Training in progress, step 500
Browse files- README.md +324 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_usingALLEssays_FineTuningAraBERT_run1_AugV5_k4_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_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k4_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: 0.7130
|
| 19 |
+
- Qwk: 0.5505
|
| 20 |
+
- Mse: 0.7130
|
| 21 |
+
- Rmse: 0.8444
|
| 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 | 0.0952 | 2 | 4.0267 | 0.0078 | 4.0267 | 2.0067 |
|
| 53 |
+
| No log | 0.1905 | 4 | 2.0978 | -0.0030 | 2.0978 | 1.4484 |
|
| 54 |
+
| No log | 0.2857 | 6 | 1.3501 | 0.0349 | 1.3501 | 1.1619 |
|
| 55 |
+
| No log | 0.3810 | 8 | 1.2569 | 0.0790 | 1.2569 | 1.1211 |
|
| 56 |
+
| No log | 0.4762 | 10 | 1.0889 | 0.2015 | 1.0889 | 1.0435 |
|
| 57 |
+
| No log | 0.5714 | 12 | 1.0846 | 0.1989 | 1.0846 | 1.0414 |
|
| 58 |
+
| No log | 0.6667 | 14 | 1.1857 | 0.1333 | 1.1857 | 1.0889 |
|
| 59 |
+
| No log | 0.7619 | 16 | 1.2821 | 0.1057 | 1.2821 | 1.1323 |
|
| 60 |
+
| No log | 0.8571 | 18 | 1.2583 | 0.1433 | 1.2583 | 1.1217 |
|
| 61 |
+
| No log | 0.9524 | 20 | 1.3290 | 0.1460 | 1.3290 | 1.1528 |
|
| 62 |
+
| No log | 1.0476 | 22 | 1.1406 | 0.1296 | 1.1406 | 1.0680 |
|
| 63 |
+
| No log | 1.1429 | 24 | 1.0540 | 0.2424 | 1.0540 | 1.0267 |
|
| 64 |
+
| No log | 1.2381 | 26 | 1.1236 | 0.2238 | 1.1236 | 1.0600 |
|
| 65 |
+
| No log | 1.3333 | 28 | 0.9990 | 0.4208 | 0.9990 | 0.9995 |
|
| 66 |
+
| No log | 1.4286 | 30 | 0.9167 | 0.4399 | 0.9167 | 0.9574 |
|
| 67 |
+
| No log | 1.5238 | 32 | 0.8661 | 0.4592 | 0.8661 | 0.9306 |
|
| 68 |
+
| No log | 1.6190 | 34 | 0.9252 | 0.4246 | 0.9252 | 0.9619 |
|
| 69 |
+
| No log | 1.7143 | 36 | 0.9182 | 0.4558 | 0.9182 | 0.9582 |
|
| 70 |
+
| No log | 1.8095 | 38 | 0.8738 | 0.5302 | 0.8738 | 0.9348 |
|
| 71 |
+
| No log | 1.9048 | 40 | 0.9116 | 0.4760 | 0.9116 | 0.9548 |
|
| 72 |
+
| No log | 2.0 | 42 | 0.9076 | 0.4539 | 0.9076 | 0.9527 |
|
| 73 |
+
| No log | 2.0952 | 44 | 0.9324 | 0.4439 | 0.9324 | 0.9656 |
|
| 74 |
+
| No log | 2.1905 | 46 | 0.8444 | 0.4662 | 0.8444 | 0.9189 |
|
| 75 |
+
| No log | 2.2857 | 48 | 0.9077 | 0.3929 | 0.9077 | 0.9527 |
|
| 76 |
+
| No log | 2.3810 | 50 | 0.8092 | 0.5359 | 0.8092 | 0.8996 |
|
| 77 |
+
| No log | 2.4762 | 52 | 0.8925 | 0.3478 | 0.8925 | 0.9447 |
|
| 78 |
+
| No log | 2.5714 | 54 | 0.9351 | 0.3545 | 0.9351 | 0.9670 |
|
| 79 |
+
| No log | 2.6667 | 56 | 0.7657 | 0.5529 | 0.7657 | 0.8750 |
|
| 80 |
+
| No log | 2.7619 | 58 | 0.7441 | 0.5590 | 0.7441 | 0.8626 |
|
| 81 |
+
