metadata
base_model: airesearch/wangchanberta-base-att-spm-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: lst20-sent-segment
results: []
lst20-sent-segment
This model is a fine-tuned version of airesearch/wangchanberta-base-att-spm-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1513
- Precision: 0.7125
- Recall: 0.5426
- F1: 0.6160
- Accuracy: 0.9403
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: 1e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1842 | 1.0 | 1274 | 0.1596 | 0.6990 | 0.4995 | 0.5827 | 0.9361 |
| 0.1622 | 2.0 | 2548 | 0.1513 | 0.7052 | 0.5330 | 0.6071 | 0.9389 |
| 0.1554 | 3.0 | 3822 | 0.1513 | 0.7125 | 0.5426 | 0.6160 | 0.9403 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0