|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilbert-base-uncased |
|
datasets: |
|
- stanfordnlp/imdb |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: distilbert-base-uncased-imdb |
|
results: [] |
|
--- |
|
|
|
# distilbert-base-uncased-imdb |
|
|
|
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co./distilbert/distilbert-base-uncased) on the [imdb](https://huggingface.co./datasets/stanfordnlp/imdb) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4367 |
|
- Accuracy: 0.9327 |
|
- F1: 0.9336 |
|
- Precision: 0.9212 |
|
- Recall: 0.9463 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.2601 | 1.0 | 3125 | 0.3550 | 0.8857 | 0.8744 | 0.9709 | 0.7953 | |
|
| 0.1842 | 2.0 | 6250 | 0.2355 | 0.9327 | 0.9327 | 0.9328 | 0.9326 | |
|
| 0.1191 | 3.0 | 9375 | 0.3287 | 0.9311 | 0.9303 | 0.9417 | 0.9191 | |
|
| 0.0452 | 4.0 | 12500 | 0.4053 | 0.9331 | 0.9337 | 0.9256 | 0.942 | |
|
| 0.0299 | 5.0 | 15625 | 0.4367 | 0.9327 | 0.9336 | 0.9212 | 0.9463 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