| No log | 2.8571 | 60 | 0.7656 | 0.5626 | 0.7656 | 0.8750 |
|
| 82 |
+
| No log | 2.9524 | 62 | 0.9405 | 0.5054 | 0.9405 | 0.9698 |
|
| 83 |
+
| No log | 3.0476 | 64 | 1.3257 | 0.3496 | 1.3257 | 1.1514 |
|
| 84 |
+
| No log | 3.1429 | 66 | 1.1137 | 0.3772 | 1.1137 | 1.0553 |
|
| 85 |
+
| No log | 3.2381 | 68 | 0.7586 | 0.5351 | 0.7586 | 0.8710 |
|
| 86 |
+
| No log | 3.3333 | 70 | 0.7346 | 0.5009 | 0.7346 | 0.8571 |
|
| 87 |
+
| No log | 3.4286 | 72 | 0.8530 | 0.4739 | 0.8530 | 0.9236 |
|
| 88 |
+
| No log | 3.5238 | 74 | 0.8153 | 0.5873 | 0.8153 | 0.9029 |
|
| 89 |
+
| No log | 3.6190 | 76 | 0.7304 | 0.5819 | 0.7304 | 0.8547 |
|
| 90 |
+
| No log | 3.7143 | 78 | 0.7392 | 0.5702 | 0.7392 | 0.8597 |
|
| 91 |
+
| No log | 3.8095 | 80 | 0.7475 | 0.5935 | 0.7475 | 0.8646 |
|
| 92 |
+
| No log | 3.9048 | 82 | 0.7442 | 0.5742 | 0.7442 | 0.8627 |
|
| 93 |
+
| No log | 4.0 | 84 | 0.7386 | 0.5352 | 0.7386 | 0.8594 |
|
| 94 |
+
| No log | 4.0952 | 86 | 0.7386 | 0.5587 | 0.7386 | 0.8594 |
|
| 95 |
+
| No log | 4.1905 | 88 | 0.7484 | 0.5934 | 0.7484 | 0.8651 |
|
| 96 |
+
| No log | 4.2857 | 90 | 0.7790 | 0.4998 | 0.7790 | 0.8826 |
|
| 97 |
+
| No log | 4.3810 | 92 | 0.7670 | 0.5678 | 0.7670 | 0.8758 |
|
| 98 |
+
| No log | 4.4762 | 94 | 0.7637 | 0.5853 | 0.7637 | 0.8739 |
|
| 99 |
+
| No log | 4.5714 | 96 | 0.7733 | 0.5534 | 0.7733 | 0.8794 |
|
| 100 |
+
| No log | 4.6667 | 98 | 0.7529 | 0.5483 | 0.7529 | 0.8677 |
|
| 101 |
+
| No log | 4.7619 | 100 | 0.9154 | 0.4738 | 0.9154 | 0.9568 |
|
| 102 |
+
| No log | 4.8571 | 102 | 0.8939 | 0.4835 | 0.8939 | 0.9455 |
|
| 103 |
+
| No log | 4.9524 | 104 | 0.7684 | 0.5133 | 0.7684 | 0.8766 |
|
| 104 |
+
| No log | 5.0476 | 106 | 0.8121 | 0.6018 | 0.8121 | 0.9012 |
|
| 105 |
+
| No log | 5.1429 | 108 | 0.7744 | 0.5402 | 0.7744 | 0.8800 |
|
| 106 |
+
| No log | 5.2381 | 110 | 0.7799 | 0.5074 | 0.7799 | 0.8831 |
|
| 107 |
+
| No log | 5.3333 | 112 | 0.7602 | 0.6085 | 0.7602 | 0.8719 |
|
| 108 |
+
| No log | 5.4286 | 114 | 0.7499 | 0.5731 | 0.7499 | 0.8659 |
|
| 109 |
+
| No log | 5.5238 | 116 | 0.7768 | 0.5641 | 0.7768 | 0.8813 |
|
| 110 |
+
| No log | 5.6190 | 118 | 0.9592 | 0.4752 | 0.9592 | 0.9794 |
|
| 111 |
+
| No log | 5.7143 | 120 | 0.8738 | 0.4376 | 0.8738 | 0.9348 |
|
| 112 |
+
| No log | 5.8095 | 122 | 0.7486 | 0.5599 | 0.7486 | 0.8652 |
|
| 113 |
+
| No log | 5.9048 | 124 | 0.7571 | 0.5607 | 0.7571 | 0.8701 |
|
| 114 |
+
| No log | 6.0 | 126 | 0.7567 | 0.5287 | 0.7567 | 0.8699 |
|
| 115 |
+
| No log | 6.0952 | 128 | 0.8758 | 0.5440 | 0.8758 | 0.9358 |
|
| 116 |
+
| No log | 6.1905 | 130 | 0.9048 | 0.5047 | 0.9048 | 0.9512 |
