Downloads · 30 days
12
23% of all-time downloads
small-mlm-glue-sst2-target-glue-mnli
muhtasham/small-mlm-glue-sst2-target-glue-mnli
small-mlm-glue-sst2-target-glue-mnli is a text classification model from muhtasham. 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
53
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin115 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jan 14, 2023
- Updated
- Jan 14, 2023
- SHA
- 6019e714
Try a prompt
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. -->
small-mlm-glue-sst2-target-glue-mnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6528
- Accuracy: 0.7271
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9063 | 0.04 | 500 | 0.8249 | 0.6370 |
| 0.8116 | 0.08 | 1000 | 0.7813 | 0.6619 |
| 0.7724 | 0.12 | 1500 | 0.7504 | 0.6764 |
| 0.7489 | 0.16 | 2000 | 0.7261 | 0.6908 |
| 0.7413 | 0.2 | 2500 | 0.7141 | 0.6900 |
| 0.7312 | 0.24 | 3000 | 0.7088 | 0.6972 |
| 0.7146 | 0.29 | 3500 | 0.6805 | 0.7127 |
| 0.7041 | 0.33 | 4000 | 0.6703 | 0.7164 |
| 0.6815 | 0.37 | 4500 | 0.6674 | 0.7241 |
| 0.6828 | 0.41 | 5000 | 0.6528 | 0.7271 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jan 14, 2023
- Updated
- Jan 14, 2023