metadata
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: vinai/bertweet-base
model-index:
- name: daryl_morey_apology
results: []
daryl_morey_apology
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: 0.7634
- Accuracy: 0.7778
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 259 | 0.7589 | 0.7585 |
| 0.8357 | 2.0 | 518 | 0.6771 | 0.7720 |
| 0.8357 | 3.0 | 777 | 0.7151 | 0.7681 |
| 0.4531 | 4.0 | 1036 | 0.7498 | 0.7826 |
| 0.4531 | 5.0 | 1295 | 0.7634 | 0.7778 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2