Downloads · 30 days
2
7% of all-time downloads
res_nw_lev_1.5
nlparabic/res_nw_lev_1.5
res_nw_lev_1.5 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
27
Public
Parameters
1.6B
75.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- gpt2
- Access
- Public
- Created
- Sep 2, 2024
- Updated
- Sep 3, 2024
- SHA
- d4a73f3e
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_lev_1.5
This model is a fine-tuned version of riotu-lab/ArabianGPT-1.5B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4514
- Bleu: 0.4604
- Rouge1: 0.6935
- Rouge2: 0.4679
- Rougel: 0.6923
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 |
|---|---|---|---|---|---|---|---|
| 0.9723 | 1.0 | 5062 | 0.5929 | 0.3381 | 0.5352 | 0.2532 | 0.5335 |
| 0.5372 | 2.0 | 10124 | 0.5345 | 0.3565 | 0.5789 | 0.3004 | 0.5771 |
| 0.4562 | 3.0 | 15186 | 0.5011 | 0.3724 | 0.6090 | 0.3366 | 0.6075 |
| 0.3888 | 4.0 | 20248 | 0.4795 | 0.3896 | 0.6308 | 0.3647 | 0.6295 |
| 0.3295 | 5.0 | 25310 | 0.4640 | 0.4085 | 0.6529 | 0.3976 | 0.6516 |
| 0.2783 | 6.0 | 30372 | 0.4554 | 0.4323 | 0.6740 | 0.4326 | 0.6729 |
| 0.2359 | 7.0 | 35434 | 0.4514 | 0.4604 | 0.6935 | 0.4679 | 0.6923 |
| 0.2013 | 8.0 | 40496 | 0.4540 | 0.4853 | 0.7055 | 0.4938 | 0.7045 |
| 0.1741 | 9.0 | 45558 | 0.4603 | 0.5067 | 0.7139 | 0.5122 | 0.7130 |
| 0.1531 | 10.0 | 50620 | 0.4672 | 0.5228 | 0.7191 | 0.5235 | 0.7181 |
| 0.1373 | 11.0 | 55682 | 0.4777 | 0.5307 | 0.7205 | 0.5283 | 0.7197 |
| 0.1256 | 12.0 | 60744 | 0.4877 | 0.5358 | 0.7214 | 0.5308 | 0.7204 |
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 2, 2024
- Updated
- Sep 3, 2024