Downloads · 30 days
5
8% of all-time downloads
bert-base-uncased-finetuned-imdb-sentiment
erikdj/bert-base-uncased-finetuned-imdb-sentiment
bert-base-uncased-finetuned-imdb-sentiment is a text classification model from erikdj. 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
62
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 1, 2025
- Updated
- Oct 1, 2025
- SHA
- b88c7cbd
Try a prompt
Base models
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. -->
results_bert
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2509
- Accuracy: 0.9428
- Precision: 0.9406
- Recall: 0.9453
- F1: 0.9429
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2409 | 1.0 | 1563 | 0.2302 | 0.9120 | 0.9635 | 0.8566 | 0.9069 |
| 0.1351 | 2.0 | 3126 | 0.2285 | 0.9312 | 0.9618 | 0.898 | 0.9288 |
| 0.0595 | 3.0 | 4689 | 0.2509 | 0.9428 | 0.9406 | 0.9453 | 0.9429 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.8.0+cu129
- Datasets 4.1.1
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Oct 1, 2025
- Updated
- Oct 1, 2025