|
--- |
|
base_model: aubmindlab/bert-base-arabertv02 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: arabert_cross_relevance_task7_fold6 |
|
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_task7_fold6 |
|
|
|
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: 0.2712 |
|
- Qwk: 0.1915 |
|
- Mse: 0.2729 |
|
|
|
## 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 | 0.0328 | 2 | 0.5105 | 0.0254 | 0.5110 | |
|
| No log | 0.0656 | 4 | 0.3468 | 0.1105 | 0.3473 | |
|
| No log | 0.0984 | 6 | 0.3739 | 0.0623 | 0.3733 | |
|
| No log | 0.1311 | 8 | 0.4061 | 0.0623 | 0.4056 | |
|
| No log | 0.1639 | 10 | 0.3781 | 0.0714 | 0.3780 | |
|
| No log | 0.1967 | 12 | 0.3204 | 0.0732 | 0.3208 | |
|
| No log | 0.2295 | 14 | 0.2912 | 0.0732 | 0.2917 | |
|
| No log | 0.2623 | 16 | 0.2824 | 0.0732 | 0.2828 | |
|
| No log | 0.2951 | 18 | 0.2830 | 0.0924 | 0.2833 | |
|
| No log | 0.3279 | 20 | 0.2833 | 0.1116 | 0.2835 | |
|
| No log | 0.3607 | 22 | 0.2895 | 0.1022 | 0.2894 | |
|
| No log | 0.3934 | 24 | 0.3016 | 0.1520 | 0.3014 | |
|
| No log | 0.4262 | 26 | 0.3147 | 0.1588 | 0.3148 | |
|
| No log | 0.4590 | 28 | 0.3134 | 0.1666 | 0.3141 | |
|
| No log | 0.4918 | 30 | 0.3075 | 0.1679 | 0.3086 | |
|
| No log | 0.5246 | 32 | 0.3003 | 0.1679 | 0.3014 | |
|
| No log | 0.5574 | 34 | 0.2952 | 0.1891 | 0.2962 | |
|
| No log | 0.5902 | 36 | 0.2815 | 0.1835 | 0.2826 | |
|
| No log | 0.6230 | 38 | 0.2722 | 0.1890 | 0.2731 | |
|
| No log | 0.6557 | 40 | 0.2672 | 0.1973 | 0.2681 | |
|
| No log | 0.6885 | 42 | 0.2631 | 0.2056 | 0.2644 | |
|
| No log | 0.7213 | 44 | 0.2625 | 0.2056 | 0.2639 | |
|
| No log | 0.7541 | 46 | 0.2628 | 0.1939 | 0.2643 | |
|
| No log | 0.7869 | 48 | 0.2640 | 0.1746 | 0.2657 | |
|
| No log | 0.8197 | 50 | 0.2654 | 0.1804 | 0.2671 | |
|
| No log | 0.8525 | 52 | 0.2657 | 0.2023 | 0.2674 | |
|
| No log | 0.8852 | 54 | 0.2677 | 0.1915 | 0.2694 | |
|
| No log | 0.9180 | 56 | 0.2701 | 0.1915 | 0.2718 | |
|
| No log | 0.9508 | 58 | 0.2708 | 0.1915 | 0.2725 | |
|
| No log | 0.9836 | 60 | 0.2712 | 0.1915 | 0.2729 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
