metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_base_cased_MultiClass_v2
results: []
bert_base_cased_MultiClass_v2
This model is a fine-tuned version of HMEXBI/bert_base_cased_MultiClass on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9806
- Accuracy: 0.8101
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: 32
- 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 |
|---|---|---|---|---|
| 1.1396 | 1.0 | 545 | 0.9023 | 0.7615 |
| 0.6961 | 2.0 | 1090 | 0.8074 | 0.7798 |
| 0.492 | 3.0 | 1635 | 0.8216 | 0.8009 |
| 0.3032 | 4.0 | 2180 | 0.9264 | 0.8018 |
| 0.1898 | 5.0 | 2725 | 0.9806 | 0.8101 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2