|
--- |
|
license: apache-2.0 |
|
base_model: riotu-lab/ArabianGPT-01B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
- rouge |
|
model-index: |
|
- name: res_nw_yem |
|
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 |
|
|
|
This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4655 |
|
- Bleu: 0.3947 |
|
- Rouge1: 0.5909 |
|
- Rouge2: 0.3232 |
|
- Rougel: 0.5882 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:| |
|
| 7.4125 | 1.0 | 153 | 2.3319 | 0.0135 | 0.4043 | 0.1765 | 0.4039 | |
|
| 1.0077 | 2.0 | 306 | 0.5519 | 0.3376 | 0.4747 | 0.1839 | 0.4733 | |
|
| 0.483 | 3.0 | 459 | 0.4973 | 0.3582 | 0.5145 | 0.2200 | 0.5135 | |
|
| 0.3795 | 4.0 | 612 | 0.4739 | 0.3717 | 0.5397 | 0.2524 | 0.5378 | |
|
| 0.2901 | 5.0 | 765 | 0.4691 | 0.3795 | 0.5710 | 0.2927 | 0.5677 | |
|
| 0.2239 | 6.0 | 918 | 0.4655 | 0.3947 | 0.5909 | 0.3232 | 0.5882 | |
|
| 0.1763 | 7.0 | 1071 | 0.4673 | 0.4011 | 0.6047 | 0.3378 | 0.6019 | |
|
| 0.1429 | 8.0 | 1224 | 0.4666 | 0.4085 | 0.6200 | 0.3652 | 0.6168 | |
|
| 0.1206 | 9.0 | 1377 | 0.4765 | 0.4130 | 0.6230 | 0.3707 | 0.6208 | |
|
| 0.1052 | 10.0 | 1530 | 0.4759 | 0.4148 | 0.6233 | 0.3762 | 0.6205 | |
|
| 0.0955 | 11.0 | 1683 | 0.4789 | 0.4179 | 0.6343 | 0.3810 | 0.6307 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
