Downloads · 30 days
8
16% of all-time downloads
CliBert-20
hung200504/CliBert-20
CliBert-20 is a question answering model from hung200504. Use it when the input is a question plus a passage. 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
Repo size
1.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin431 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Oct 19, 2023
- Updated
- Oct 19, 2023
- SHA
- a4df8839
Try a prompt
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. -->
CliBert-20
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.9825
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: 2e-05
- 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
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.9707 | 0.09 | 5 | 6.0008 |
| 5.9661 | 0.18 | 10 | 5.9998 |
| 5.9659 | 0.27 | 15 | 5.9987 |
| 5.9441 | 0.36 | 20 | 5.9974 |
| 5.9937 | 0.45 | 25 | 5.9965 |
| 5.9483 | 0.55 | 30 | 5.9953 |
| 5.9214 | 0.64 | 35 | 5.9945 |
| 5.9332 | 0.73 | 40 | 5.9937 |
| 5.9383 | 0.82 | 45 | 5.9926 |
| 5.9223 | 0.91 | 50 | 5.9919 |
| 5.9233 | 1.0 | 55 | 5.9911 |
| 5.8762 | 1.09 | 60 | 5.9905 |
| 5.8967 | 1.18 | 65 | 5.9899 |
| 5.9024 | 1.27 | 70 | 5.9891 |
| 5.9122 | 1.36 | 75 | 5.9885 |
| 5.902 | 1.45 | 80 | 5.9879 |
| 5.874 | 1.55 | 85 | 5.9872 |
| 5.8774 | 1.64 | 90 | 5.9867 |
| 5.8782 | 1.73 | 95 | 5.9862 |
| 5.8664 | 1.82 | 100 | 5.9857 |
| 5.8833 | 1.91 | 105 | 5.9852 |
| 5.8488 | 2.0 | 110 | 5.9848 |
| 5.8747 | 2.09 | 115 | 5.9843 |
| 5.8333 | 2.18 | 120 | 5.9840 |
| 5.8573 | 2.27 | 125 | 5.9837 |
| 5.8398 | 2.36 | 130 | 5.9834 |
| 5.8371 | 2.45 | 135 | 5.9832 |
| 5.8274 | 2.55 | 140 | 5.9831 |
| 5.863 | 2.64 | 145 | 5.9829 |
| 5.8183 | 2.73 | 150 | 5.9827 |
| 5.8448 | 2.82 | 155 | 5.9826 |
| 5.9111 | 2.91 | 160 | 5.9825 |
| 5.8316 | 3.0 | 165 | 5.9825 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Oct 19, 2023
- Updated
- Oct 19, 2023