metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: roberta-base_legal_nli_finetuned
results: []
roberta-base_legal_nli_finetuned
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7710
- Accuracy: 0.8298
- Precision: 0.8442
- Recall: 0.8324
- F1: 0.8363
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 28 | 1.0979 | 0.3085 | 0.1028 | 0.3333 | 0.1572 |
| No log | 2.0 | 56 | 1.0881 | 0.3085 | 0.1028 | 0.3333 | 0.1572 |
| No log | 3.0 | 84 | 0.4565 | 0.8404 | 0.8412 | 0.8437 | 0.8423 |
| No log | 4.0 | 112 | 0.4155 | 0.8617 | 0.8651 | 0.8652 | 0.8650 |
| No log | 5.0 | 140 | 0.5513 | 0.8085 | 0.8386 | 0.8130 | 0.8167 |
| No log | 6.0 | 168 | 0.6108 | 0.8723 | 0.8783 | 0.8750 | 0.8765 |
| No log | 7.0 | 196 | 0.6971 | 0.8298 | 0.8442 | 0.8324 | 0.8363 |
| No log | 8.0 | 224 | 0.6893 | 0.8298 | 0.8442 | 0.8324 | 0.8363 |
| No log | 9.0 | 252 | 0.7855 | 0.8298 | 0.8442 | 0.8324 | 0.8363 |
| No log | 10.0 | 280 | 0.7710 | 0.8298 | 0.8442 | 0.8324 | 0.8363 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1