Downloads · 30 days
11
19% of all-time downloads
bigbird_race_1
augmdc/bigbird_race_1
bigbird_race_1 is a multiple choice model from augmdc. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
58
Public
Repo size
4.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin510 MB · 99%
At a glance
- Task
- multiple choice
- Library
- transformers
- License
- apache-2.0
- Model type
- big_bird
- Access
- Public
- Created
- Oct 28, 2023
- Updated
- Jan 8, 2024
- SHA
- 51cf4b8b
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. -->
bigbird_race_1
This model is a fine-tuned version of google/bigbird-roberta-base on the race dataset. It achieves the following results on the evaluation set:
- Loss: 1.0178
- Accuracy: 0.5884
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.313 | 1.0 | 1589 | 1.2015 | 0.4896 |
| 1.0197 | 2.0 | 3178 | 1.0178 | 0.5884 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Task
- multiple choice
- Library
- transformers
- Type
- big_bird
- License
- apache-2.0
- Created
- Oct 28, 2023
- Updated
- Jan 8, 2024