metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: headlines_news_sentiment_distil
results: []
headlines_news_sentiment_distil
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6265
- Model Preparation Time: 0.0026
- Accuracy: 0.8423
- F1: 0.8423
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | F1 |
|---|---|---|---|---|---|---|
| 0.4834 | 1.0 | 504 | 0.4035 | 0.0026 | 0.8156 | 0.8156 |
| 0.3402 | 2.0 | 1008 | 0.3987 | 0.0026 | 0.8343 | 0.8343 |
| 0.2343 | 3.0 | 1512 | 0.4514 | 0.0026 | 0.8392 | 0.8391 |
| 0.1604 | 4.0 | 2016 | 0.5443 | 0.0026 | 0.8396 | 0.8396 |
| 0.1151 | 5.0 | 2520 | 0.6265 | 0.0026 | 0.8423 | 0.8423 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1