Downloads · 30 days
6
19% of all-time downloads
res_nw_arabiangpt0.3
nlparabic/res_nw_arabiangpt0.3
res_nw_arabiangpt0.3 is a machine learning model from nlparabic. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
31
Public
Parameters
369M
11.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- gpt2
- Access
- Public
- Created
- Sep 28, 2024
- Updated
- Oct 1, 2024
- SHA
- bc0f9640
Base models
Model card
From the Hugging Face model README
<!-- 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_arabiangpt0.3
This model is a fine-tuned version of riotu-lab/ArabianGPT-03B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0679
- Bleu: 0.1681
- Rouge1: 0.5343
- Rouge2: 0.3158
- Rougel: 0.5319
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0845 | 1.0 | 33752 | 0.0709 | 0.1360 | 0.4841 | 0.2595 | 0.4811 |
| 0.0638 | 2.0 | 67504 | 0.0683 | 0.1557 | 0.5166 | 0.2948 | 0.5140 |
| 0.0546 | 3.0 | 101256 | 0.0679 | 0.1681 | 0.5343 | 0.3158 | 0.5319 |
| 0.0468 | 4.0 | 135008 | 0.0689 | 0.1830 | 0.5477 | 0.3320 | 0.5452 |
| 0.0401 | 5.0 | 168760 | 0.0706 | 0.1941 | 0.5549 | 0.3422 | 0.5527 |
| 0.0345 | 6.0 | 202512 | 0.0734 | 0.2016 | 0.5580 | 0.3486 | 0.5558 |
| 0.0302 | 7.0 | 236264 | 0.0769 | 0.2083 | 0.5600 | 0.3535 | 0.5577 |
| 0.0269 | 8.0 | 270016 | 0.0797 | 0.2112 | 0.5592 | 0.3546 | 0.5569 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Type
- gpt2
- License
- apache-2.0
- Created
- Sep 28, 2024
- Updated
- Oct 1, 2024