metadata
library_name: transformers
license: mit
base_model: vinai/bertweet-base
tags:
- generated_from_trainer
model-index:
- name: BERTweet_retrain_2023_01
results: []
BERTweet_retrain_2023_01
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: 3.6244
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: 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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.7841 | 1.0 | 12 | 4.0105 |
| 4.1789 | 2.0 | 24 | 3.7325 |
| 3.9868 | 3.0 | 36 | 3.6244 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.1.0+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0