metadata
library_name: transformers
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-tweeteval-distilroberta
results: []
bert-tweeteval-distilroberta
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8631
- Accuracy: 0.7513
- F1: 0.6838
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: 100
- seed: 15179996
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6579 | 1.0 | 204 | 0.6120 | 0.7861 | 0.7276 |
| 0.5403 | 2.0 | 408 | 0.6891 | 0.7380 | 0.6899 |
| 0.3781 | 3.0 | 612 | 0.6893 | 0.7834 | 0.7245 |
| 0.2714 | 4.0 | 816 | 0.8631 | 0.7513 | 0.6838 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2