metadata
base_model: vinai/bertweet-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bertweet-base_3epoch3
results: []
bertweet-base_3epoch3
This model is a fine-tuned version of vinai/bertweet-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0492
- Accuracy: 0.7450
- F1: 0.4080
- Precision: 0.61
- Recall: 0.3065
- Precision Sarcastic: 0.61
- Recall Sarcastic: 0.3065
- F1 Sarcastic: 0.4080
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 347 | 1.9148 | 0.7205 | 0.4294 | 0.5177 | 0.3668 | 0.5177 | 0.3668 | 0.4294 |
| 0.0342 | 2.0 | 694 | 2.0035 | 0.7450 | 0.4587 | 0.5859 | 0.3769 | 0.5859 | 0.3769 | 0.4587 |
| 0.0213 | 3.0 | 1041 | 2.0492 | 0.7450 | 0.4080 | 0.61 | 0.3065 | 0.61 | 0.3065 | 0.4080 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1