Training in progress, step 500
Browse files- README.md +315 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_run2_AugV5_k18_task1_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_run2_AugV5_k18_task1_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: 0.6326
|
| 19 |
+
- Qwk: 0.7815
|
| 20 |
+
- Mse: 0.6326
|
| 21 |
+
- Rmse: 0.7954
|
| 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 | 0.0227 | 2 | 6.9743 | -0.0278 | 6.9743 | 2.6409 |
|
| 53 |
+
| No log | 0.0455 | 4 | 4.5592 | 0.0169 | 4.5592 | 2.1352 |
|
| 54 |
+
| No log | 0.0682 | 6 | 3.4820 | -0.0430 | 3.4820 | 1.8660 |
|
| 55 |
+
| No log | 0.0909 | 8 | 2.3864 | 0.2302 | 2.3864 | 1.5448 |
|
| 56 |
+
| No log | 0.1136 | 10 | 2.0758 | 0.2677 | 2.0758 | 1.4408 |
|
| 57 |
+
| No log | 0.1364 | 12 | 2.2326 | 0.1630 | 2.2326 | 1.4942 |
|
| 58 |
+
| No log | 0.1591 | 14 | 2.1811 | 0.1926 | 2.1811 | 1.4769 |
|
| 59 |
+
| No log | 0.1818 | 16 | 2.0686 | 0.2687 | 2.0686 | 1.4383 |
|
| 60 |
+
| No log | 0.2045 | 18 | 1.5153 | 0.2435 | 1.5153 | 1.2310 |
|
| 61 |
+
| No log | 0.2273 | 20 | 1.7749 | 0.1091 | 1.7749 | 1.3323 |
|
| 62 |
+
| No log | 0.25 | 22 | 1.8188 | 0.0550 | 1.8188 | 1.3486 |
|
| 63 |
+
| No log | 0.2727 | 24 | 1.3981 | 0.2364 | 1.3981 | 1.1824 |
|
| 64 |
+
| No log | 0.2955 | 26 | 1.7041 | 0.3622 | 1.7041 | 1.3054 |
|
| 65 |
+
| No log | 0.3182 | 28 | 2.1101 | 0.2162 | 2.1101 | 1.4526 |
|
| 66 |
+
| No log | 0.3409 | 30 | 1.8572 | 0.3231 | 1.8572 | 1.3628 |
|
| 67 |
+
| No log | 0.3636 | 32 | 1.3338 | 0.3559 | 1.3338 | 1.1549 |
|
| 68 |
+
| No log | 0.3864 | 34 | 1.2047 | 0.3621 | 1.2047 | 1.0976 |
|
| 69 |
+
| No log | 0.4091 | 36 | 1.2954 | 0.4262 | 1.2954 | 1.1382 |
|
| 70 |
+
| No log | 0.4318 | 38 | 1.4506 | 0.4032 | 1.4506 | 1.2044 |
|
| 71 |
+
| No log | 0.4545 | 40 | 1.3107 | 0.4160 | 1.3107 | 1.1448 |
|
| 72 |
+
| No log | 0.4773 | 42 | 1.0420 | 0.5984 | 1.0420 | 1.0208 |
|
| 73 |
+
| No log | 0.5 | 44 | 1.1420 | 0.5410 | 1.1420 | 1.0687 |
|
| 74 |
+
| No log | 0.5227 | 46 | 2.1427 | 0.0 | 2.1427 | 1.4638 |
|
| 75 |
+
| No log | 0.5455 | 48 | 1.9143 | 0.1311 | 1.9143 | 1.3836 |
|
| 76 |
+
| No log | 0.5682 | 50 | 1.1752 | 0.4 | 1.1752 | 1.0841 |
|
| 77 |
+
| No log | 0.5909 | 52 | 1.4822 | 0.4444 | 1.4822 | 1.2174 |
|
| 78 |
+
| No log | 0.6136 | 54 | 1.5423 | 0.4521 | 1.5423 | 1.2419 |
|
| 79 |
+
| No log | 0.6364 | 56 | 1.0415 | 0.5522 | 1.0415 | 1.0205 |
|
| 80 |
+
| No log | 0.6591 | 58 | 1.2423 | 0.4553 | 1.2423 | 1.1146 |
