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_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k12_task3_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_k12_task3_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: 0.6965
|
| 19 |
+
- Qwk: 0.1379
|
| 20 |
+
- Mse: 0.6965
|
| 21 |
+
- Rmse: 0.8346
|
| 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 | 0.0323 | 2 | 3.6688 | 0.0035 | 3.6688 | 1.9154 |
|
| 53 |
+
| No log | 0.0645 | 4 | 1.7493 | 0.0591 | 1.7493 | 1.3226 |
|
| 54 |
+
| No log | 0.0968 | 6 | 1.1215 | 0.0403 | 1.1215 | 1.0590 |
|
| 55 |
+
| No log | 0.1290 | 8 | 1.9600 | 0.0626 | 1.9600 | 1.4000 |
|
| 56 |
+
| No log | 0.1613 | 10 | 0.9659 | -0.0182 | 0.9659 | 0.9828 |
|
| 57 |
+
| No log | 0.1935 | 12 | 0.6732 | -0.0069 | 0.6732 | 0.8205 |
|
| 58 |
+
| No log | 0.2258 | 14 | 0.6677 | 0.0555 | 0.6677 | 0.8172 |
|
| 59 |
+
| No log | 0.2581 | 16 | 0.6645 | 0.0555 | 0.6645 | 0.8152 |
|
| 60 |
+
| No log | 0.2903 | 18 | 0.7197 | -0.0188 | 0.7197 | 0.8484 |
|
| 61 |
+
| No log | 0.3226 | 20 | 0.9105 | 0.0912 | 0.9105 | 0.9542 |
|
| 62 |
+
| No log | 0.3548 | 22 | 0.8497 | -0.0316 | 0.8497 | 0.9218 |
|
| 63 |
+
| No log | 0.3871 | 24 | 0.7995 | -0.0179 | 0.7995 | 0.8941 |
|
| 64 |
+
| No log | 0.4194 | 26 | 0.8723 | 0.0205 | 0.8723 | 0.9340 |
|
| 65 |
+
| No log | 0.4516 | 28 | 1.3049 | -0.0237 | 1.3049 | 1.1423 |
|
| 66 |
+
| No log | 0.4839 | 30 | 1.4813 | -0.0065 | 1.4813 | 1.2171 |
|
| 67 |
+
| No log | 0.5161 | 32 | 0.9467 | 0.0938 | 0.9467 | 0.9730 |
|
| 68 |
+
| No log | 0.5484 | 34 | 0.8727 | 0.0464 | 0.8727 | 0.9342 |
|
| 69 |
+
| No log | 0.5806 | 36 | 0.8903 | 0.1790 | 0.8903 | 0.9436 |
|
| 70 |
+
| No log | 0.6129 | 38 | 0.8195 | 0.1863 | 0.8195 | 0.9053 |
|
| 71 |
+
| No log | 0.6452 | 40 | 0.8034 | 0.1597 | 0.8034 | 0.8963 |
|
| 72 |
+
| No log | 0.6774 | 42 | 0.8024 | 0.2382 | 0.8024 | 0.8958 |
|
| 73 |
+
| No log | 0.7097 | 44 | 0.7990 | 0.2481 | 0.7990 | 0.8938 |
|
| 74 |
+
| No log | 0.7419 | 46 | 0.8485 | 0.1247 | 0.8485 | 0.9212 |
|
| 75 |
+
| No log | 0.7742 | 48 | 1.2353 | 0.0328 | 1.2353 | 1.1115 |
|
| 76 |
+
| No log | 0.8065 | 50 | 1.1903 | 0.1015 | 1.1903 | 1.0910 |
|
| 77 |
+
| No log | 0.8387 | 52 | 0.8720 | 0.1569 | 0.8720 | 0.9338 |
|
| 78 |
+
| No log | 0.8710 | 54 | 0.9832 | 0.1187 | 0.9832 | 0.9916 |
|
| 79 |
+
| No log | 0.9032 | 56 | 1.3703 | 0.1366 | 1.3703 | 1.1706 |
|
| 80 |
+
| No log | 0.9355 | 58 | 0.9817 | 0.1504 | 0.9817 | 0.9908 |
