metadata
base_model: vinai/bertweet-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BERTweet
results: []
BERTweet
This model is a fine-tuned version of vinai/bertweet-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2787
- Accuracy: 0.9025
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: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6 | 0.0994 | 47 | 0.5233 | 0.7661 |
| 0.4809 | 0.1987 | 94 | 0.5148 | 0.7661 |
| 0.4065 | 0.2981 | 141 | 0.4387 | 0.8373 |
| 0.4104 | 0.3975 | 188 | 0.4005 | 0.8553 |
| 0.3518 | 0.4968 | 235 | 0.4069 | 0.8508 |
| 0.3192 | 0.5962 | 282 | 0.3263 | 0.8883 |
| 0.372 | 0.6956 | 329 | 0.3642 | 0.8816 |
| 0.3068 | 0.7949 | 376 | 0.3216 | 0.9003 |
| 0.3238 | 0.8943 | 423 | 0.2972 | 0.9010 |
| 0.3152 | 0.9937 | 470 | 0.2787 | 0.9025 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1