|
--- |
|
base_model: aubmindlab/bert-base-arabertv02 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: arabert_cross_relevance_task4_fold4 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# arabert_cross_relevance_task4_fold4 |
|
|
|
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2131 |
|
- Qwk: 0.2800 |
|
- Mse: 0.2131 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:| |
|
| No log | 0.0290 | 2 | 1.5877 | 0.0071 | 1.5877 | |
|
| No log | 0.0580 | 4 | 0.7523 | 0.0797 | 0.7523 | |
|
| No log | 0.0870 | 6 | 0.4972 | 0.2325 | 0.4972 | |
|
| No log | 0.1159 | 8 | 0.4973 | 0.2818 | 0.4973 | |
|
| No log | 0.1449 | 10 | 0.3782 | 0.2548 | 0.3782 | |
|
| No log | 0.1739 | 12 | 0.3328 | 0.2641 | 0.3328 | |
|
| No log | 0.2029 | 14 | 0.2810 | 0.2677 | 0.2810 | |
|
| No log | 0.2319 | 16 | 0.2749 | 0.2717 | 0.2749 | |
|
| No log | 0.2609 | 18 | 0.2745 | 0.2169 | 0.2745 | |
|
| No log | 0.2899 | 20 | 0.2605 | 0.2602 | 0.2605 | |
|
| No log | 0.3188 | 22 | 0.2453 | 0.2528 | 0.2453 | |
|
| No log | 0.3478 | 24 | 0.2442 | 0.2459 | 0.2442 | |
|
| No log | 0.3768 | 26 | 0.2468 | 0.2763 | 0.2468 | |
|
| No log | 0.4058 | 28 | 0.2595 | 0.2864 | 0.2595 | |
|
| No log | 0.4348 | 30 | 0.2694 | 0.2852 | 0.2694 | |
|
| No log | 0.4638 | 32 | 0.2515 | 0.2790 | 0.2515 | |
|
| No log | 0.4928 | 34 | 0.2280 | 0.3189 | 0.2280 | |
|
| No log | 0.5217 | 36 | 0.2522 | 0.4255 | 0.2522 | |
|
| No log | 0.5507 | 38 | 0.2616 | 0.3794 | 0.2616 | |
|
| No log | 0.5797 | 40 | 0.2487 | 0.2990 | 0.2487 | |
|
| No log | 0.6087 | 42 | 0.2345 | 0.2490 | 0.2345 | |
|
| No log | 0.6377 | 44 | 0.2296 | 0.2615 | 0.2296 | |
|
| No log | 0.6667 | 46 | 0.2262 | 0.2654 | 0.2262 | |
|
| No log | 0.6957 | 48 | 0.2230 | 0.2654 | 0.2230 | |
|
| No log | 0.7246 | 50 | 0.2198 | 0.2691 | 0.2198 | |
|
| No log | 0.7536 | 52 | 0.2182 | 0.2728 | 0.2182 | |
|
| No log | 0.7826 | 54 | 0.2166 | 0.2763 | 0.2166 | |
|
| No log | 0.8116 | 56 | 0.2162 | 0.2763 | 0.2162 | |
|
| No log | 0.8406 | 58 | 0.2158 | 0.2798 | 0.2158 | |
|
| No log | 0.8696 | 60 | 0.2144 | 0.2798 | 0.2144 | |
|
| No log | 0.8986 | 62 | 0.2129 | 0.2798 | 0.2129 | |
|
| No log | 0.9275 | 64 | 0.2125 | 0.2763 | 0.2125 | |
|
| No log | 0.9565 | 66 | 0.2128 | 0.2728 | 0.2128 | |
|
| No log | 0.9855 | 68 | 0.2131 | 0.2800 | 0.2131 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
