metadata
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: hana-persona-emotion-bert-finetuning-1
results: []
hana-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: 1.5912
- Accuracy: 0.7882
- F1: 0.7869
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 |
---|---|---|---|---|---|
0.5768 | 1.0 | 2284 | 0.5723 | 0.7762 | 0.7712 |
0.451 | 2.0 | 4568 | 0.5570 | 0.7955 | 0.7909 |
0.3514 | 3.0 | 6852 | 0.6058 | 0.7843 | 0.7819 |
0.2273 | 4.0 | 9136 | 0.7584 | 0.7916 | 0.7887 |
0.1727 | 5.0 | 11420 | 0.9155 | 0.7873 | 0.7877 |
0.1271 | 6.0 | 13704 | 1.0717 | 0.7882 | 0.7883 |
0.0983 | 7.0 | 15988 | 1.2988 | 0.7819 | 0.7830 |
0.0618 | 8.0 | 18272 | 1.4363 | 0.7862 | 0.7838 |
0.0408 | 9.0 | 20556 | 1.5631 | 0.7839 | 0.7827 |
0.0223 | 10.0 | 22840 | 1.5912 | 0.7882 | 0.7869 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2