metadata
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: pogny-persona-emotion-bert-finetuning-1
results: []
pogny-persona-emotion-bert-finetuning-1
This model is a fine-tuned version of klue/bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4030
- Accuracy: 0.8256
- F1: 0.8253
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.487 | 1.0 | 4153 | 0.4409 | 0.8322 | 0.8276 |
| 0.374 | 2.0 | 8306 | 0.4491 | 0.8342 | 0.8330 |
| 0.2794 | 3.0 | 12459 | 0.5038 | 0.8338 | 0.8316 |
| 0.1871 | 4.0 | 16612 | 0.6531 | 0.8335 | 0.8322 |
| 0.1428 | 5.0 | 20765 | 0.8888 | 0.8258 | 0.8240 |
| 0.0968 | 6.0 | 24918 | 1.0803 | 0.8186 | 0.8186 |
| 0.076 | 7.0 | 29071 | 1.1708 | 0.8267 | 0.8261 |
| 0.0516 | 8.0 | 33224 | 1.2664 | 0.8270 | 0.8257 |
| 0.0368 | 9.0 | 37377 | 1.3662 | 0.8270 | 0.8264 |
| 0.0233 | 10.0 | 41530 | 1.4030 | 0.8256 | 0.8253 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2