Downloads · 30 days
14
3% of all-time downloads
distilbert_sa_GLUE_Experiment_logit_kd_pretrain_rte
gokuls/distilbert_sa_GLUE_Experiment_logit_kd_pretrain_rte
distilbert_sa_GLUE_Experiment_logit_kd_pretrain_rte 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
417
Public
Repo size
804 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Jan 30, 2023
- Updated
- Jan 30, 2023
- SHA
- aa0bdd11
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. -->
distilbert_sa_GLUE_Experiment_logit_kd_pretrain_rte
This model is a fine-tuned version of gokuls/distilbert_sa_pre-training-complete on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.4152
- Accuracy: 0.4838
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: 256
- eval_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4259 | 1.0 | 10 | 0.4215 | 0.4729 |
| 0.4131 | 2.0 | 20 | 0.4219 | 0.4729 |
| 0.4029 | 3.0 | 30 | 0.4152 | 0.4838 |
| 0.3796 | 4.0 | 40 | 0.4234 | 0.5090 |
| 0.3551 | 5.0 | 50 | 0.4266 | 0.4982 |
| 0.3192 | 6.0 | 60 | 0.4537 | 0.5740 |
| 0.2954 | 7.0 | 70 | 0.4482 | 0.5415 |
| 0.2822 | 8.0 | 80 | 0.4573 | 0.5560 |
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
- distilbert
- License
- apache-2.0
- Languages
- en
- Created
- Jan 30, 2023
- Updated
- Jan 30, 2023