Downloads · 30 days
5
10% of all-time downloads
qa_kor_hospital_2
idah4/qa_kor_hospital_2
qa_kor_hospital_2 is a machine learning model from idah4. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
124M
6.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors496 MB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- bart
- Access
- Public
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024
- SHA
- eb03bb9c
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. -->
qa_kor_hospital_2
This model is a fine-tuned version of hyunwoongko/kobart on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1627
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.11 | 100 | 1.7331 |
| No log | 0.21 | 200 | 1.4674 |
| No log | 0.32 | 300 | 1.3987 |
| No log | 0.42 | 400 | 1.3671 |
| 2.0632 | 0.53 | 500 | 1.4153 |
| 2.0632 | 0.63 | 600 | 1.3083 |
| 2.0632 | 0.74 | 700 | 1.2721 |
| 2.0632 | 0.85 | 800 | 1.2572 |
| 2.0632 | 0.95 | 900 | 1.2314 |
| 1.3262 | 1.06 | 1000 | 1.2468 |
| 1.3262 | 1.16 | 1100 | 1.2230 |
| 1.3262 | 1.27 | 1200 | 1.2158 |
| 1.3262 | 1.37 | 1300 | 1.2019 |
| 1.3262 | 1.48 | 1400 | 1.2011 |
| 1.1014 | 1.59 | 1500 | 1.1909 |
| 1.1014 | 1.69 | 1600 | 1.1768 |
| 1.1014 | 1.8 | 1700 | 1.1648 |
| 1.1014 | 1.9 | 1800 | 1.1608 |
| 1.1014 | 2.01 | 1900 | 1.1736 |
| 1.0434 | 2.11 | 2000 | 1.1865 |
| 1.0434 | 2.22 | 2100 | 1.1853 |
| 1.0434 | 2.33 | 2200 | 1.1890 |
| 1.0434 | 2.43 | 2300 | 1.1765 |
| 1.0434 | 2.54 | 2400 | 1.1696 |
| 0.8701 | 2.64 | 2500 | 1.1720 |
| 0.8701 | 2.75 | 2600 | 1.1611 |
| 0.8701 | 2.85 | 2700 | 1.1641 |
| 0.8701 | 2.96 | 2800 | 1.1627 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- transformers
- Type
- bart
- License
- mit
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024