|
| 81 |
+
| No log | 0.6818 | 60 | 1.7989 | 0.1404 | 1.7989 | 1.3412 |
|
| 82 |
+
| No log | 0.7045 | 62 | 1.3875 | 0.3902 | 1.3875 | 1.1779 |
|
| 83 |
+
| No log | 0.7273 | 64 | 0.8910 | 0.6094 | 0.8910 | 0.9439 |
|
| 84 |
+
| No log | 0.75 | 66 | 0.9726 | 0.5846 | 0.9726 | 0.9862 |
|
| 85 |
+
| No log | 0.7727 | 68 | 0.9403 | 0.6107 | 0.9403 | 0.9697 |
|
| 86 |
+
| No log | 0.7955 | 70 | 0.8847 | 0.6716 | 0.8847 | 0.9406 |
|
| 87 |
+
| No log | 0.8182 | 72 | 0.8187 | 0.6212 | 0.8187 | 0.9048 |
|
| 88 |
+
| No log | 0.8409 | 74 | 0.8983 | 0.6565 | 0.8983 | 0.9478 |
|
| 89 |
+
| No log | 0.8636 | 76 | 0.8959 | 0.6565 | 0.8959 | 0.9465 |
|
| 90 |
+
| No log | 0.8864 | 78 | 0.8795 | 0.5781 | 0.8795 | 0.9378 |
|
| 91 |
+
| No log | 0.9091 | 80 | 0.9962 | 0.5538 | 0.9962 | 0.9981 |
|
| 92 |
+
| No log | 0.9318 | 82 | 0.9786 | 0.5758 | 0.9786 | 0.9893 |
|
| 93 |
+
| No log | 0.9545 | 84 | 0.8415 | 0.5649 | 0.8415 | 0.9174 |
|
| 94 |
+
| No log | 0.9773 | 86 | 0.7479 | 0.6906 | 0.7479 | 0.8648 |
|
| 95 |
+
| No log | 1.0 | 88 | 0.7046 | 0.6809 | 0.7046 | 0.8394 |
|
| 96 |
+
| No log | 1.0227 | 90 | 0.6924 | 0.6853 | 0.6924 | 0.8321 |
|
| 97 |
+
| No log | 1.0455 | 92 | 0.7287 | 0.7123 | 0.7287 | 0.8537 |
|
| 98 |
+
| No log | 1.0682 | 94 | 0.7314 | 0.7075 | 0.7314 | 0.8552 |
|
| 99 |
+
| No log | 1.0909 | 96 | 0.7086 | 0.6763 | 0.7086 | 0.8418 |
|
| 100 |
+
| No log | 1.1136 | 98 | 0.8119 | 0.7376 | 0.8119 | 0.9011 |
|
| 101 |
+
| No log | 1.1364 | 100 | 0.9955 | 0.6667 | 0.9955 | 0.9978 |
|
| 102 |
+
| No log | 1.1591 | 102 | 1.0284 | 0.6567 | 1.0284 | 1.0141 |
|
| 103 |
+
| No log | 1.1818 | 104 | 0.9645 | 0.6765 | 0.9645 | 0.9821 |
|
| 104 |
+
| No log | 1.2045 | 106 | 0.9483 | 0.6618 | 0.9483 | 0.9738 |
|
| 105 |
+
| No log | 1.2273 | 108 | 0.9764 | 0.5496 | 0.9764 | 0.9881 |
|
| 106 |
+
| No log | 1.25 | 110 | 0.9327 | 0.6015 | 0.9327 | 0.9658 |
|
| 107 |
+
| No log | 1.2727 | 112 | 0.8524 | 0.7183 | 0.8524 | 0.9233 |
|
| 108 |
+
| No log | 1.2955 | 114 | 0.9425 | 0.6622 | 0.9425 | 0.9708 |
|
| 109 |
+
| No log | 1.3182 | 116 | 1.0199 | 0.6577 | 1.0199 | 1.0099 |
|
| 110 |
+
| No log | 1.3409 | 118 | 0.9427 | 0.6622 | 0.9427 | 0.9709 |
|
| 111 |
+
| No log | 1.3636 | 120 | 0.8206 | 0.7517 | 0.8206 | 0.9059 |
|
| 112 |
+
| No log | 1.3864 | 122 | 0.8274 | 0.7034 | 0.8274 | 0.9096 |
|
| 113 |
+
| No log | 1.4091 | 124 | 0.9004 | 0.7550 | 0.9004 | 0.9489 |
|
| 114 |
+
