Downloads · 30 days
12
40% of all-time downloads
nw_egy
nlparabic/nw_egy
nw_egy 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
30
Public
Parameters
135M
1.6 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 25, 2024
- Updated
- Aug 25, 2024
- SHA
- 1325fe54
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. -->
nw_egy
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: 2.5201
- Bleu: 0.2511
- Rouge1: 0.4534
- Rouge2: 0.2137
- Rougel: 0.3984
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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|---|
| 4.0723 | 1.0 | 442 | 2.9581 | 0.2228 | 0.3913 | 0.1648 | 0.3201 |
| 2.8055 | 2.0 | 884 | 2.6063 | 0.2415 | 0.4347 | 0.1971 | 0.3777 |
| 2.5505 | 3.0 | 1326 | 2.5201 | 0.2511 | 0.4534 | 0.2137 | 0.3984 |
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 25, 2024
- Updated
- Aug 25, 2024