|
| 81 |
+
| No log | 0.9677 | 60 | 1.3353 | 0.1094 | 1.3353 | 1.1556 |
|
| 82 |
+
| No log | 1.0 | 62 | 1.7664 | 0.0741 | 1.7664 | 1.3291 |
|
| 83 |
+
| No log | 1.0323 | 64 | 1.0600 | 0.0623 | 1.0600 | 1.0296 |
|
| 84 |
+
| No log | 1.0645 | 66 | 0.7274 | 0.1865 | 0.7274 | 0.8529 |
|
| 85 |
+
| No log | 1.0968 | 68 | 1.0579 | 0.0848 | 1.0579 | 1.0286 |
|
| 86 |
+
| No log | 1.1290 | 70 | 0.8731 | 0.0794 | 0.8731 | 0.9344 |
|
| 87 |
+
| No log | 1.1613 | 72 | 0.7218 | 0.2883 | 0.7218 | 0.8496 |
|
| 88 |
+
| No log | 1.1935 | 74 | 0.9654 | 0.1152 | 0.9654 | 0.9825 |
|
| 89 |
+
| No log | 1.2258 | 76 | 0.8577 | 0.0316 | 0.8577 | 0.9261 |
|
| 90 |
+
| No log | 1.2581 | 78 | 0.7811 | 0.2430 | 0.7811 | 0.8838 |
|
| 91 |
+
| No log | 1.2903 | 80 | 1.0103 | 0.1808 | 1.0103 | 1.0051 |
|
| 92 |
+
| No log | 1.3226 | 82 | 0.9614 | 0.1243 | 0.9614 | 0.9805 |
|
| 93 |
+
| No log | 1.3548 | 84 | 1.1169 | 0.0710 | 1.1169 | 1.0569 |
|
| 94 |
+
| No log | 1.3871 | 86 | 1.3591 | 0.1200 | 1.3591 | 1.1658 |
|
| 95 |
+
| No log | 1.4194 | 88 | 0.9923 | 0.1813 | 0.9923 | 0.9961 |
|
| 96 |
+
| No log | 1.4516 | 90 | 0.9271 | 0.2296 | 0.9271 | 0.9628 |
|
| 97 |
+
| No log | 1.4839 | 92 | 0.9525 | 0.0945 | 0.9525 | 0.9760 |
|
| 98 |
+
| No log | 1.5161 | 94 | 0.7841 | 0.2424 | 0.7841 | 0.8855 |
|
| 99 |
+
| No log | 1.5484 | 96 | 0.7266 | 0.2096 | 0.7266 | 0.8524 |
|
| 100 |
+
| No log | 1.5806 | 98 | 0.7771 | 0.1986 | 0.7771 | 0.8815 |
|
| 101 |
+
| No log | 1.6129 | 100 | 0.7281 | 0.2096 | 0.7281 | 0.8533 |
|
| 102 |
+
| No log | 1.6452 | 102 | 0.7512 | 0.1630 | 0.7512 | 0.8667 |
|
| 103 |
+
| No log | 1.6774 | 104 | 0.8112 | 0.2096 | 0.8112 | 0.9006 |
|
| 104 |
+
| No log | 1.7097 | 106 | 0.8456 | 0.2294 | 0.8456 | 0.9196 |
|
| 105 |
+
| No log | 1.7419 | 108 | 0.9786 | 0.0970 | 0.9786 | 0.9892 |
|
| 106 |
+
| No log | 1.7742 | 110 | 0.9895 | 0.0970 | 0.9895 | 0.9947 |
|
| 107 |
+
| No log | 1.8065 | 112 | 0.8950 | 0.1626 | 0.8950 | 0.9461 |
|
| 108 |
+
| No log | 1.8387 | 114 | 0.8938 | 0.0762 | 0.8938 | 0.9454 |
|
| 109 |
+
| No log | 1.8710 | 116 | 0.8430 | 0.1001 | 0.8430 | 0.9181 |
|
| 110 |
+
| No log | 1.9032 | 118 | 0.8598 | 0.0962 | 0.8598 | 0.9272 |
|
| 111 |
+
| No log | 1.9355 | 120 | 0.9304 | 0.0665 | 0.9304 | 0.9646 |
|
| 112 |
+
| No log | 1.9677 | 122 | 0.8174 | 0.1365 | 0.8174 | 0.9041 |
|
| 113 |
+
| No log | 2.0 | 124 | 0.8222 | 0.1783 | 0.8222 | 0.9068 |
