Downloads · 30 days
15
7% of all-time downloads
hBERTv1_new_pretrain_48_KD_mrpc
gokuls/hBERTv1_new_pretrain_48_KD_mrpc
hBERTv1_new_pretrain_48_KD_mrpc 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
215
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin481 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Jun 14, 2023
- Updated
- Jun 14, 2023
- SHA
- d455c7b0
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. -->
hBERTv1_new_pretrain_48_KD_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5967
- Accuracy: 0.6912
- F1: 0.7934
- Combined Score: 0.7423
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6601 | 1.0 | 29 | 0.6269 | 0.6593 | 0.7640 | 0.7117 |
| 0.6098 | 2.0 | 58 | 0.5967 | 0.6912 | 0.7934 | 0.7423 |
| 0.5712 | 3.0 | 87 | 0.6127 | 0.6961 | 0.8110 | 0.7535 |
| 0.5155 | 4.0 | 116 | 0.6627 | 0.6618 | 0.7518 | 0.7068 |
| 0.4462 | 5.0 | 145 | 0.7563 | 0.6348 | 0.7129 | 0.6739 |
| 0.358 | 6.0 | 174 | 0.7009 | 0.6397 | 0.7303 | 0.6850 |
| 0.2842 | 7.0 | 203 | 1.0233 | 0.6471 | 0.7517 | 0.6994 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- hybridbert
- Languages
- en
- Created
- Jun 14, 2023
- Updated
- Jun 14, 2023