Downloads · 30 days
66
1% of all-time downloads
distilbert-base-uncased-finetuned-imdb
huggingface-course/distilbert-base-uncased-finetuned-imdb
distilbert-base-uncased-finetuned-imdb is a fill-mask model from huggingface-course. Use it when you need the model to fill a missing word. 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
12.4K
Public
Repo size
899 MB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.h5363 MB · 57%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Nov 11, 2021
- SHA
- 10abb8b2
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-base-uncased-finetuned-imdb
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 2.4264
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.708 | 1.0 | 157 | 2.4715 |
| 2.5627 | 2.0 | 314 | 2.4145 |
| 2.5385 | 3.0 | 471 | 2.4451 |
Framework versions
- Transformers 4.12.0.dev0
- Pytorch 1.9.1+cu111
- Datasets 1.12.2.dev0
- Tokenizers 0.10.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- Nov 11, 2021