metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sentiment-analyzer
results: []
datasets:
- stanfordnlp/imdb
language:
- en
pipeline_tag: text-classification
sentiment-analyzer
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1976
- Accuracy: 0.9306
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: 32
- eval_batch_size: 32
- 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
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2850 | 1.0 | 782 | 0.1937 | 0.925 |
| 0.1412 | 2.0 | 1564 | 0.1976 | 0.9306 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2