| No log | 1.4318 | 126 | 0.9260 | 0.7310 | 0.9260 | 0.9623 |
|
| 115 |
+
| No log | 1.4545 | 128 | 0.9116 | 0.6571 | 0.9116 | 0.9548 |
|
| 116 |
+
| No log | 1.4773 | 130 | 1.0824 | 0.4889 | 1.0824 | 1.0404 |
|
| 117 |
+
| No log | 1.5 | 132 | 1.0732 | 0.4615 | 1.0732 | 1.0359 |
|
| 118 |
+
| No log | 1.5227 | 134 | 1.0542 | 0.5039 | 1.0542 | 1.0267 |
|
| 119 |
+
| No log | 1.5455 | 136 | 1.0443 | 0.4960 | 1.0443 | 1.0219 |
|
| 120 |
+
| No log | 1.5682 | 138 | 0.9862 | 0.6165 | 0.9862 | 0.9931 |
|
| 121 |
+
| No log | 1.5909 | 140 | 0.8693 | 0.7413 | 0.8693 | 0.9324 |
|
| 122 |
+
| No log | 1.6136 | 142 | 0.7538 | 0.7483 | 0.7538 | 0.8682 |
|
| 123 |
+
| No log | 1.6364 | 144 | 0.7626 | 0.7333 | 0.7626 | 0.8732 |
|
| 124 |
+
| No log | 1.6591 | 146 | 0.8456 | 0.7342 | 0.8456 | 0.9196 |
|
| 125 |
+
| No log | 1.6818 | 148 | 0.8284 | 0.7436 | 0.8284 | 0.9102 |
|
| 126 |
+
| No log | 1.7045 | 150 | 0.8071 | 0.7484 | 0.8071 | 0.8984 |
|
| 127 |
+
| No log | 1.7273 | 152 | 0.7607 | 0.7397 | 0.7607 | 0.8722 |
|
| 128 |
+
| No log | 1.75 | 154 | 0.8006 | 0.7042 | 0.8006 | 0.8947 |
|
| 129 |
+
| No log | 1.7727 | 156 | 0.8423 | 0.7172 | 0.8423 | 0.9178 |
|
| 130 |
+
| No log | 1.7955 | 158 | 0.9368 | 0.6803 | 0.9368 | 0.9679 |
|
| 131 |
+
| No log | 1.8182 | 160 | 0.9032 | 0.7123 | 0.9032 | 0.9504 |
|
| 132 |
+
| No log | 1.8409 | 162 | 0.9733 | 0.6622 | 0.9733 | 0.9865 |
|
| 133 |
+
| No log | 1.8636 | 164 | 0.9280 | 0.6901 | 0.9280 | 0.9633 |
|
| 134 |
+
| No log | 1.8864 | 166 | 0.8882 | 0.6763 | 0.8882 | 0.9424 |
|
| 135 |
+
| No log | 1.9091 | 168 | 0.9003 | 0.6423 | 0.9003 | 0.9488 |
|
| 136 |
+
| No log | 1.9318 | 170 | 0.9544 | 0.7286 | 0.9544 | 0.9769 |
|
| 137 |
+
| No log | 1.9545 | 172 | 0.9196 | 0.7194 | 0.9196 | 0.9590 |
|
| 138 |
+
| No log | 1.9773 | 174 | 0.8268 | 0.7007 | 0.8268 | 0.9093 |
|
| 139 |
+
| No log | 2.0 | 176 | 0.8000 | 0.6620 | 0.8000 | 0.8945 |
|
| 140 |
+
| No log | 2.0227 | 178 | 0.7447 | 0.7027 | 0.7447 | 0.8630 |
|
| 141 |
+
| No log | 2.0455 | 180 | 0.6651 | 0.7755 | 0.6651 | 0.8155 |
|
| 142 |
+
| No log | 2.0682 | 182 | 0.7993 | 0.6667 | 0.7993 | 0.8941 |
|
| 143 |
+
| No log | 2.0909 | 184 | 0.8174 | 0.6711 | 0.8174 | 0.9041 |
|
| 144 |
+
| No log | 2.1136 | 186 | 0.8542 | 0.6711 | 0.8542 | 0.9242 |
|
| 145 |
+
| No log | 2.1364 | 188 | 0.7723 | 0.7114 | 0.7723 | 0.8788 |
|
| 146 |
+
| No log | 2.1591 | 190 | 0.7465 | 0.7448 | 0.7465 | 0.8640 |
|
| 147 |
+
| No log | 2.1818 | 192 | 0.7758 | 0.7222 | 0.7758 | 0.8808 |
