Downloads · 30 days
4
21% of all-time downloads
res_nw_eg
nlparabic/res_nw_eg
res_nw_eg 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
19
Public
Parameters
135M
11.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors539 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- gpt2
- Access
- Public
- Created
- Aug 31, 2024
- Updated
- Sep 1, 2024
- SHA
- 28797498
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_eg
This model is a fine-tuned version of riotu-lab/ArabianGPT-01B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8298
- Bleu: 0.3390
- Rouge1: 0.5962
- Rouge2: 0.3298
- Rougel: 0.5921
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 |
|---|---|---|---|---|---|---|---|
| 1.1362 | 1.0 | 7105 | 0.9123 | 0.3024 | 0.5276 | 0.2508 | 0.5228 |
| 0.7501 | 2.0 | 14210 | 0.8436 | 0.3299 | 0.5754 | 0.3055 | 0.5713 |
| 0.6462 | 3.0 | 21315 | 0.8298 | 0.3390 | 0.5962 | 0.3298 | 0.5921 |
| 0.5705 | 4.0 | 28420 | 0.8328 | 0.3444 | 0.6048 | 0.3412 | 0.6011 |
| 0.5087 | 5.0 | 35525 | 0.8406 | 0.3480 | 0.6133 | 0.3512 | 0.6096 |
| 0.4559 | 6.0 | 42630 | 0.8647 | 0.3478 | 0.6133 | 0.3520 | 0.6094 |
| 0.4104 | 7.0 | 49735 | 0.8770 | 0.3485 | 0.6148 | 0.3533 | 0.6107 |
| 0.3708 | 8.0 | 56840 | 0.9003 | 0.3478 | 0.6166 | 0.3549 | 0.6125 |
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
- Aug 31, 2024
- Updated
- Sep 1, 2024