|
| 117 |
+
| No log | 6.2857 | 132 | 0.8507 | 0.5011 | 0.8507 | 0.9223 |
|
| 118 |
+
| No log | 6.3810 | 134 | 0.7867 | 0.5524 | 0.7867 | 0.8869 |
|
| 119 |
+
| No log | 6.4762 | 136 | 0.8283 | 0.5207 | 0.8283 | 0.9101 |
|
| 120 |
+
| No log | 6.5714 | 138 | 0.8265 | 0.5312 | 0.8265 | 0.9091 |
|
| 121 |
+
| No log | 6.6667 | 140 | 0.8416 | 0.5312 | 0.8416 | 0.9174 |
|
| 122 |
+
| No log | 6.7619 | 142 | 0.7569 | 0.5684 | 0.7569 | 0.8700 |
|
| 123 |
+
| No log | 6.8571 | 144 | 0.8170 | 0.5462 | 0.8170 | 0.9039 |
|
| 124 |
+
| No log | 6.9524 | 146 | 0.8439 | 0.5129 | 0.8439 | 0.9186 |
|
| 125 |
+
| No log | 7.0476 | 148 | 0.7601 | 0.5819 | 0.7601 | 0.8718 |
|
| 126 |
+
| No log | 7.1429 | 150 | 0.7740 | 0.4561 | 0.7740 | 0.8798 |
|
| 127 |
+
| No log | 7.2381 | 152 | 0.8497 | 0.4699 | 0.8497 | 0.9218 |
|
| 128 |
+
| No log | 7.3333 | 154 | 0.7843 | 0.4968 | 0.7843 | 0.8856 |
|
| 129 |
+
| No log | 7.4286 | 156 | 0.7530 | 0.5247 | 0.7530 | 0.8678 |
|
| 130 |
+
| No log | 7.5238 | 158 | 0.8162 | 0.5242 | 0.8162 | 0.9034 |
|
| 131 |
+
| No log | 7.6190 | 160 | 0.7799 | 0.5470 | 0.7799 | 0.8831 |
|
| 132 |
+
| No log | 7.7143 | 162 | 0.7055 | 0.6123 | 0.7055 | 0.8399 |
|
| 133 |
+
| No log | 7.8095 | 164 | 0.7441 | 0.5427 | 0.7441 | 0.8626 |
|
| 134 |
+
| No log | 7.9048 | 166 | 0.8221 | 0.5552 | 0.8221 | 0.9067 |
|
| 135 |
+
| No log | 8.0 | 168 | 0.7779 | 0.5946 | 0.7779 | 0.8820 |
|
| 136 |
+
| No log | 8.0952 | 170 | 0.7225 | 0.6116 | 0.7225 | 0.8500 |
|
| 137 |
+
| No log | 8.1905 | 172 | 0.7756 | 0.5719 | 0.7756 | 0.8807 |
|
| 138 |
+
| No log | 8.2857 | 174 | 0.8409 | 0.5520 | 0.8409 | 0.9170 |
|
| 139 |
+
| No log | 8.3810 | 176 | 0.7566 | 0.5625 | 0.7566 | 0.8698 |
|
| 140 |
+
| No log | 8.4762 | 178 | 0.6983 | 0.5837 | 0.6983 | 0.8357 |
|
| 141 |
+
| No log | 8.5714 | 180 | 0.6824 | 0.6052 | 0.6824 | 0.8261 |
|
| 142 |
+
| No log | 8.6667 | 182 | 0.7605 | 0.5525 | 0.7605 | 0.8721 |
|
| 143 |
+
| No log | 8.7619 | 184 | 0.7430 | 0.5727 | 0.7430 | 0.8620 |
|
| 144 |
+
| No log | 8.8571 | 186 | 0.6804 | 0.5955 | 0.6804 | 0.8249 |
|
| 145 |
+
| No log | 8.9524 | 188 | 0.6640 | 0.6339 | 0.6640 | 0.8149 |
|
| 146 |
+
| No log | 9.0476 | 190 | 0.6677 | 0.6226 | 0.6677 | 0.8171 |
|
| 147 |
+
| No log | 9.1429 | 192 | 0.6516 | 0.6068 | 0.6516 | 0.8072 |
|
| 148 |
+
| No log | 9.2381 | 194 | 0.7191 | 0.5432 | 0.7191 | 0.8480 |
|
| 149 |
+
| No log | 9.3333 | 196 | 0.7502 | 0.5432 | 0.7502 | 0.8661 |
|
| 150 |
+
| No log | 9.4286 | 198 | 0.6731 | 0.5971 | 0.6731 | 0.8204 |
|
| 151 |
+
