metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: email_question_extraction
results: []
email_question_extraction
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1217
- Precision: 0.3878
- Recall: 0.7037
- F1: 0.5
- Accuracy: 0.9781
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.398 | 1.0 | 30 | 0.1426 | 0.1493 | 0.3704 | 0.2128 | 0.9649 |
| 0.1839 | 2.0 | 60 | 0.1316 | 0.2453 | 0.4815 | 0.325 | 0.9699 |
| 0.1011 | 3.0 | 90 | 0.1125 | 0.3878 | 0.7037 | 0.5 | 0.9779 |
| 0.1296 | 4.0 | 120 | 0.1217 | 0.3878 | 0.7037 | 0.5 | 0.9781 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.16.0
- Tokenizers 0.15.0