Downloads · 30 days
6
11% of all-time downloads
res_nw_lev_aragpt2-base
nlparabic/res_nw_lev_aragpt2-base
res_nw_lev_aragpt2-base 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
55
Public
Parameters
135M
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors540 MB · 99%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Sep 7, 2024
- Updated
- Sep 8, 2024
- SHA
- eb807b8e
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_aragpt2-base
This model is a fine-tuned version of aubmindlab/aragpt2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0520
- Bleu: 0.1724
- Rouge1: 0.5243
- Rouge2: 0.3044
- Rougel: 0.5218
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 |
|---|---|---|---|---|---|---|---|
| 0.26 | 1.0 | 5062 | 0.0696 | 0.0245 | 0.3013 | 0.0862 | 0.2973 |
| 0.0691 | 2.0 | 10124 | 0.0627 | 0.0520 | 0.3752 | 0.1476 | 0.3720 |
| 0.061 | 3.0 | 15186 | 0.0592 | 0.0728 | 0.4151 | 0.1846 | 0.4119 |
| 0.055 | 4.0 | 20248 | 0.0568 | 0.0853 | 0.4403 | 0.2078 | 0.4371 |
| 0.0501 | 5.0 | 25310 | 0.0552 | 0.1006 | 0.4609 | 0.2304 | 0.4581 |
| 0.0458 | 6.0 | 30372 | 0.0542 | 0.1181 | 0.4821 | 0.2520 | 0.4793 |
| 0.0421 | 7.0 | 35434 | 0.0534 | 0.1341 | 0.4963 | 0.2701 | 0.4938 |
| 0.0389 | 8.0 | 40496 | 0.0527 | 0.1531 | 0.5119 | 0.2877 | 0.5094 |
| 0.036 | 9.0 | 45558 | 0.0520 | 0.1724 | 0.5243 | 0.3044 | 0.5218 |
| 0.0335 | 10.0 | 50620 | 0.0522 | 0.1916 | 0.5355 | 0.3184 | 0.5331 |
| 0.0314 | 11.0 | 55682 | 0.0526 | 0.2161 | 0.5483 | 0.3340 | 0.5464 |
| 0.0295 | 12.0 | 60744 | 0.0531 | 0.2349 | 0.5567 | 0.3463 | 0.5542 |
| 0.0278 | 13.0 | 65806 | 0.0534 | 0.2526 | 0.5650 | 0.3578 | 0.5630 |
| 0.0264 | 14.0 | 70868 | 0.0542 | 0.2696 | 0.5713 | 0.3696 | 0.5696 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Type
- gpt2
- Created
- Sep 7, 2024
- Updated
- Sep 8, 2024