Downloads · 30 days
9
3% of all-time downloads
bart-base-snli-model3
varun-v-rao/bart-base-snli-model3
bart-base-snli-model3 is a text classification model from varun-v-rao. Use it when you need a label for a piece of text. 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
300
Public
Parameters
140M
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors560 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Jun 19, 2024
- Updated
- Jun 19, 2024
- SHA
- 47f5f2af
Try a prompt
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. -->
bart-base-snli-model3
This model is a fine-tuned version of facebook/bart-base on the snli dataset. It achieves the following results on the evaluation set:
- Loss: 0.2606
- Accuracy: 0.9097
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: 256
- eval_batch_size: 128
- seed: 70
- 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 |
|---|---|---|---|---|
| 0.3738 | 1.0 | 2146 | 0.2868 | 0.8973 |
| 0.3227 | 2.0 | 4292 | 0.2618 | 0.9065 |
| 0.294 | 3.0 | 6438 | 0.2606 | 0.9097 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Text Classification
- Library
- transformers
- Type
- bart
- License
- apache-2.0
- Created
- Jun 19, 2024
- Updated
- Jun 19, 2024