Downloads · 30 days
21
5% of all-time downloads
mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_qnli
gokuls/mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_qnli
mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
443
Public
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin99.8 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- mobilebert
- Access
- Public
- Created
- Jan 29, 2023
- Updated
- Jan 30, 2023
- SHA
- 0ff6752b
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. -->
mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_qnli
This model is a fine-tuned version of gokuls/mobilebert_sa_pre-training-complete on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.2158
- Accuracy: 0.8984
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: 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 |
|---|---|---|---|---|
| 1.1418 | 1.0 | 819 | 1.0623 | 0.5054 |
| 1.1397 | 2.0 | 1638 | 1.0617 | 0.5054 |
| 1.1439 | 3.0 | 2457 | 1.0634 | 0.5054 |
| 1.1397 | 4.0 | 3276 | 1.0635 | 0.5054 |
| 1.14 | 5.0 | 4095 | 1.0643 | 0.5054 |
| 1.1399 | 6.0 | 4914 | 1.0611 | 0.5054 |
| 1.14 | 7.0 | 5733 | 1.0625 | 0.5054 |
| 1.0013 | 8.0 | 6552 | 0.3801 | 0.8420 |
| 0.3353 | 9.0 | 7371 | 0.2163 | 0.9030 |
| 0.2165 | 10.0 | 8190 | 0.2158 | 0.8984 |
| 0.1593 | 11.0 | 9009 | 0.2205 | 0.9057 |
| 0.126 | 12.0 | 9828 | 0.2291 | 0.9077 |
| 0.1049 | 13.0 | 10647 | 0.2323 | 0.9072 |
| 0.0903 | 14.0 | 11466 | 0.2676 | 0.8984 |
| 0.0819 | 15.0 | 12285 | 0.2377 | 0.9006 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- mobilebert
- License
- apache-2.0
- Languages
- en
- Created
- Jan 29, 2023
- Updated
- Jan 30, 2023