metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: Distilbert-finetuned-IMDB
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.9066666666666666
- name: F1
type: f1
value: 0.9065709953659213
Distilbert-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: 0.2736
- Accuracy: 0.9067
- F1: 0.9066
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5314 | 1.0 | 40 | 0.3674 | 0.8453 | 0.8431 |
| 0.2634 | 2.0 | 80 | 0.2709 | 0.888 | 0.8876 |
| 0.1826 | 3.0 | 120 | 0.2656 | 0.8933 | 0.8930 |
| 0.1433 | 4.0 | 160 | 0.2822 | 0.8893 | 0.8890 |
| 0.1062 | 5.0 | 200 | 0.2736 | 0.9067 | 0.9066 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1