Downloads · 30 days
12
2% of all-time downloads
bigbird-roberta-base-snli
pepa/bigbird-roberta-base-snli
bigbird-roberta-base-snli is a text classification model from pepa. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
482
Public
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin512 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- big_bird
- Access
- Public
- Created
- Oct 23, 2022
- Updated
- Oct 23, 2022
- SHA
- 3cd1108b
Try a prompt
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-roberta-base-snli
This model was trained from scratch on the snli dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2738
- eval_p: 0.9034
- eval_r: 0.9033
- eval_f1: 0.9033
- eval_runtime: 10.9262
- eval_samples_per_second: 899.126
- eval_steps_per_second: 56.195
- step: 0
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: cosine
- num_epochs: 4
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.12.1
- Task
- Text Classification
- Library
- transformers
- Type
- big_bird
- Created
- Oct 23, 2022
- Updated
- Oct 23, 2022