| No log | 9.5238 | 200 | 0.6815 | 0.5977 | 0.6815 | 0.8255 |
|
| 152 |
+
| No log | 9.6190 | 202 | 0.6877 | 0.5868 | 0.6877 | 0.8293 |
|
| 153 |
+
| No log | 9.7143 | 204 | 0.7070 | 0.5759 | 0.7070 | 0.8408 |
|
| 154 |
+
| No log | 9.8095 | 206 | 0.6975 | 0.5934 | 0.6975 | 0.8352 |
|
| 155 |
+
| No log | 9.9048 | 208 | 0.7131 | 0.6526 | 0.7131 | 0.8444 |
|
| 156 |
+
| No log | 10.0 | 210 | 0.7296 | 0.5797 | 0.7296 | 0.8542 |
|
| 157 |
+
| No log | 10.0952 | 212 | 0.7193 | 0.5797 | 0.7193 | 0.8481 |
|
| 158 |
+
| No log | 10.1905 | 214 | 0.7108 | 0.5726 | 0.7108 | 0.8431 |
|
| 159 |
+
| No log | 10.2857 | 216 | 0.7204 | 0.5530 | 0.7204 | 0.8488 |
|
| 160 |
+
| No log | 10.3810 | 218 | 0.7312 | 0.5514 | 0.7312 | 0.8551 |
|
| 161 |
+
| No log | 10.4762 | 220 | 0.7038 | 0.5994 | 0.7038 | 0.8389 |
|
| 162 |
+
| No log | 10.5714 | 222 | 0.7400 | 0.6133 | 0.7400 | 0.8602 |
|
| 163 |
+
| No log | 10.6667 | 224 | 0.8139 | 0.5211 | 0.8139 | 0.9022 |
|
| 164 |
+
| No log | 10.7619 | 226 | 0.7482 | 0.5697 | 0.7482 | 0.8650 |
|
| 165 |
+
| No log | 10.8571 | 228 | 0.6809 | 0.5315 | 0.6809 | 0.8252 |
|
| 166 |
+
| No log | 10.9524 | 230 | 0.6903 | 0.5548 | 0.6903 | 0.8309 |
|
| 167 |
+
| No log | 11.0476 | 232 | 0.7167 | 0.5759 | 0.7167 | 0.8466 |
|
| 168 |
+
| No log | 11.1429 | 234 | 0.6660 | 0.6042 | 0.6660 | 0.8161 |
|
| 169 |
+
| No log | 11.2381 | 236 | 0.6593 | 0.6225 | 0.6593 | 0.8120 |
|
| 170 |
+
| No log | 11.3333 | 238 | 0.6577 | 0.6359 | 0.6577 | 0.8110 |
|
| 171 |
+
| No log | 11.4286 | 240 | 0.6650 | 0.6263 | 0.6650 | 0.8155 |
|
| 172 |
+
| No log | 11.5238 | 242 | 0.6937 | 0.5888 | 0.6937 | 0.8329 |
|
| 173 |
+
| No log | 11.6190 | 244 | 0.6923 | 0.5888 | 0.6923 | 0.8321 |
|
| 174 |
+
| No log | 11.7143 | 246 | 0.6888 | 0.6224 | 0.6888 | 0.8299 |
|
| 175 |
+
| No log | 11.8095 | 248 | 0.7665 | 0.5840 | 0.7665 | 0.8755 |
|
| 176 |
+
| No log | 11.9048 | 250 | 0.7837 | 0.5631 | 0.7837 | 0.8853 |
|
| 177 |
+
| No log | 12.0 | 252 | 0.7349 | 0.5832 | 0.7349 | 0.8573 |
|
| 178 |
+
| No log | 12.0952 | 254 | 0.7308 | 0.5518 | 0.7308 | 0.8549 |
|
| 179 |
+
| No log | 12.1905 | 256 | 0.7693 | 0.4998 | 0.7693 | 0.8771 |
|
| 180 |
+
| No log | 12.2857 | 258 | 0.7478 | 0.5185 | 0.7478 | 0.8648 |
|
| 181 |
+
| No log | 12.3810 | 260 | 0.7354 | 0.5485 | 0.7354 | 0.8576 |
|
| 182 |
+
| No log | 12.4762 | 262 | 0.7141 | 0.5847 | 0.7141 | 0.8450 |
|
| 183 |
+
| No log | 12.5714 | 264 | 0.6989 | 0.6756 | 0.6989 | 0.8360 |
|
| 184 |
+
| No log | 12.6667 | 266 | 0.7098 | 0.5503 | 0.7098 | 0.8425 |
|
| 185 |
+
| No log | 12.7619 | 268 | 0.7399 | 0.5793 | 0.7399 | 0.8602 |
