|
--- |
|
license: apache-2.0 |
|
base_model: riotu-lab/ArabianGPT-03B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
- rouge |
|
model-index: |
|
- name: res_nw_lev_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_lev_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: 0.3660 |
|
- Bleu: 0.4889 |
|
- Rouge1: 0.7442 |
|
- Rouge2: 0.5302 |
|
- Rougel: 0.7434 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:------:| |
|
| 0.6345 | 1.0 | 5062 | 0.4249 | 0.4054 | 0.6718 | 0.4168 | 0.6706 | |
|
| 0.3258 | 2.0 | 10124 | 0.3824 | 0.4443 | 0.7135 | 0.4800 | 0.7124 | |
|
| 0.2266 | 3.0 | 15186 | 0.3660 | 0.4889 | 0.7442 | 0.5302 | 0.7434 | |
|
| 0.1702 | 4.0 | 20248 | 0.3713 | 0.5217 | 0.7592 | 0.5618 | 0.7584 | |
|
| 0.1405 | 5.0 | 25310 | 0.3809 | 0.5411 | 0.7671 | 0.5785 | 0.7663 | |
|
| 0.1253 | 6.0 | 30372 | 0.3939 | 0.5539 | 0.7718 | 0.5899 | 0.7710 | |
|
| 0.1166 | 7.0 | 35434 | 0.3990 | 0.5536 | 0.7745 | 0.5942 | 0.7737 | |
|
| 0.1107 | 8.0 | 40496 | 0.4050 | 0.5608 | 0.7770 | 0.5994 | 0.7763 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