|
| 114 |
+
| No log | 2.0323 | 126 | 0.7878 | 0.1585 | 0.7878 | 0.8876 |
|
| 115 |
+
| No log | 2.0645 | 128 | 0.9271 | 0.1005 | 0.9271 | 0.9629 |
|
| 116 |
+
| No log | 2.0968 | 130 | 0.9613 | 0.0701 | 0.9613 | 0.9805 |
|
| 117 |
+
| No log | 2.1290 | 132 | 0.8387 | 0.2012 | 0.8387 | 0.9158 |
|
| 118 |
+
| No log | 2.1613 | 134 | 0.8165 | 0.2430 | 0.8165 | 0.9036 |
|
| 119 |
+
| No log | 2.1935 | 136 | 0.7851 | 0.2969 | 0.7851 | 0.8861 |
|
| 120 |
+
| No log | 2.2258 | 138 | 0.7628 | 0.2194 | 0.7628 | 0.8734 |
|
| 121 |
+
| No log | 2.2581 | 140 | 0.7633 | 0.2239 | 0.7633 | 0.8737 |
|
| 122 |
+
| No log | 2.2903 | 142 | 0.8056 | 0.1407 | 0.8056 | 0.8975 |
|
| 123 |
+
| No log | 2.3226 | 144 | 0.8328 | 0.1790 | 0.8328 | 0.9126 |
|
| 124 |
+
| No log | 2.3548 | 146 | 0.8346 | 0.2608 | 0.8346 | 0.9135 |
|
| 125 |
+
| No log | 2.3871 | 148 | 0.8497 | 0.2126 | 0.8497 | 0.9218 |
|
| 126 |
+
| No log | 2.4194 | 150 | 0.8475 | 0.2236 | 0.8475 | 0.9206 |
|
| 127 |
+
| No log | 2.4516 | 152 | 0.7638 | 0.1415 | 0.7638 | 0.8740 |
|
| 128 |
+
| No log | 2.4839 | 154 | 0.8483 | 0.1571 | 0.8483 | 0.9210 |
|
| 129 |
+
| No log | 2.5161 | 156 | 0.7486 | 0.1541 | 0.7486 | 0.8652 |
|
| 130 |
+
| No log | 2.5484 | 158 | 0.8151 | -0.0138 | 0.8151 | 0.9028 |
|
| 131 |
+
| No log | 2.5806 | 160 | 0.8845 | 0.1078 | 0.8845 | 0.9405 |
|
| 132 |
+
| No log | 2.6129 | 162 | 0.7356 | -0.0513 | 0.7356 | 0.8577 |
|
| 133 |
+
| No log | 2.6452 | 164 | 0.7405 | 0.2009 | 0.7405 | 0.8605 |
|
| 134 |
+
| No log | 2.6774 | 166 | 0.8455 | 0.2220 | 0.8455 | 0.9195 |
|
| 135 |
+
| No log | 2.7097 | 168 | 0.7799 | 0.1144 | 0.7799 | 0.8831 |
|
| 136 |
+
| No log | 2.7419 | 170 | 0.8559 | -0.0522 | 0.8559 | 0.9251 |
|
| 137 |
+
| No log | 2.7742 | 172 | 0.7750 | 0.1413 | 0.7750 | 0.8803 |
|
| 138 |
+
| No log | 2.8065 | 174 | 0.8161 | 0.1742 | 0.8161 | 0.9034 |
|
| 139 |
+
| No log | 2.8387 | 176 | 0.7715 | 0.1783 | 0.7715 | 0.8784 |
|
| 140 |
+
| No log | 2.8710 | 178 | 0.7288 | 0.1371 | 0.7288 | 0.8537 |
|
| 141 |
+
| No log | 2.9032 | 180 | 0.8175 | 0.0570 | 0.8175 | 0.9042 |
|
| 142 |
+
| No log | 2.9355 | 182 | 0.7847 | 0.1962 | 0.7847 | 0.8858 |
|
| 143 |
+
| No log | 2.9677 | 184 | 0.8227 | 0.1783 | 0.8227 | 0.9071 |
|
| 144 |
+
| No log | 3.0 | 186 | 0.8246 | 0.1846 | 0.8246 | 0.9081 |
|
| 145 |
+
| No log | 3.0323 | 188 | 0.9158 | 0.1220 | 0.9158 | 0.9570 |
|
| 146 |
+
| No log | 3.0645 | 190 | 0.8598 | 0.1553 | 0.8598 | 0.9273 |
