metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: roberta-base-finetuned-3d-sentiment
results: []
roberta-base-finetuned-3d-sentiment
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6047
- Accuracy: 0.7713
- Precision: 0.7719
- Recall: 0.7713
- F1: 0.7703
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 6381
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.7978 | 1.0 | 1595 | 0.7782 | 0.6953 | 0.7191 | 0.6953 | 0.6926 |
| 0.5526 | 2.0 | 3190 | 0.6951 | 0.7229 | 0.7398 | 0.7229 | 0.7233 |
| 0.4904 | 3.0 | 4785 | 0.6390 | 0.7388 | 0.7530 | 0.7388 | 0.7366 |
| 0.4307 | 4.0 | 6380 | 0.6047 | 0.7713 | 0.7719 | 0.7713 | 0.7703 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3