|
| 186 |
+
| No log | 12.8571 | 270 | 0.8832 | 0.4879 | 0.8832 | 0.9398 |
|
| 187 |
+
| No log | 12.9524 | 272 | 0.8322 | 0.4946 | 0.8322 | 0.9122 |
|
| 188 |
+
| No log | 13.0476 | 274 | 0.7819 | 0.5415 | 0.7819 | 0.8842 |
|
| 189 |
+
| No log | 13.1429 | 276 | 0.7233 | 0.6125 | 0.7233 | 0.8505 |
|
| 190 |
+
| No log | 13.2381 | 278 | 0.6979 | 0.6392 | 0.6979 | 0.8354 |
|
| 191 |
+
| No log | 13.3333 | 280 | 0.7061 | 0.6293 | 0.7061 | 0.8403 |
|
| 192 |
+
| No log | 13.4286 | 282 | 0.6957 | 0.6401 | 0.6957 | 0.8341 |
|
| 193 |
+
| No log | 13.5238 | 284 | 0.6867 | 0.6491 | 0.6867 | 0.8286 |
|
| 194 |
+
| No log | 13.6190 | 286 | 0.6847 | 0.6491 | 0.6847 | 0.8275 |
|
| 195 |
+
| No log | 13.7143 | 288 | 0.6858 | 0.6254 | 0.6858 | 0.8281 |
|
| 196 |
+
| No log | 13.8095 | 290 | 0.6918 | 0.6426 | 0.6918 | 0.8317 |
|
| 197 |
+
| No log | 13.9048 | 292 | 0.6920 | 0.6796 | 0.6920 | 0.8319 |
|
| 198 |
+
| No log | 14.0 | 294 | 0.7042 | 0.6119 | 0.7042 | 0.8391 |
|
| 199 |
+
| No log | 14.0952 | 296 | 0.7556 | 0.5766 | 0.7556 | 0.8692 |
|
| 200 |
+
| No log | 14.1905 | 298 | 0.7682 | 0.5455 | 0.7682 | 0.8765 |
|
| 201 |
+
| No log | 14.2857 | 300 | 0.7112 | 0.5485 | 0.7112 | 0.8433 |
|
| 202 |
+
| No log | 14.3810 | 302 | 0.7095 | 0.6076 | 0.7095 | 0.8423 |
|
| 203 |
+
| No log | 14.4762 | 304 | 0.7216 | 0.5930 | 0.7216 | 0.8495 |
|
| 204 |
+
| No log | 14.5714 | 306 | 0.7194 | 0.6392 | 0.7194 | 0.8482 |
|
| 205 |
+
| No log | 14.6667 | 308 | 0.7149 | 0.6659 | 0.7149 | 0.8455 |
|
| 206 |
+
| No log | 14.7619 | 310 | 0.7172 | 0.6628 | 0.7172 | 0.8469 |
|
| 207 |
+
| No log | 14.8571 | 312 | 0.7169 | 0.5987 | 0.7169 | 0.8467 |
|
| 208 |
+
| No log | 14.9524 | 314 | 0.6891 | 0.6288 | 0.6891 | 0.8301 |
|
| 209 |
+
| No log | 15.0476 | 316 | 0.7035 | 0.6383 | 0.7035 | 0.8387 |
|
| 210 |
+
| No log | 15.1429 | 318 | 0.7842 | 0.4937 | 0.7842 | 0.8855 |
|
| 211 |
+
| No log | 15.2381 | 320 | 0.7472 | 0.5235 | 0.7472 | 0.8644 |
|
| 212 |
+
| No log | 15.3333 | 322 | 0.6749 | 0.6526 | 0.6749 | 0.8215 |
|
| 213 |
+
| No log | 15.4286 | 324 | 0.6989 | 0.6012 | 0.6989 | 0.8360 |
|
| 214 |
+
| No log | 15.5238 | 326 | 0.7082 | 0.6188 | 0.7082 | 0.8416 |
|
| 215 |
+
| No log | 15.6190 | 328 | 0.6813 | 0.6875 | 0.6813 | 0.8254 |
|
| 216 |
+
| No log | 15.7143 | 330 | 0.6747 | 0.6916 | 0.6747 | 0.8214 |
|
| 217 |
+
| No log | 15.8095 | 332 | 0.6775 | 0.6589 | 0.6775 | 0.8231 |
|
| 218 |
+
| No log | 15.9048 | 334 | 0.6846 | 0.7070 | 0.6846 | 0.8274 |
|
| 219 |
+
| No log | 16.0 | 336 | 0.6874 | 0.6736 | 0.6874 | 0.8291 |
|
| 220 |