|
| 148 |
+
| No log | 2.2045 | 194 | 0.8063 | 0.7222 | 0.8063 | 0.8980 |
|
| 149 |
+
| No log | 2.2273 | 196 | 0.8914 | 0.6622 | 0.8914 | 0.9441 |
|
| 150 |
+
| No log | 2.25 | 198 | 0.9911 | 0.6531 | 0.9911 | 0.9956 |
|
| 151 |
+
| No log | 2.2727 | 200 | 0.9027 | 0.6575 | 0.9027 | 0.9501 |
|
| 152 |
+
| No log | 2.2955 | 202 | 0.8462 | 0.7042 | 0.8462 | 0.9199 |
|
| 153 |
+
| No log | 2.3182 | 204 | 0.9090 | 0.6957 | 0.9090 | 0.9534 |
|
| 154 |
+
| No log | 2.3409 | 206 | 1.0338 | 0.5538 | 1.0338 | 1.0168 |
|
| 155 |
+
| No log | 2.3636 | 208 | 1.1545 | 0.5303 | 1.1545 | 1.0745 |
|
| 156 |
+
| No log | 2.3864 | 210 | 1.0709 | 0.5344 | 1.0709 | 1.0349 |
|
| 157 |
+
| No log | 2.4091 | 212 | 0.9374 | 0.6519 | 0.9374 | 0.9682 |
|
| 158 |
+
| No log | 2.4318 | 214 | 0.8529 | 0.7 | 0.8529 | 0.9235 |
|
| 159 |
+
| No log | 2.4545 | 216 | 0.8650 | 0.6479 | 0.8650 | 0.9301 |
|
| 160 |
+
| No log | 2.4773 | 218 | 0.9528 | 0.6294 | 0.9528 | 0.9761 |
|
| 161 |
+
| No log | 2.5 | 220 | 0.9113 | 0.6434 | 0.9113 | 0.9546 |
|
| 162 |
+
| No log | 2.5227 | 222 | 0.8445 | 0.6571 | 0.8445 | 0.9190 |
|
| 163 |
+
| No log | 2.5455 | 224 | 0.9030 | 0.6434 | 0.9030 | 0.9503 |
|
| 164 |
+
| No log | 2.5682 | 226 | 0.8839 | 0.6667 | 0.8839 | 0.9402 |
|
| 165 |
+
| No log | 2.5909 | 228 | 0.8481 | 0.6715 | 0.8481 | 0.9209 |
|
| 166 |
+
| No log | 2.6136 | 230 | 0.8205 | 0.6944 | 0.8205 | 0.9058 |
|
| 167 |
+
| No log | 2.6364 | 232 | 0.8385 | 0.6849 | 0.8385 | 0.9157 |
|
| 168 |
+
| No log | 2.6591 | 234 | 0.9321 | 0.6577 | 0.9321 | 0.9655 |
|
| 169 |
+
| No log | 2.6818 | 236 | 0.8383 | 0.6577 | 0.8383 | 0.9156 |
|
| 170 |
+
| No log | 2.7045 | 238 | 0.6823 | 0.7448 | 0.6823 | 0.8260 |
|
| 171 |
+
| No log | 2.7273 | 240 | 0.6504 | 0.7517 | 0.6504 | 0.8065 |
|
| 172 |
+
| No log | 2.75 | 242 | 0.6413 | 0.7712 | 0.6413 | 0.8008 |
|
| 173 |
+
| No log | 2.7727 | 244 | 0.6410 | 0.7484 | 0.6410 | 0.8006 |
|
| 174 |
+
| No log | 2.7955 | 246 | 0.6645 | 0.75 | 0.6645 | 0.8152 |
|
| 175 |
+
| No log | 2.8182 | 248 | 0.6972 | 0.7320 | 0.6972 | 0.8350 |
|
| 176 |
+
| No log | 2.8409 | 250 | 0.7412 | 0.7586 | 0.7412 | 0.8609 |
|
| 177 |
+
| No log | 2.8636 | 252 | 0.7820 | 0.7273 | 0.7820 | 0.8843 |
|
| 178 |
+
| No log | 2.8864 | 254 | 0.7875 | 0.7234 | 0.7875 | 0.8874 |
|
| 179 |
+
| No log | 2.9091 | 256 | 0.9850 | 0.6133 | 0.9850 | 0.9925 |
|
| 180 |
+
| No log | 2.9318 | 258 | 1.1042 | 0.5503 | 1.1042 | 1.0508 |
