|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: distilbert-base-cased |
|
tags: |
|
- pytorch |
|
- movie-review-sentiment |
|
- BertForSequenceClassification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- matthews_correlation |
|
model-index: |
|
- name: distilbert-base-imdb |
|
results: [] |
|
--- |
|
|
|
<!-- 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-imdb |
|
|
|
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co./distilbert-base-cased) on the imdb dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3490 |
|
- Accuracy: 0.9315 |
|
- Matthews Correlation: 0.8630 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 320 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Matthews Correlation | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------------------:| |
|
| 0.2597 | 1.0 | 1250 | 0.1997 | 0.921 | 0.8426 | |
|
| 0.165 | 2.0 | 2500 | 0.1839 | 0.9291 | 0.8582 | |
|
| 0.0788 | 3.0 | 3750 | 0.2218 | 0.9308 | 0.8617 | |
|
| 0.0235 | 4.0 | 5000 | 0.3490 | 0.9315 | 0.8630 | |
|
| 0.0123 | 5.0 | 6250 | 0.3721 | 0.9314 | 0.8628 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