+
| No log | 16.0952 | 338 | 0.6802 | 0.6756 | 0.6802 | 0.8248 |
|
| 221 |
+
| No log | 16.1905 | 340 | 0.6849 | 0.6275 | 0.6849 | 0.8276 |
|
| 222 |
+
| No log | 16.2857 | 342 | 0.6871 | 0.6085 | 0.6871 | 0.8289 |
|
| 223 |
+
| No log | 16.3810 | 344 | 0.6946 | 0.5660 | 0.6946 | 0.8334 |
|
| 224 |
+
| No log | 16.4762 | 346 | 0.6980 | 0.5752 | 0.6980 | 0.8354 |
|
| 225 |
+
| No log | 16.5714 | 348 | 0.6705 | 0.6509 | 0.6705 | 0.8188 |
|
| 226 |
+
| No log | 16.6667 | 350 | 0.6889 | 0.5862 | 0.6889 | 0.8300 |
|
| 227 |
+
| No log | 16.7619 | 352 | 0.7877 | 0.5342 | 0.7877 | 0.8875 |
|
| 228 |
+
| No log | 16.8571 | 354 | 0.8072 | 0.5241 | 0.8072 | 0.8984 |
|
| 229 |
+
| No log | 16.9524 | 356 | 0.6824 | 0.6003 | 0.6824 | 0.8261 |
|
| 230 |
+
| No log | 17.0476 | 358 | 0.6441 | 0.6952 | 0.6441 | 0.8025 |
|
| 231 |
+
| No log | 17.1429 | 360 | 0.6797 | 0.6728 | 0.6797 | 0.8244 |
|
| 232 |
+
| No log | 17.2381 | 362 | 0.6952 | 0.5968 | 0.6952 | 0.8338 |
|
| 233 |
+
| No log | 17.3333 | 364 | 0.6717 | 0.5787 | 0.6717 | 0.8196 |
|
| 234 |
+
| No log | 17.4286 | 366 | 0.6610 | 0.5969 | 0.6610 | 0.8130 |
|
| 235 |
+
| No log | 17.5238 | 368 | 0.6428 | 0.6380 | 0.6428 | 0.8018 |
|
| 236 |
+
| No log | 17.6190 | 370 | 0.6351 | 0.5854 | 0.6351 | 0.7970 |
|
| 237 |
+
| No log | 17.7143 | 372 | 0.6321 | 0.6828 | 0.6321 | 0.7951 |
|
| 238 |
+
| No log | 17.8095 | 374 | 0.6416 | 0.6828 | 0.6416 | 0.8010 |
|
| 239 |
+
| No log | 17.9048 | 376 | 0.6502 | 0.6882 | 0.6502 | 0.8064 |
|
| 240 |
+
| No log | 18.0 | 378 | 0.6508 | 0.6828 | 0.6508 | 0.8067 |
|
| 241 |
+
| No log | 18.0952 | 380 | 0.6498 | 0.6756 | 0.6498 | 0.8061 |
|
| 242 |
+
| No log | 18.1905 | 382 | 0.6570 | 0.5971 | 0.6570 | 0.8105 |
|
| 243 |
+
| No log | 18.2857 | 384 | 0.6952 | 0.5641 | 0.6952 | 0.8338 |
|
| 244 |
+
| No log | 18.3810 | 386 | 0.7228 | 0.5653 | 0.7228 | 0.8502 |
|
| 245 |
+
| No log | 18.4762 | 388 | 0.7102 | 0.5301 | 0.7102 | 0.8427 |
|
| 246 |
+
| No log | 18.5714 | 390 | 0.7016 | 0.5656 | 0.7016 | 0.8376 |
|
| 247 |
+
| No log | 18.6667 | 392 | 0.7028 | 0.6249 | 0.7028 | 0.8383 |
|
| 248 |
+
| No log | 18.7619 | 394 | 0.7098 | 0.6526 | 0.7098 | 0.8425 |
|
| 249 |
+
| No log | 18.8571 | 396 | 0.7153 | 0.6144 | 0.7153 | 0.8457 |
|
| 250 |
+
| No log | 18.9524 | 398 | 0.7356 | 0.5826 | 0.7356 | 0.8577 |
|
| 251 |
+
| No log | 19.0476 | 400 | 0.7182 | 0.5804 | 0.7182 | 0.8475 |
|
| 252 |
+
| No log | 19.1429 | 402 | 0.6997 | 0.6526 | 0.6997 | 0.8365 |
|
| 253 |
+
| No log | 19.2381 | 404 | 0.6954 | 0.6526 | 0.6955 | 0.8339 |
|
| 254 |
+