|
| 181 |
+
| No log | 2.9545 | 260 | 0.9412 | 0.6358 | 0.9412 | 0.9701 |
|
| 182 |
+
| No log | 2.9773 | 262 | 0.7571 | 0.7234 | 0.7571 | 0.8701 |
|
| 183 |
+
| No log | 3.0 | 264 | 0.8047 | 0.7324 | 0.8047 | 0.8971 |
|
| 184 |
+
| No log | 3.0227 | 266 | 0.7769 | 0.7324 | 0.7769 | 0.8814 |
|
| 185 |
+
| No log | 3.0455 | 268 | 0.6807 | 0.7755 | 0.6807 | 0.8251 |
|
| 186 |
+
| No log | 3.0682 | 270 | 0.6464 | 0.7815 | 0.6464 | 0.8040 |
|
| 187 |
+
| No log | 3.0909 | 272 | 0.6470 | 0.7755 | 0.6470 | 0.8044 |
|
| 188 |
+
| No log | 3.1136 | 274 | 0.6447 | 0.7724 | 0.6447 | 0.8030 |
|
| 189 |
+
| No log | 3.1364 | 276 | 0.6631 | 0.7862 | 0.6631 | 0.8143 |
|
| 190 |
+
| No log | 3.1591 | 278 | 0.6699 | 0.7808 | 0.6699 | 0.8185 |
|
| 191 |
+
| No log | 3.1818 | 280 | 0.7265 | 0.7260 | 0.7265 | 0.8524 |
|
| 192 |
+
| No log | 3.2045 | 282 | 0.6701 | 0.7413 | 0.6701 | 0.8186 |
|
| 193 |
+
| No log | 3.2273 | 284 | 0.6245 | 0.7808 | 0.6245 | 0.7903 |
|
| 194 |
+
| No log | 3.25 | 286 | 0.6322 | 0.7586 | 0.6322 | 0.7951 |
|
| 195 |
+
| No log | 3.2727 | 288 | 0.6238 | 0.7586 | 0.6238 | 0.7898 |
|
| 196 |
+
| No log | 3.2955 | 290 | 0.6449 | 0.7211 | 0.6449 | 0.8030 |
|
| 197 |
+
| No log | 3.3182 | 292 | 0.5603 | 0.8079 | 0.5603 | 0.7485 |
|
| 198 |
+
| No log | 3.3409 | 294 | 0.5685 | 0.8079 | 0.5685 | 0.7540 |
|
| 199 |
+
| No log | 3.3636 | 296 | 0.6257 | 0.7838 | 0.6257 | 0.7910 |
|
| 200 |
+
| No log | 3.3864 | 298 | 0.7448 | 0.6667 | 0.7448 | 0.8630 |
|
| 201 |
+
| No log | 3.4091 | 300 | 0.7606 | 0.6667 | 0.7606 | 0.8721 |
|
| 202 |
+
| No log | 3.4318 | 302 | 0.6708 | 0.7619 | 0.6708 | 0.8190 |
|
| 203 |
+
| No log | 3.4545 | 304 | 0.6598 | 0.7808 | 0.6598 | 0.8123 |
|
| 204 |
+
| No log | 3.4773 | 306 | 0.6642 | 0.7808 | 0.6642 | 0.8150 |
|
| 205 |
+
| No log | 3.5 | 308 | 0.6977 | 0.7183 | 0.6977 | 0.8353 |
|
| 206 |
+
| No log | 3.5227 | 310 | 0.8358 | 0.6241 | 0.8358 | 0.9142 |
|
| 207 |
+
| No log | 3.5455 | 312 | 0.8519 | 0.6241 | 0.8519 | 0.9230 |
|
| 208 |
+
| No log | 3.5682 | 314 | 0.7862 | 0.7143 | 0.7862 | 0.8867 |
|
| 209 |
+
| No log | 3.5909 | 316 | 0.8436 | 0.6423 | 0.8436 | 0.9185 |
|
| 210 |
+
| No log | 3.6136 | 318 | 0.9416 | 0.5985 | 0.9416 | 0.9704 |
|
| 211 |
+
| No log | 3.6364 | 320 | 0.8990 | 0.6434 | 0.8990 | 0.9481 |
|
| 212 |
+
| No log | 3.6591 | 322 | 0.7402 | 0.7755 | 0.7402 | 0.8603 |
|
| 213 |
+
| No log | 3.6818 | 324 | 0.6738 | 0.7891 | 0.6738 | 0.8209 |
|
| 214 |
