metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: twitter-data-pysentimiento-robertuito-sentiment-finetuned-memes
results: []
twitter-data-pysentimiento-robertuito-sentiment-finetuned-memes
This model is a fine-tuned version of pysentimiento/robertuito-sentiment-analysis on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2563
- Accuracy: 0.9262
- Precision: 0.9271
- Recall: 0.9262
- F1: 0.9263
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3641 | 1.0 | 1762 | 0.3197 | 0.8999 | 0.9001 | 0.8999 | 0.8995 |
| 0.272 | 2.0 | 3524 | 0.2723 | 0.9171 | 0.9181 | 0.9171 | 0.9171 |
| 0.2451 | 3.0 | 5286 | 0.2633 | 0.9224 | 0.9226 | 0.9224 | 0.9223 |
| 0.2084 | 4.0 | 7048 | 0.2518 | 0.9256 | 0.9270 | 0.9256 | 0.9257 |
| 0.199 | 5.0 | 8810 | 0.2545 | 0.9268 | 0.9277 | 0.9268 | 0.9269 |
| 0.1926 | 6.0 | 10572 | 0.2563 | 0.9262 | 0.9271 | 0.9262 | 0.9263 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1