metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: model
results: []
model
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0309
- Precision: 0.2689
- Recall: 0.2544
- F1: 0.2615
- Accuracy: 0.8742
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1094 | 0.4292 | 100 | 1.8029 | 0.3026 | 0.1599 | 0.2092 | 0.8942 |
| 0.1068 | 0.8584 | 200 | 1.7311 | 0.2883 | 0.2617 | 0.2744 | 0.8789 |
| 0.059 | 1.2876 | 300 | 2.0629 | 0.3091 | 0.2212 | 0.2579 | 0.8886 |
| 0.0713 | 1.7167 | 400 | 2.5245 | 0.3529 | 0.1308 | 0.1909 | 0.9029 |
| 0.0634 | 2.1459 | 500 | 2.3395 | 0.3122 | 0.1786 | 0.2272 | 0.8937 |
| 0.0572 | 2.5751 | 600 | 2.2058 | 0.2864 | 0.2347 | 0.2580 | 0.8819 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0