|
--- |
|
license: apache-2.0 |
|
base_model: riotu-lab/ArabianGPT-03B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
- rouge |
|
model-index: |
|
- name: res_nw_yem_03 |
|
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. --> |
|
|
|
# res_nw_yem_03 |
|
|
|
This model is a fine-tuned version of [riotu-lab/ArabianGPT-03B](https://huggingface.co/riotu-lab/ArabianGPT-03B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3767 |
|
- Bleu: 0.4279 |
|
- Rouge1: 0.6599 |
|
- Rouge2: 0.3971 |
|
- Rougel: 0.6585 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 20.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:| |
|
| 4.4383 | 1.0 | 153 | 0.7436 | 0.0155 | 0.4698 | 0.1921 | 0.4693 | |
|
| 0.4733 | 2.0 | 306 | 0.3933 | 0.3967 | 0.5938 | 0.3154 | 0.5909 | |
|
| 0.2714 | 3.0 | 459 | 0.3767 | 0.4279 | 0.6599 | 0.3971 | 0.6585 | |
|
| 0.1837 | 4.0 | 612 | 0.3863 | 0.4380 | 0.6762 | 0.4184 | 0.6726 | |
|
| 0.129 | 5.0 | 765 | 0.3835 | 0.4536 | 0.6994 | 0.4576 | 0.6968 | |
|
| 0.0999 | 6.0 | 918 | 0.3938 | 0.4493 | 0.6979 | 0.4541 | 0.6936 | |
|
| 0.0844 | 7.0 | 1071 | 0.3971 | 0.4623 | 0.7107 | 0.4766 | 0.7069 | |
|
| 0.0741 | 8.0 | 1224 | 0.3947 | 0.4715 | 0.7229 | 0.4895 | 0.7189 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
