Downloads · 30 days
10
20% of all-time downloads
HBERTv1_48_L8_H256_A4_emotion
gokuls/HBERTv1_48_L8_H256_A4_emotion
HBERTv1_48_L8_H256_A4_emotion is a text classification model from gokuls. 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
50
Public
Repo size
424 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin60.6 MB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Oct 4, 2023
- Updated
- Oct 4, 2023
- SHA
- fd1e8c08
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. -->
HBERTv1_48_L8_H256_A4_emotion
This model is a fine-tuned version of gokuls/HBERTv1_48_L8_H256_A4 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4048
- Accuracy: 0.878
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.393 | 1.0 | 250 | 1.1681 | 0.561 |
| 1.004 | 2.0 | 500 | 0.8514 | 0.6875 |
| 0.6992 | 3.0 | 750 | 0.6116 | 0.806 |
| 0.4951 | 4.0 | 1000 | 0.5253 | 0.841 |
| 0.3991 | 5.0 | 1250 | 0.4786 | 0.8585 |
| 0.3368 | 6.0 | 1500 | 0.4240 | 0.868 |
| 0.2891 | 7.0 | 1750 | 0.4324 | 0.8715 |
| 0.2554 | 8.0 | 2000 | 0.4005 | 0.875 |
| 0.2302 | 9.0 | 2250 | 0.4080 | 0.874 |
| 0.2121 | 10.0 | 2500 | 0.4048 | 0.878 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0
- Task
- Text Classification
- Library
- transformers
- Type
- hybridbert
- Created
- Oct 4, 2023
- Updated
- Oct 4, 2023