metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: sentiment_analysis
results: []
sentiment_analysis
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8114
- F1 Score: 0.7322
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
- 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 | F1 Score |
|---|---|---|---|---|
| 0.7577 | 1.0 | 1000 | 0.7996 | 0.6603 |
| 0.7168 | 2.0 | 2000 | 0.7362 | 0.6627 |
| 0.7201 | 3.0 | 3000 | 0.7231 | 0.6675 |
| 0.6752 | 4.0 | 4000 | 0.7051 | 0.6970 |
| 0.6374 | 5.0 | 5000 | 0.7167 | 0.7007 |
| 0.6288 | 6.0 | 6000 | 0.7278 | 0.7193 |
| 0.5579 | 7.0 | 7000 | 0.8242 | 0.7190 |
| 0.5485 | 8.0 | 8000 | 0.7587 | 0.7291 |
| 0.5309 | 9.0 | 9000 | 0.7876 | 0.7269 |
| 0.4767 | 10.0 | 10000 | 0.8114 | 0.7322 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3