metadata
library_name: transformers
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: finetuning-sentiment-model-youtube-samples
results: []
finetuning-sentiment-model-youtube-samples
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9901
- Accuracy: 0.8418
- F1: 0.8381
- Precision: 0.8418
- Recall: 0.8418
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6387 | 1.0 | 22 | 0.6277 | 0.7062 | 0.7069 | 0.7062 | 0.7062 |
| 0.3508 | 2.0 | 44 | 0.4970 | 0.8023 | 0.8043 | 0.8023 | 0.8023 |
| 0.1586 | 3.0 | 66 | 0.8574 | 0.7910 | 0.7829 | 0.7910 | 0.7910 |
| 0.0663 | 4.0 | 88 | 0.7822 | 0.8079 | 0.8086 | 0.8079 | 0.8079 |
| 0.0351 | 5.0 | 110 | 0.8371 | 0.8305 | 0.8188 | 0.8305 | 0.8305 |
| 0.0274 | 6.0 | 132 | 0.8634 | 0.8475 | 0.8423 | 0.8475 | 0.8475 |
| 0.0049 | 7.0 | 154 | 0.9682 | 0.8079 | 0.8023 | 0.8079 | 0.8079 |
| 0.0015 | 8.0 | 176 | 0.9604 | 0.8362 | 0.8348 | 0.8362 | 0.8362 |
| 0.0007 | 9.0 | 198 | 0.9754 | 0.8418 | 0.8381 | 0.8418 | 0.8418 |
| 0.0011 | 10.0 | 220 | 0.9901 | 0.8418 | 0.8381 | 0.8418 | 0.8418 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3