Downloads · 30 days
10
3% of all-time downloads
longformer-medqa-usmle-nocontext
GBaker/longformer-medqa-usmle-nocontext
longformer-medqa-usmle-nocontext is a multiple choice model from GBaker. Use it for the multiple choice task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
310
Public
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin595 MB · 99%
At a glance
- Task
- multiple choice
- Library
- transformers
- Model type
- longformer
- Access
- Public
- Created
- Jan 24, 2023
- Updated
- Jan 25, 2023
- SHA
- d53e07c3
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. -->
longformer_model_nocontext
This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3861
- Accuracy: 0.2467
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 | Accuracy |
|---|---|---|---|---|
| 1.3896 | 1.0 | 636 | 1.3861 | 0.2482 |
| 1.39 | 2.0 | 1272 | 1.3860 | 0.2459 |
| 1.3885 | 3.0 | 1908 | 1.3861 | 0.2467 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- multiple choice
- Library
- transformers
- Type
- longformer
- Created
- Jan 24, 2023
- Updated
- Jan 25, 2023