|
| 147 |
+
| No log | 3.0968 | 192 | 0.7945 | 0.2118 | 0.7945 | 0.8914 |
|
| 148 |
+
| No log | 3.1290 | 194 | 0.7582 | 0.1347 | 0.7582 | 0.8708 |
|
| 149 |
+
| No log | 3.1613 | 196 | 0.7579 | 0.1362 | 0.7579 | 0.8706 |
|
| 150 |
+
| No log | 3.1935 | 198 | 0.8205 | 0.1372 | 0.8205 | 0.9058 |
|
| 151 |
+
| No log | 3.2258 | 200 | 0.8156 | 0.0660 | 0.8156 | 0.9031 |
|
| 152 |
+
| No log | 3.2581 | 202 | 0.7675 | 0.0828 | 0.7675 | 0.8760 |
|
| 153 |
+
| No log | 3.2903 | 204 | 0.7769 | 0.0056 | 0.7769 | 0.8814 |
|
| 154 |
+
| No log | 3.3226 | 206 | 0.7615 | 0.0874 | 0.7615 | 0.8726 |
|
| 155 |
+
| No log | 3.3548 | 208 | 0.7828 | 0.0056 | 0.7828 | 0.8847 |
|
| 156 |
+
| No log | 3.3871 | 210 | 0.7958 | 0.0532 | 0.7958 | 0.8921 |
|
| 157 |
+
| No log | 3.4194 | 212 | 0.7775 | 0.2239 | 0.7775 | 0.8817 |
|
| 158 |
+
| No log | 3.4516 | 214 | 0.7869 | 0.0981 | 0.7869 | 0.8871 |
|
| 159 |
+
| No log | 3.4839 | 216 | 0.9070 | 0.1039 | 0.9070 | 0.9523 |
|
| 160 |
+
| No log | 3.5161 | 218 | 0.9201 | 0.1040 | 0.9201 | 0.9592 |
|
| 161 |
+
| No log | 3.5484 | 220 | 0.7736 | 0.0981 | 0.7736 | 0.8795 |
|
| 162 |
+
| No log | 3.5806 | 222 | 0.7847 | 0.1599 | 0.7847 | 0.8858 |
|
| 163 |
+
| No log | 3.6129 | 224 | 0.7827 | 0.2627 | 0.7827 | 0.8847 |
|
| 164 |
+
| No log | 3.6452 | 226 | 0.7952 | 0.1372 | 0.7952 | 0.8917 |
|
| 165 |
+
| No log | 3.6774 | 228 | 0.7674 | 0.2437 | 0.7674 | 0.8760 |
|
| 166 |
+
| No log | 3.7097 | 230 | 0.7586 | 0.2667 | 0.7586 | 0.8710 |
|
| 167 |
+
| No log | 3.7419 | 232 | 0.7943 | 0.0987 | 0.7943 | 0.8912 |
|
| 168 |
+
| No log | 3.7742 | 234 | 0.7502 | 0.2252 | 0.7502 | 0.8661 |
|
| 169 |
+
| No log | 3.8065 | 236 | 0.8566 | 0.1185 | 0.8566 | 0.9255 |
|
| 170 |
+
| No log | 3.8387 | 238 | 0.9319 | 0.0273 | 0.9319 | 0.9653 |
|
| 171 |
+
| No log | 3.8710 | 240 | 0.8168 | 0.1884 | 0.8168 | 0.9038 |
|
| 172 |
+
| No log | 3.9032 | 242 | 1.2060 | 0.1281 | 1.2060 | 1.0982 |
|
| 173 |
+
| No log | 3.9355 | 244 | 1.3356 | 0.1275 | 1.3356 | 1.1557 |
|
| 174 |
+
| No log | 3.9677 | 246 | 0.9845 | 0.1185 | 0.9845 | 0.9922 |
|
| 175 |
+
| No log | 4.0 | 248 | 0.9554 | 0.0960 | 0.9554 | 0.9775 |
|
| 176 |
+
| No log | 4.0323 | 250 | 0.9983 | 0.0575 | 0.9983 | 0.9992 |
|
| 177 |
+
| No log | 4.0645 | 252 | 0.8399 | 0.2247 | 0.8399 | 0.9165 |
|
| 178 |
+
| No log | 4.0968 | 254 | 0.8199 | 0.2132 | 0.8199 | 0.9055 |
|
| 179 |
+
