Downloads · 30 days
13
4% of all-time downloads
roberta-large-finetuned-cosmos
Benlitzen43/roberta-large-finetuned-cosmos
roberta-large-finetuned-cosmos is a multiple choice model from Benlitzen43. 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. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
306
Public
Repo size
64 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.4 GB · 100%
At a glance
- Task
- multiple choice
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Nov 22, 2023
- Updated
- Nov 25, 2023
- SHA
- 0ecff3be
Base models
Datasets
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. -->
roberta-large-finetuned-cosmos
This model is a fine-tuned version of roberta-large on the cosmos_qa dataset. It achieves the following results on the evaluation set:
- Loss: 1.3863
- Accuracy: 0.2533
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: 2
- eval_batch_size: 2
- 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 | Accuracy |
|---|---|---|---|---|
| 1.39 | 1.0 | 12631 | 1.3863 | 0.2586 |
| 1.3956 | 2.0 | 25262 | 1.3863 | 0.2563 |
| 1.3902 | 3.0 | 37893 | 1.3863 | 0.2533 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Task
- multiple choice
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Nov 22, 2023
- Updated
- Nov 25, 2023