Downloads · 30 days
25
33% of all-time downloads
opt-125m-finetuned-mnli
velaa/opt-125m-finetuned-mnli
opt-125m-finetuned-mnli is a text classification model from velaa. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
76
Public
Parameters
125M
10.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors503 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- other
- Model type
- opt
- Access
- Public
- Created
- Nov 30, 2023
- Updated
- Dec 3, 2023
- SHA
- a756eb65
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. -->
opt-125m-finetuned-mnli
This model is a fine-tuned version of facebook/opt-125m on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.7566
- Accuracy: 0.3552
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-06
- 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: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0726 | 1.0 | 1 | 1.7835 | 0.3536 |
| 0.1157 | 2.0 | 2 | 1.7566 | 0.3552 |
| 0.0624 | 3.0 | 3 | 1.7372 | 0.3548 |
| 0.07 | 4.0 | 4 | 1.7249 | 0.3544 |
| 0.0689 | 5.0 | 5 | 1.7189 | 0.3545 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Text Classification
- Library
- transformers
- Type
- opt
- License
- other
- Created
- Nov 30, 2023
- Updated
- Dec 3, 2023