| No log | 4.1290 | 256 | 0.7460 | 0.0874 | 0.7460 | 0.8637 |
|
| 180 |
+
| No log | 4.1613 | 258 | 0.7476 | 0.1964 | 0.7476 | 0.8647 |
|
| 181 |
+
| No log | 4.1935 | 260 | 0.7350 | 0.1244 | 0.7350 | 0.8573 |
|
| 182 |
+
| No log | 4.2258 | 262 | 0.7359 | 0.1244 | 0.7359 | 0.8578 |
|
| 183 |
+
| No log | 4.2581 | 264 | 0.7725 | 0.2085 | 0.7725 | 0.8789 |
|
| 184 |
+
| No log | 4.2903 | 266 | 0.8436 | 0.1598 | 0.8436 | 0.9185 |
|
| 185 |
+
| No log | 4.3226 | 268 | 0.8621 | 0.1918 | 0.8621 | 0.9285 |
|
| 186 |
+
| No log | 4.3548 | 270 | 0.8040 | 0.2063 | 0.8040 | 0.8967 |
|
| 187 |
+
| No log | 4.3871 | 272 | 0.8142 | 0.0532 | 0.8142 | 0.9024 |
|
| 188 |
+
| No log | 4.4194 | 274 | 0.7816 | 0.0532 | 0.7816 | 0.8841 |
|
| 189 |
+
| No log | 4.4516 | 276 | 0.7088 | 0.0436 | 0.7088 | 0.8419 |
|
| 190 |
+
| No log | 4.4839 | 278 | 0.7426 | 0.2258 | 0.7426 | 0.8618 |
|
| 191 |
+
| No log | 4.5161 | 280 | 0.7723 | 0.2669 | 0.7723 | 0.8788 |
|
| 192 |
+
| No log | 4.5484 | 282 | 0.7843 | 0.0926 | 0.7843 | 0.8856 |
|
| 193 |
+
| No log | 4.5806 | 284 | 0.8105 | 0.0934 | 0.8105 | 0.9003 |
|
| 194 |
+
| No log | 4.6129 | 286 | 0.8747 | 0.1504 | 0.8747 | 0.9352 |
|
| 195 |
+
| No log | 4.6452 | 288 | 1.0096 | 0.1930 | 1.0096 | 1.0048 |
|
| 196 |
+
| No log | 4.6774 | 290 | 0.9898 | 0.0824 | 0.9898 | 0.9949 |
|
| 197 |
+
| No log | 4.7097 | 292 | 0.7865 | 0.2122 | 0.7865 | 0.8869 |
|
| 198 |
+
| No log | 4.7419 | 294 | 0.8019 | 0.0532 | 0.8019 | 0.8955 |
|
| 199 |
+
| No log | 4.7742 | 296 | 0.8083 | 0.0106 | 0.8083 | 0.8991 |
|
| 200 |
+
| No log | 4.8065 | 298 | 0.7572 | -0.0030 | 0.7572 | 0.8702 |
|
| 201 |
+
| No log | 4.8387 | 300 | 0.9058 | 0.1744 | 0.9058 | 0.9517 |
|
| 202 |
+
| No log | 4.8710 | 302 | 1.0732 | 0.0451 | 1.0732 | 1.0359 |
|
| 203 |
+
| No log | 4.9032 | 304 | 0.9476 | 0.1219 | 0.9476 | 0.9735 |
|
| 204 |
+
| No log | 4.9355 | 306 | 0.8287 | 0.1272 | 0.8287 | 0.9104 |
|
| 205 |
+
| No log | 4.9677 | 308 | 0.8994 | 0.0007 | 0.8994 | 0.9484 |
|
| 206 |
+
| No log | 5.0 | 310 | 0.8136 | 0.0129 | 0.8136 | 0.9020 |
|
| 207 |
+
| No log | 5.0323 | 312 | 0.7679 | 0.1807 | 0.7679 | 0.8763 |
|
| 208 |
+
| No log | 5.0645 | 314 | 0.8893 | 0.1696 | 0.8893 | 0.9430 |
|
| 209 |
+
| No log | 5.0968 | 316 | 0.9318 | 0.0824 | 0.9318 | 0.9653 |
|
| 210 |
+
| No log | 5.1290 | 318 | 0.7946 | 0.1612 | 0.7946 | 0.8914 |
|
| 211 |
+
| No log | 5.1613 | 320 | 0.8447 | -0.0180 | 0.8447 | 0.9191 |
|
| 212 |
+
