metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: emotion-analysis-trans
results: []
emotion-analysis-trans
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0950
- Accuracy: 0.9429
- F1: 0.9433
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0921 | 1.0 | 5211 | 0.0895 | 0.9418 | 0.9398 |
| 0.0868 | 2.0 | 10422 | 0.0868 | 0.9420 | 0.9407 |
| 0.0824 | 3.0 | 15633 | 0.0896 | 0.9425 | 0.9439 |
| 0.0791 | 4.0 | 20844 | 0.0950 | 0.9429 | 0.9433 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2