metadata
license: mit
base_model: LIAMF-USP/roberta-large-finetuned-race
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: test-roberta-finetuned-mathqa
results: []
test-roberta-finetuned-mathqa
This model is a fine-tuned version of LIAMF-USP/roberta-large-finetuned-race on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6094
- Accuracy: 0.2007
- F1: 0.1089
- Precision: 0.1782
- Recall: 0.1954
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: 10
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.6207 | 1.0 | 2970 | 1.6094 | 0.2064 | 0.0714 | 0.1694 | 0.2010 |
| 1.6136 | 2.0 | 5940 | 1.6094 | 0.2064 | 0.0951 | 0.1934 | 0.2020 |
| 1.6161 | 3.0 | 8910 | 1.6094 | 0.2007 | 0.1089 | 0.1782 | 0.1954 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1