| No log | 5.1935 | 322 | 0.9089 | -0.0035 | 0.9089 | 0.9534 |
|
| 213 |
+
| No log | 5.2258 | 324 | 0.7972 | 0.0981 | 0.7972 | 0.8929 |
|
| 214 |
+
| No log | 5.2581 | 326 | 0.7720 | 0.2225 | 0.7720 | 0.8786 |
|
| 215 |
+
| No log | 5.2903 | 328 | 0.8202 | 0.2155 | 0.8202 | 0.9056 |
|
| 216 |
+
| No log | 5.3226 | 330 | 0.7672 | 0.2626 | 0.7672 | 0.8759 |
|
| 217 |
+
| No log | 5.3548 | 332 | 0.7795 | 0.2795 | 0.7795 | 0.8829 |
|
| 218 |
+
| No log | 5.3871 | 334 | 0.7672 | 0.1585 | 0.7672 | 0.8759 |
|
| 219 |
+
| No log | 5.4194 | 336 | 0.8181 | 0.2032 | 0.8181 | 0.9045 |
|
| 220 |
+
| No log | 5.4516 | 338 | 0.8055 | 0.1621 | 0.8055 | 0.8975 |
|
| 221 |
+
| No log | 5.4839 | 340 | 0.7352 | 0.1371 | 0.7352 | 0.8574 |
|
| 222 |
+
| No log | 5.5161 | 342 | 0.7227 | 0.0914 | 0.7227 | 0.8501 |
|
| 223 |
+
| No log | 5.5484 | 344 | 0.7164 | 0.0914 | 0.7164 | 0.8464 |
|
| 224 |
+
| No log | 5.5806 | 346 | 0.7299 | 0.2339 | 0.7299 | 0.8544 |
|
| 225 |
+
| No log | 5.6129 | 348 | 0.9371 | 0.0856 | 0.9371 | 0.9680 |
|
| 226 |
+
| No log | 5.6452 | 350 | 1.1105 | 0.0894 | 1.1105 | 1.0538 |
|
| 227 |
+
| No log | 5.6774 | 352 | 0.9536 | 0.1219 | 0.9536 | 0.9765 |
|
| 228 |
+
| No log | 5.7097 | 354 | 0.8283 | 0.2815 | 0.8283 | 0.9101 |
|
| 229 |
+
| No log | 5.7419 | 356 | 0.8105 | 0.2481 | 0.8105 | 0.9003 |
|
| 230 |
+
| No log | 5.7742 | 358 | 0.7656 | 0.1882 | 0.7656 | 0.8750 |
|
| 231 |
+
| No log | 5.8065 | 360 | 0.7339 | 0.1311 | 0.7339 | 0.8567 |
|
| 232 |
+
| No log | 5.8387 | 362 | 0.7662 | 0.2318 | 0.7662 | 0.8753 |
|
| 233 |
+
| No log | 5.8710 | 364 | 0.7380 | 0.2180 | 0.7380 | 0.8591 |
|
| 234 |
+
| No log | 5.9032 | 366 | 0.7578 | 0.1413 | 0.7578 | 0.8705 |
|
| 235 |
+
| No log | 5.9355 | 368 | 0.9521 | 0.0329 | 0.9521 | 0.9758 |
|
| 236 |
+
| No log | 5.9677 | 370 | 1.0110 | 0.1284 | 1.0110 | 1.0055 |
|
| 237 |
+
| No log | 6.0 | 372 | 0.8641 | 0.1695 | 0.8641 | 0.9296 |
|
| 238 |
+
| No log | 6.0323 | 374 | 0.8252 | 0.2204 | 0.8252 | 0.9084 |
|
| 239 |
+
| No log | 6.0645 | 376 | 0.9119 | 0.1542 | 0.9119 | 0.9549 |
|
| 240 |
+
| No log | 6.0968 | 378 | 0.8740 | 0.1584 | 0.8740 | 0.9349 |
|
| 241 |
+
| No log | 6.1290 | 380 | 0.7588 | 0.2169 | 0.7588 | 0.8711 |
|
| 242 |
+
| No log | 6.1613 | 382 | 0.7702 | 0.0449 | 0.7702 | 0.8776 |
|
| 243 |
+
| No log | 6.1935 | 384 | 0.7704 | 0.0449 | 0.7704 | 0.8777 |
|
| 244 |
+
| No log | 6.2258 | 386 | 0.7447 | 0.0914 | 0.7447 | 0.8630 |
