metadata
license: mit
base_model: LIAMF-USP/roberta-large-finetuned-race
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: roberta-large-finetuned-race-finetuned-mathqa
results: []
roberta-large-finetuned-race-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: 1.1282
- Accuracy: 0.5476
- F1: 0.5470
- Precision: 0.5528
- Recall: 0.5444
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: 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 |
|---|---|---|---|---|---|---|---|
| 1.3497 | 1.0 | 3712 | 1.2886 | 0.4659 | 0.4640 | 0.4761 | 0.4609 |
| 1.2074 | 2.0 | 7424 | 1.1684 | 0.5187 | 0.5182 | 0.5253 | 0.5153 |
| 1.0072 | 3.0 | 11136 | 1.1282 | 0.5476 | 0.5470 | 0.5528 | 0.5444 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1