| No log | 19.3333 | 406 | 0.6949 | 0.6606 | 0.6949 | 0.8336 |
|
| 255 |
+
| No log | 19.4286 | 408 | 0.6959 | 0.6606 | 0.6959 | 0.8342 |
|
| 256 |
+
| No log | 19.5238 | 410 | 0.7506 | 0.5547 | 0.7506 | 0.8664 |
|
| 257 |
+
| No log | 19.6190 | 412 | 0.8842 | 0.5164 | 0.8842 | 0.9403 |
|
| 258 |
+
| No log | 19.7143 | 414 | 0.9005 | 0.4890 | 0.9005 | 0.9489 |
|
| 259 |
+
| No log | 19.8095 | 416 | 0.7783 | 0.5130 | 0.7783 | 0.8822 |
|
| 260 |
+
| No log | 19.9048 | 418 | 0.6980 | 0.6526 | 0.6980 | 0.8355 |
|
| 261 |
+
| No log | 20.0 | 420 | 0.6953 | 0.5475 | 0.6953 | 0.8338 |
|
| 262 |
+
| No log | 20.0952 | 422 | 0.6954 | 0.5542 | 0.6954 | 0.8339 |
|
| 263 |
+
| No log | 20.1905 | 424 | 0.7150 | 0.5442 | 0.7150 | 0.8456 |
|
| 264 |
+
| No log | 20.2857 | 426 | 0.7565 | 0.5656 | 0.7565 | 0.8697 |
|
| 265 |
+
| No log | 20.3810 | 428 | 0.7617 | 0.5333 | 0.7617 | 0.8727 |
|
| 266 |
+
| No log | 20.4762 | 430 | 0.7169 | 0.5322 | 0.7169 | 0.8467 |
|
| 267 |
+
| No log | 20.5714 | 432 | 0.6856 | 0.6526 | 0.6856 | 0.8280 |
|
| 268 |
+
| No log | 20.6667 | 434 | 0.7039 | 0.5747 | 0.7039 | 0.8390 |
|
| 269 |
+
| No log | 20.7619 | 436 | 0.7391 | 0.6026 | 0.7391 | 0.8597 |
|
| 270 |
+
| No log | 20.8571 | 438 | 0.7611 | 0.5451 | 0.7611 | 0.8724 |
|
| 271 |
+
| No log | 20.9524 | 440 | 0.7491 | 0.5451 | 0.7491 | 0.8655 |
|
| 272 |
+
| No log | 21.0476 | 442 | 0.7340 | 0.5455 | 0.7340 | 0.8567 |
|
| 273 |
+
| No log | 21.1429 | 444 | 0.7068 | 0.6157 | 0.7068 | 0.8407 |
|
| 274 |
+
| No log | 21.2381 | 446 | 0.6986 | 0.6484 | 0.6986 | 0.8358 |
|
| 275 |
+
| No log | 21.3333 | 448 | 0.7036 | 0.6544 | 0.7036 | 0.8388 |
|
| 276 |
+
| No log | 21.4286 | 450 | 0.7060 | 0.5787 | 0.7060 | 0.8402 |
|
| 277 |
+
| No log | 21.5238 | 452 | 0.6991 | 0.6649 | 0.6991 | 0.8361 |
|
| 278 |
+
| No log | 21.6190 | 454 | 0.6971 | 0.6154 | 0.6971 | 0.8349 |
|
| 279 |
+
| No log | 21.7143 | 456 | 0.7012 | 0.5852 | 0.7012 | 0.8374 |
|
| 280 |
+
| No log | 21.8095 | 458 | 0.7034 | 0.5325 | 0.7034 | 0.8387 |
|
| 281 |
+
| No log | 21.9048 | 460 | 0.7251 | 0.5220 | 0.7251 | 0.8515 |
|
| 282 |
+
| No log | 22.0 | 462 | 0.7420 | 0.5451 | 0.7420 | 0.8614 |
|
| 283 |
+
| No log | 22.0952 | 464 | 0.7266 | 0.5325 | 0.7266 | 0.8524 |
|
| 284 |
+
| No log | 22.1905 | 466 | 0.6881 | 0.6078 | 0.6881 | 0.8295 |
|
| 285 |
+
| No log | 22.2857 | 468 | 0.7168 | 0.5610 | 0.7168 | 0.8466 |
|
| 286 |
+
| No log | 22.3810 | 470 | 0.7331 | 0.5500 | 0.7331 | 0.8562 |
|
| 287 |
+
| No log | 22.4762 | 472 | 0.7216 | 0.5517 | 0.7216 | 0.8495 |
|
| 288 |
+
| No log | 22.5714 | 474 | 0.7070 | 0.6272 | 0.7070 | 0.8408 |
