Downloads · 30 days
23
9% of all-time downloads
add_BERT_48_qnli
gokuls/add_BERT_48_qnli
add_BERT_48_qnli 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
254
Public
Repo size
3.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin467 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Jun 15, 2023
- Updated
- Jun 15, 2023
- SHA
- ee20d0fd
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. -->
add_BERT_48_qnli
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new_48 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6899
- Accuracy: 0.5263
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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6959 | 1.0 | 819 | 0.6933 | 0.5103 |
| 0.6945 | 2.0 | 1638 | 0.6917 | 0.4946 |
| 0.6938 | 3.0 | 2457 | 0.6899 | 0.5263 |
| 0.6925 | 4.0 | 3276 | 0.6903 | 0.5318 |
| 0.6961 | 5.0 | 4095 | 0.6940 | 0.5222 |
| 0.6929 | 6.0 | 4914 | 0.6914 | 0.5252 |
| 0.6922 | 7.0 | 5733 | 0.6921 | 0.5043 |
| 0.692 | 8.0 | 6552 | 0.6904 | 0.5303 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- hybridbert
- Languages
- en
- Created
- Jun 15, 2023
- Updated
- Jun 15, 2023