+
| No log | 3.7045 | 326 | 0.6549 | 0.7891 | 0.6549 | 0.8093 |
|
| 215 |
+
| No log | 3.7273 | 328 | 0.6481 | 0.7973 | 0.6481 | 0.8051 |
|
| 216 |
+
| No log | 3.75 | 330 | 0.6604 | 0.7950 | 0.6604 | 0.8126 |
|
| 217 |
+
| No log | 3.7727 | 332 | 0.6685 | 0.8108 | 0.6685 | 0.8176 |
|
| 218 |
+
| No log | 3.7955 | 334 | 0.7141 | 0.7785 | 0.7141 | 0.8450 |
|
| 219 |
+
| No log | 3.8182 | 336 | 0.7666 | 0.72 | 0.7666 | 0.8755 |
|
| 220 |
+
| No log | 3.8409 | 338 | 0.7184 | 0.7368 | 0.7184 | 0.8476 |
|
| 221 |
+
| No log | 3.8636 | 340 | 0.6854 | 0.7771 | 0.6854 | 0.8279 |
|
| 222 |
+
| No log | 3.8864 | 342 | 0.7161 | 0.7607 | 0.7161 | 0.8462 |
|
| 223 |
+
| No log | 3.9091 | 344 | 0.6703 | 0.7975 | 0.6703 | 0.8187 |
|
| 224 |
+
| No log | 3.9318 | 346 | 0.6987 | 0.7467 | 0.6987 | 0.8359 |
|
| 225 |
+
| No log | 3.9545 | 348 | 0.8475 | 0.6887 | 0.8475 | 0.9206 |
|
| 226 |
+
| No log | 3.9773 | 350 | 0.8747 | 0.6803 | 0.8747 | 0.9353 |
|
| 227 |
+
| No log | 4.0 | 352 | 0.8075 | 0.7034 | 0.8075 | 0.8986 |
|
| 228 |
+
| No log | 4.0227 | 354 | 0.7749 | 0.7448 | 0.7749 | 0.8803 |
|
| 229 |
+
| No log | 4.0455 | 356 | 0.7778 | 0.7222 | 0.7778 | 0.8819 |
|
| 230 |
+
| No log | 4.0682 | 358 | 0.7701 | 0.7222 | 0.7701 | 0.8776 |
|
| 231 |
+
| No log | 4.0909 | 360 | 0.7874 | 0.7234 | 0.7874 | 0.8874 |
|
| 232 |
+
| No log | 4.1136 | 362 | 0.8250 | 0.6667 | 0.8250 | 0.9083 |
|
| 233 |
+
| No log | 4.1364 | 364 | 0.8343 | 0.6667 | 0.8343 | 0.9134 |
|
| 234 |
+
| No log | 4.1591 | 366 | 0.7378 | 0.7484 | 0.7378 | 0.8590 |
|
| 235 |
+
| No log | 4.1818 | 368 | 0.7665 | 0.7170 | 0.7665 | 0.8755 |
|
| 236 |
+
| No log | 4.2045 | 370 | 0.8407 | 0.6875 | 0.8407 | 0.9169 |
|
| 237 |
+
| No log | 4.2273 | 372 | 0.7967 | 0.7097 | 0.7967 | 0.8926 |
|
| 238 |
+
| No log | 4.25 | 374 | 0.7298 | 0.76 | 0.7298 | 0.8543 |
|
| 239 |
+
| No log | 4.2727 | 376 | 0.8087 | 0.6901 | 0.8087 | 0.8993 |
|
| 240 |
+
| No log | 4.2955 | 378 | 0.8583 | 0.6331 | 0.8583 | 0.9264 |
|
| 241 |
+
| No log | 4.3182 | 380 | 0.8249 | 0.7133 | 0.8249 | 0.9082 |
|
| 242 |
+
| No log | 4.3409 | 382 | 0.8174 | 0.6849 | 0.8174 | 0.9041 |
|
| 243 |
+
| No log | 4.3636 | 384 | 0.7752 | 0.7067 | 0.7752 | 0.8805 |
|
| 244 |
+
| No log | 4.3864 | 386 | 0.6636 | 0.7632 | 0.6636 | 0.8146 |
|
| 245 |
+
| No log | 4.4091 | 388 | 0.6456 | 0.8024 | 0.6456 | 0.8035 |
|
| 246 |
+
| No log | 4.4318 | 390 | 0.6938 | 0.7811 | 0.6938 | 0.8329 |
|
| 247 |
+
