metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: finetuning-sentiment-model-3000-samples-5pm
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.88
finetuning-sentiment-model-3000-samples-5pm
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: 0.4325
- Accuracy: 0.88
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 188 | 0.3858 | 0.84 |
| No log | 2.0 | 376 | 0.3146 | 0.8833 |
| 0.2573 | 3.0 | 564 | 0.3938 | 0.8833 |
| 0.2573 | 4.0 | 752 | 0.4325 | 0.88 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1