|
| 245 |
+
| No log | 6.2581 | 388 | 0.7919 | 0.1660 | 0.7919 | 0.8899 |
|
| 246 |
+
| No log | 6.2903 | 390 | 0.8998 | 0.1584 | 0.8998 | 0.9486 |
|
| 247 |
+
| No log | 6.3226 | 392 | 0.9038 | 0.1368 | 0.9038 | 0.9507 |
|
| 248 |
+
| No log | 6.3548 | 394 | 0.8881 | 0.0826 | 0.8881 | 0.9424 |
|
| 249 |
+
| No log | 6.3871 | 396 | 0.8942 | 0.1140 | 0.8942 | 0.9456 |
|
| 250 |
+
| No log | 6.4194 | 398 | 0.8718 | 0.1140 | 0.8718 | 0.9337 |
|
| 251 |
+
| No log | 6.4516 | 400 | 0.8212 | 0.1673 | 0.8212 | 0.9062 |
|
| 252 |
+
| No log | 6.4839 | 402 | 0.7741 | 0.1292 | 0.7741 | 0.8798 |
|
| 253 |
+
| No log | 6.5161 | 404 | 0.7574 | 0.1371 | 0.7574 | 0.8703 |
|
| 254 |
+
| No log | 6.5484 | 406 | 0.7723 | 0.2431 | 0.7723 | 0.8788 |
|
| 255 |
+
| No log | 6.5806 | 408 | 0.8141 | 0.1742 | 0.8141 | 0.9023 |
|
| 256 |
+
| No log | 6.6129 | 410 | 0.8369 | 0.1318 | 0.8369 | 0.9148 |
|
| 257 |
+
| No log | 6.6452 | 412 | 0.8413 | 0.1187 | 0.8413 | 0.9172 |
|
| 258 |
+
| No log | 6.6774 | 414 | 0.8581 | 0.0717 | 0.8581 | 0.9263 |
|
| 259 |
+
| No log | 6.7097 | 416 | 0.8995 | 0.1102 | 0.8995 | 0.9484 |
|
| 260 |
+
| No log | 6.7419 | 418 | 0.8985 | 0.1514 | 0.8985 | 0.9479 |
|
| 261 |
+
| No log | 6.7742 | 420 | 0.9081 | 0.1017 | 0.9081 | 0.9529 |
|
| 262 |
+
| No log | 6.8065 | 422 | 0.8748 | 0.1140 | 0.8748 | 0.9353 |
|
| 263 |
+
| No log | 6.8387 | 424 | 0.8469 | 0.1183 | 0.8469 | 0.9203 |
|
| 264 |
+
| No log | 6.8710 | 426 | 0.8312 | 0.1387 | 0.8312 | 0.9117 |
|
| 265 |
+
| No log | 6.9032 | 428 | 0.7658 | 0.1828 | 0.7658 | 0.8751 |
|
| 266 |
+
| No log | 6.9355 | 430 | 0.7107 | 0.1444 | 0.7107 | 0.8430 |
|
| 267 |
+
| No log | 6.9677 | 432 | 0.7179 | 0.0918 | 0.7179 | 0.8473 |
|
| 268 |
+
| No log | 7.0 | 434 | 0.7438 | 0.0869 | 0.7438 | 0.8624 |
|
| 269 |
+
| No log | 7.0323 | 436 | 0.7975 | 0.2150 | 0.7975 | 0.8930 |
|
| 270 |
+
| No log | 7.0645 | 438 | 0.9505 | 0.1222 | 0.9505 | 0.9749 |
|
| 271 |
+
| No log | 7.0968 | 440 | 0.9813 | 0.1146 | 0.9813 | 0.9906 |
|
| 272 |
+
| No log | 7.1290 | 442 | 1.1224 | -0.0252 | 1.1224 | 1.0594 |
|
| 273 |
+
| No log | 7.1613 | 444 | 1.1595 | -0.0857 | 1.1595 | 1.0768 |
|
| 274 |
+
| No log | 7.1935 | 446 | 0.9901 | 0.1146 | 0.9901 | 0.9950 |
|
| 275 |
+
| No log | 7.2258 | 448 | 0.8142 | 0.1659 | 0.8142 | 0.9023 |
|
| 276 |
+
| No log | 7.2581 | 450 | 0.7875 | 0.0869 | 0.7875 | 0.8874 |
|
| 277 |
+
| No log | 7.2903 | 452 | 0.7810 | 0.1379 | 0.7810 | 0.8837 |
