metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: temp_model_output_dir
results: []
temp_model_output_dir
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7204
- Precision: 0.8552
- Recall: 0.8448
- F1: 0.8399
- Accuracy: 0.8448
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: 8.8e-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: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.209 | 1.0 | 756 | 0.7528 | 0.8238 | 0.8130 | 0.8013 | 0.8130 |
| 0.7337 | 2.0 | 1512 | 0.7899 | 0.8209 | 0.8031 | 0.7952 | 0.8031 |
| 0.644 | 3.0 | 2268 | 0.7417 | 0.8394 | 0.8299 | 0.8238 | 0.8299 |
| 0.4777 | 4.0 | 3024 | 0.7204 | 0.8552 | 0.8448 | 0.8399 | 0.8448 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0