|
| 289 |
+
| No log | 22.6667 | 476 | 0.6986 | 0.5735 | 0.6986 | 0.8358 |
|
| 290 |
+
| No log | 22.7619 | 478 | 0.7039 | 0.5759 | 0.7039 | 0.8390 |
|
| 291 |
+
| No log | 22.8571 | 480 | 0.7088 | 0.6035 | 0.7088 | 0.8419 |
|
| 292 |
+
| No log | 22.9524 | 482 | 0.7216 | 0.5500 | 0.7216 | 0.8495 |
|
| 293 |
+
| No log | 23.0476 | 484 | 0.7226 | 0.6002 | 0.7226 | 0.8501 |
|
| 294 |
+
| No log | 23.1429 | 486 | 0.7173 | 0.6002 | 0.7173 | 0.8470 |
|
| 295 |
+
| No log | 23.2381 | 488 | 0.6869 | 0.6068 | 0.6869 | 0.8288 |
|
| 296 |
+
| No log | 23.3333 | 490 | 0.7108 | 0.5519 | 0.7108 | 0.8431 |
|
| 297 |
+
| No log | 23.4286 | 492 | 0.7150 | 0.5629 | 0.7150 | 0.8456 |
|
| 298 |
+
| No log | 23.5238 | 494 | 0.6795 | 0.6225 | 0.6795 | 0.8243 |
|
| 299 |
+
| No log | 23.6190 | 496 | 0.6876 | 0.5929 | 0.6876 | 0.8292 |
|
| 300 |
+
| No log | 23.7143 | 498 | 0.6939 | 0.6002 | 0.6939 | 0.8330 |
|
| 301 |
+
| 0.2186 | 23.8095 | 500 | 0.7109 | 0.6179 | 0.7109 | 0.8432 |
|
| 302 |
+
| 0.2186 | 23.9048 | 502 | 0.6945 | 0.6028 | 0.6945 | 0.8334 |
|
| 303 |
+
| 0.2186 | 24.0 | 504 | 0.6798 | 0.6398 | 0.6798 | 0.8245 |
|
| 304 |
+
| 0.2186 | 24.0952 | 506 | 0.6910 | 0.6278 | 0.6910 | 0.8313 |
|
| 305 |
+
| 0.2186 | 24.1905 | 508 | 0.7036 | 0.5865 | 0.7036 | 0.8388 |
|
| 306 |
+
| 0.2186 | 24.2857 | 510 | 0.7007 | 0.6175 | 0.7007 | 0.8371 |
|
| 307 |
+
| 0.2186 | 24.3810 | 512 | 0.7072 | 0.6046 | 0.7072 | 0.8409 |
|
| 308 |
+
| 0.2186 | 24.4762 | 514 | 0.7126 | 0.5877 | 0.7126 | 0.8442 |
|
| 309 |
+
| 0.2186 | 24.5714 | 516 | 0.7061 | 0.6207 | 0.7061 | 0.8403 |
|
| 310 |
+
| 0.2186 | 24.6667 | 518 | 0.6988 | 0.6619 | 0.6988 | 0.8360 |
|
| 311 |
+
| 0.2186 | 24.7619 | 520 | 0.6995 | 0.6537 | 0.6995 | 0.8364 |
|
| 312 |
+
| 0.2186 | 24.8571 | 522 | 0.7080 | 0.5954 | 0.7080 | 0.8414 |
|
| 313 |
+
| 0.2186 | 24.9524 | 524 | 0.7390 | 0.5699 | 0.7390 | 0.8596 |
|
| 314 |
+
| 0.2186 | 25.0476 | 526 | 0.7637 | 0.5366 | 0.7637 | 0.8739 |
|
| 315 |
+
| 0.2186 | 25.1429 | 528 | 0.7635 | 0.5366 | 0.7635 | 0.8738 |
|
| 316 |
+
| 0.2186 | 25.2381 | 530 | 0.7130 | 0.5505 | 0.7130 | 0.8444 |
|
| 317 |
+
|
| 318 |
+
|
| 319 |
+
### Framework versions
|
| 320 |
+
|
| 321 |
+
- Transformers 4.44.2
|
| 322 |
+
- Pytorch 2.4.0+cu118
|
| 323 |
+
- Datasets 2.21.0
|
| 324 |
+
- 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:e02bb8bedb5cf2e6993a2993ad7d8559f760df5f6ac41c46da40148c1b5783da
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9ddd64b801f2dcfbae58ba92fa33978180a6178da0df0e6950109f7a3290f43
|
| 3 |
+
size 5304
|