| No log | 4.4545 | 392 | 0.7262 | 0.7636 | 0.7262 | 0.8522 |
|
| 248 |
+
| No log | 4.4773 | 394 | 0.6698 | 0.7974 | 0.6698 | 0.8184 |
|
| 249 |
+
| No log | 4.5 | 396 | 0.6725 | 0.7891 | 0.6725 | 0.8201 |
|
| 250 |
+
| No log | 4.5227 | 398 | 0.6864 | 0.7467 | 0.6864 | 0.8285 |
|
| 251 |
+
| No log | 4.5455 | 400 | 0.6981 | 0.7568 | 0.6981 | 0.8355 |
|
| 252 |
+
| No log | 4.5682 | 402 | 0.6928 | 0.7534 | 0.6928 | 0.8324 |
|
| 253 |
+
| No log | 4.5909 | 404 | 0.6856 | 0.7586 | 0.6856 | 0.8280 |
|
| 254 |
+
| No log | 4.6136 | 406 | 0.6931 | 0.7534 | 0.6931 | 0.8325 |
|
| 255 |
+
| No log | 4.6364 | 408 | 0.7094 | 0.7619 | 0.7094 | 0.8423 |
|
| 256 |
+
| No log | 4.6591 | 410 | 0.8204 | 0.6849 | 0.8204 | 0.9058 |
|
| 257 |
+
| No log | 4.6818 | 412 | 0.9091 | 0.6383 | 0.9091 | 0.9535 |
|
| 258 |
+
| No log | 4.7045 | 414 | 0.8611 | 0.6571 | 0.8611 | 0.9280 |
|
| 259 |
+
| No log | 4.7273 | 416 | 0.7949 | 0.75 | 0.7949 | 0.8916 |
|
| 260 |
+
| No log | 4.75 | 418 | 0.7360 | 0.7361 | 0.7360 | 0.8579 |
|
| 261 |
+
| No log | 4.7727 | 420 | 0.7258 | 0.7133 | 0.7258 | 0.8519 |
|
| 262 |
+
| No log | 4.7955 | 422 | 0.7124 | 0.7534 | 0.7124 | 0.8441 |
|
| 263 |
+
| No log | 4.8182 | 424 | 0.7407 | 0.7324 | 0.7407 | 0.8606 |
|
| 264 |
+
| No log | 4.8409 | 426 | 0.7665 | 0.6993 | 0.7665 | 0.8755 |
|
| 265 |
+
| No log | 4.8636 | 428 | 0.7552 | 0.7143 | 0.7552 | 0.8690 |
|
| 266 |
+
| No log | 4.8864 | 430 | 0.7642 | 0.7273 | 0.7642 | 0.8742 |
|
| 267 |
+
| No log | 4.9091 | 432 | 0.7823 | 0.7042 | 0.7823 | 0.8845 |
|
| 268 |
+
| No log | 4.9318 | 434 | 0.7719 | 0.6950 | 0.7719 | 0.8786 |
|
| 269 |
+
| No log | 4.9545 | 436 | 0.7652 | 0.7397 | 0.7652 | 0.8747 |
|
| 270 |
+
| No log | 4.9773 | 438 | 0.8592 | 0.6849 | 0.8592 | 0.9269 |
|
| 271 |
+
| No log | 5.0 | 440 | 0.8796 | 0.6849 | 0.8796 | 0.9379 |
|
| 272 |
+
| No log | 5.0227 | 442 | 0.8554 | 0.7 | 0.8554 | 0.9249 |
|
| 273 |
+
| No log | 5.0455 | 444 | 0.8548 | 0.6715 | 0.8548 | 0.9245 |
|
| 274 |
+
| No log | 5.0682 | 446 | 0.8016 | 0.6950 | 0.8016 | 0.8953 |
|
| 275 |
+
| No log | 5.0909 | 448 | 0.7498 | 0.7397 | 0.7498 | 0.8659 |
|
| 276 |
+
| No log | 5.1136 | 450 | 0.7401 | 0.7432 | 0.7401 | 0.8603 |
|
| 277 |
+
| No log | 5.1364 | 452 | 0.7312 | 0.7397 | 0.7312 | 0.8551 |
|
| 278 |
+
| No log | 5.1591 | 454 | 0.7830 | 0.7034 | 0.7830 | 0.8849 |
|
| 279 |
+
| No log | 5.1818 | 456 | 0.8324 | 0.7034 | 0.8324 | 0.9124 |
|
| 280 |
+
| No log | 5.2045 | 458 | 0.8319 | 0.7034 | 0.8319 | 0.9121 |