|
| 278 |
+
| No log | 7.3226 | 454 | 0.7919 | 0.1828 | 0.7919 | 0.8899 |
|
| 279 |
+
| No log | 7.3548 | 456 | 0.7658 | 0.1379 | 0.7658 | 0.8751 |
|
| 280 |
+
| No log | 7.3871 | 458 | 0.7949 | 0.2258 | 0.7949 | 0.8916 |
|
| 281 |
+
| No log | 7.4194 | 460 | 0.8576 | 0.0871 | 0.8576 | 0.9261 |
|
| 282 |
+
| No log | 7.4516 | 462 | 0.8426 | 0.2318 | 0.8426 | 0.9179 |
|
| 283 |
+
| No log | 7.4839 | 464 | 0.8585 | 0.1379 | 0.8585 | 0.9266 |
|
| 284 |
+
| No log | 7.5161 | 466 | 0.8563 | 0.1823 | 0.8563 | 0.9254 |
|
| 285 |
+
| No log | 7.5484 | 468 | 0.8621 | 0.0460 | 0.8621 | 0.9285 |
|
| 286 |
+
| No log | 7.5806 | 470 | 0.8727 | 0.0784 | 0.8727 | 0.9342 |
|
| 287 |
+
| No log | 7.6129 | 472 | 0.8622 | 0.0078 | 0.8622 | 0.9286 |
|
| 288 |
+
| No log | 7.6452 | 474 | 0.8242 | 0.1630 | 0.8242 | 0.9079 |
|
| 289 |
+
| No log | 7.6774 | 476 | 0.8638 | 0.1430 | 0.8638 | 0.9294 |
|
| 290 |
+
| No log | 7.7097 | 478 | 0.8305 | 0.2092 | 0.8305 | 0.9113 |
|
| 291 |
+
| No log | 7.7419 | 480 | 0.7793 | 0.0922 | 0.7793 | 0.8828 |
|
| 292 |
+
| No log | 7.7742 | 482 | 0.8881 | 0.0680 | 0.8881 | 0.9424 |
|
| 293 |
+
| No log | 7.8065 | 484 | 0.9052 | 0.0977 | 0.9052 | 0.9514 |
|
| 294 |
+
| No log | 7.8387 | 486 | 0.8314 | 0.0101 | 0.8314 | 0.9118 |
|
| 295 |
+
| No log | 7.8710 | 488 | 0.8553 | 0.1621 | 0.8553 | 0.9249 |
|
| 296 |
+
| No log | 7.9032 | 490 | 0.8642 | 0.1621 | 0.8642 | 0.9296 |
|
| 297 |
+
| No log | 7.9355 | 492 | 0.8258 | 0.1713 | 0.8258 | 0.9087 |
|
| 298 |
+
| No log | 7.9677 | 494 | 0.8041 | 0.1901 | 0.8041 | 0.8967 |
|
| 299 |
+
| No log | 8.0 | 496 | 0.7837 | 0.1143 | 0.7837 | 0.8853 |
|
| 300 |
+
| No log | 8.0323 | 498 | 0.7728 | 0.1143 | 0.7728 | 0.8791 |
|
| 301 |
+
| 0.2861 | 8.0645 | 500 | 0.7940 | 0.1859 | 0.7940 | 0.8911 |
|
| 302 |
+
| 0.2861 | 8.0968 | 502 | 0.7893 | 0.1859 | 0.7893 | 0.8884 |
|
| 303 |
+
| 0.2861 | 8.1290 | 504 | 0.7412 | 0.1828 | 0.7412 | 0.8609 |
|
| 304 |
+
| 0.2861 | 8.1613 | 506 | 0.7090 | 0.1444 | 0.7090 | 0.8420 |
|
| 305 |
+
| 0.2861 | 8.1935 | 508 | 0.6983 | 0.1444 | 0.6983 | 0.8357 |
|
| 306 |
+
| 0.2861 | 8.2258 | 510 | 0.6965 | 0.1379 | 0.6965 | 0.8346 |
|
| 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:bf412ed2b4679baa73d34a41c6f5df11b6976969cc4d7fb58a752c08fe59b2c9
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1e1056dd9e39b9b853e25b183d33e78e6eaec33f5fbd7654756c8c9e8778ed9
|
| 3 |
+
size 5304
|