metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: twitter-roberta-base-sentiment
results: []
twitter-roberta-base-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: 0.9462
- Accuracy: 0.7222
- Macro Precision: 0.7068
- Macro Recall: 0.7491
- Macro F1: 0.7246
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro Precision | Macro Recall | Macro F1 |
|---|---|---|---|---|---|---|---|
| 0.9337 | 0.2667 | 1000 | 0.8398 | 0.6273 | 0.6577 | 0.6723 | 0.6322 |
| 0.8101 | 0.5333 | 2000 | 0.7526 | 0.6780 | 0.6598 | 0.7406 | 0.6851 |
| 0.7097 | 0.8 | 3000 | 0.8075 | 0.7068 | 0.6853 | 0.7515 | 0.7081 |
| 0.5513 | 1.0667 | 4000 | 0.8310 | 0.7113 | 0.7007 | 0.7316 | 0.7135 |
| 0.4368 | 1.3333 | 5000 | 0.9000 | 0.7154 | 0.7001 | 0.7487 | 0.7192 |
| 0.4084 | 1.6 | 6000 | 0.9042 | 0.7154 | 0.7035 | 0.7413 | 0.7194 |
| 0.3481 | 1.8667 | 7000 | 0.9868 | 0.7246 | 0.7121 | 0.7441 | 0.7255 |
| 0.3693 | 2.0 | 7500 | 0.9462 | 0.7222 | 0.7068 | 0.7491 | 0.7246 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2