|
| 281 |
+
| No log | 5.2273 | 460 | 0.8182 | 0.7092 | 0.8182 | 0.9046 |
|
| 282 |
+
| No log | 5.25 | 462 | 0.8412 | 0.7092 | 0.8412 | 0.9171 |
|
| 283 |
+
| No log | 5.2727 | 464 | 0.8856 | 0.7 | 0.8856 | 0.9411 |
|
| 284 |
+
| No log | 5.2955 | 466 | 0.8862 | 0.6667 | 0.8862 | 0.9414 |
|
| 285 |
+
| No log | 5.3182 | 468 | 0.8618 | 0.7 | 0.8618 | 0.9283 |
|
| 286 |
+
| No log | 5.3409 | 470 | 0.8294 | 0.7234 | 0.8294 | 0.9107 |
|
| 287 |
+
| No log | 5.3636 | 472 | 0.8005 | 0.7324 | 0.8005 | 0.8947 |
|
| 288 |
+
| No log | 5.3864 | 474 | 0.8225 | 0.7075 | 0.8225 | 0.9069 |
|
| 289 |
+
| No log | 5.4091 | 476 | 0.8039 | 0.7143 | 0.8039 | 0.8966 |
|
| 290 |
+
| No log | 5.4318 | 478 | 0.7463 | 0.7285 | 0.7463 | 0.8639 |
|
| 291 |
+
| No log | 5.4545 | 480 | 0.7326 | 0.75 | 0.7326 | 0.8559 |
|
| 292 |
+
| No log | 5.4773 | 482 | 0.8084 | 0.7237 | 0.8084 | 0.8991 |
|
| 293 |
+
| No log | 5.5 | 484 | 0.8386 | 0.7152 | 0.8386 | 0.9157 |
|
| 294 |
+
| No log | 5.5227 | 486 | 0.7689 | 0.7483 | 0.7689 | 0.8768 |
|
| 295 |
+
| No log | 5.5455 | 488 | 0.7289 | 0.7383 | 0.7289 | 0.8538 |
|
| 296 |
+
| No log | 5.5682 | 490 | 0.7855 | 0.7211 | 0.7855 | 0.8863 |
|
| 297 |
+
| No log | 5.5909 | 492 | 0.8410 | 0.7027 | 0.8410 | 0.9170 |
|
| 298 |
+
| No log | 5.6136 | 494 | 0.8070 | 0.7211 | 0.8070 | 0.8983 |
|
| 299 |
+
| No log | 5.6364 | 496 | 0.7323 | 0.76 | 0.7323 | 0.8557 |
|
| 300 |
+
| No log | 5.6591 | 498 | 0.6802 | 0.7843 | 0.6802 | 0.8248 |
|
| 301 |
+
| 0.4345 | 5.6818 | 500 | 0.6692 | 0.7952 | 0.6692 | 0.8181 |
|
| 302 |
+
| 0.4345 | 5.7045 | 502 | 0.6164 | 0.8242 | 0.6164 | 0.7851 |
|
| 303 |
+
| 0.4345 | 5.7273 | 504 | 0.5909 | 0.7792 | 0.5909 | 0.7687 |
|
| 304 |
+
| 0.4345 | 5.75 | 506 | 0.6855 | 0.7403 | 0.6855 | 0.8279 |
|
| 305 |
+
| 0.4345 | 5.7727 | 508 | 0.7308 | 0.7485 | 0.7308 | 0.8549 |
|
| 306 |
+
| 0.4345 | 5.7955 | 510 | 0.6786 | 0.7578 | 0.6786 | 0.8238 |
|
| 307 |
+
| 0.4345 | 5.8182 | 512 | 0.6326 | 0.7815 | 0.6326 | 0.7954 |
|
| 308 |
+
|
| 309 |
+
|
| 310 |
+
### Framework versions
|
| 311 |
+
|
| 312 |
+
- Transformers 4.44.2
|
| 313 |
+
- Pytorch 2.4.0+cu118
|
| 314 |
+
- Datasets 2.21.0
|
| 315 |
+
- 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:a687ca20c2054f308150a0ab829ce2828494446061aa99e6c13fc6f87f95db6f
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1fb8c3121cf181271c3ddaaae4208b753e2a580b5543387663bd8db5576c5eb
|
| 3 |
+
size 5368
|