Downloads · 30 days
5
2% of all-time downloads
minilm-finetuned-emotion
Zhichao-W/minilm-finetuned-emotion
minilm-finetuned-emotion is a text classification model from Zhichao-W. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
303
Public
Repo size
534 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin134 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Jun 14, 2023
- Updated
- Jun 14, 2023
- SHA
- 535a5be2
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. -->
minilm-finetuned-emotion
This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4243
- F1: 0.9043
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: 64
- eval_batch_size: 64
- 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 | F1 |
|---|---|---|---|---|
| 1.3683 | 1.0 | 250 | 1.0425 | 0.5804 |
| 0.8949 | 2.0 | 500 | 0.7223 | 0.7873 |
| 0.6448 | 3.0 | 750 | 0.5382 | 0.8796 |
| 0.4985 | 4.0 | 1000 | 0.4578 | 0.8987 |
| 0.4346 | 5.0 | 1250 | 0.4243 | 0.9043 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Jun 14, 2023
- Updated
- Jun 14, 2023