0.6259 | 0.6161 | 0.7849 |
|
| 295 |
+
| No log | 5.4222 | 488 | 0.6722 | 0.6189 | 0.6722 | 0.8199 |
|
| 296 |
+
| No log | 5.4444 | 490 | 0.6832 | 0.6319 | 0.6832 | 0.8266 |
|
| 297 |
+
| No log | 5.4667 | 492 | 0.6471 | 0.5894 | 0.6471 | 0.8044 |
|
| 298 |
+
| No log | 5.4889 | 494 | 0.6205 | 0.5666 | 0.6205 | 0.7877 |
|
| 299 |
+
| No log | 5.5111 | 496 | 0.6277 | 0.5450 | 0.6277 | 0.7923 |
|
| 300 |
+
| No log | 5.5333 | 498 | 0.6362 | 0.5522 | 0.6362 | 0.7976 |
|
| 301 |
+
| 0.3047 | 5.5556 | 500 | 0.6558 | 0.5758 | 0.6558 | 0.8098 |
|
| 302 |
+
| 0.3047 | 5.5778 | 502 | 0.6672 | 0.6176 | 0.6672 | 0.8168 |
|
| 303 |
+
| 0.3047 | 5.6 | 504 | 0.7278 | 0.5241 | 0.7278 | 0.8531 |
|
| 304 |
+
| 0.3047 | 5.6222 | 506 | 0.7938 | 0.5417 | 0.7938 | 0.8910 |
|
| 305 |
+
| 0.3047 | 5.6444 | 508 | 0.7186 | 0.5636 | 0.7186 | 0.8477 |
|
| 306 |
+
| 0.3047 | 5.6667 | 510 | 0.5972 | 0.6771 | 0.5972 | 0.7728 |
|
| 307 |
+
| 0.3047 | 5.6889 | 512 | 0.5966 | 0.5747 | 0.5966 | 0.7724 |
|
| 308 |
+
| 0.3047 | 5.7111 | 514 | 0.6035 | 0.5644 | 0.6035 | 0.7769 |
|
| 309 |
+
| 0.3047 | 5.7333 | 516 | 0.6191 | 0.5972 | 0.6191 | 0.7868 |
|
| 310 |
+
| 0.3047 | 5.7556 | 518 | 0.6392 | 0.5710 | 0.6392 | 0.7995 |
|
| 311 |
+
| 0.3047 | 5.7778 | 520 | 0.6529 | 0.5921 | 0.6529 | 0.8080 |
|
| 312 |
+
| 0.3047 | 5.8 | 522 | 0.6818 | 0.6003 | 0.6818 | 0.8257 |
|
| 313 |
+
| 0.3047 | 5.8222 | 524 | 0.7010 | 0.6032 | 0.7010 | 0.8373 |
|
| 314 |
+
| 0.3047 | 5.8444 | 526 | 0.7083 | 0.5459 | 0.7083 | 0.8416 |
|
| 315 |
+
| 0.3047 | 5.8667 | 528 | 0.6922 | 0.5710 | 0.6922 | 0.8320 |
|
| 316 |
+
| 0.3047 | 5.8889 | 530 | 0.6779 | 0.4893 | 0.6779 | 0.8233 |
|
| 317 |
+
| 0.3047 | 5.9111 | 532 | 0.6681 | 0.4151 | 0.6681 | 0.8174 |
|
| 318 |
+
| 0.3047 | 5.9333 | 534 | 0.6499 | 0.5357 | 0.6499 | 0.8062 |
|
| 319 |
+
|
| 320 |
+
|
| 321 |
+
### Framework versions
|
| 322 |
+
|
| 323 |
+
- Transformers 4.44.2
|
| 324 |
+
- Pytorch 2.4.0+cu118
|
| 325 |
+
- Datasets 2.21.0
|
| 326 |
+
- 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:cb859d545022470b2541587866cdd3e04444ee8775b791b38dd1dd17076b8ec1
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ef08982d66ffca415b4e5b22542fe7d8a5563fcfa0e996f93e154b83d5d6c7
|
| 3 |
+
size 5304
|