metadata
library_name: transformers
license: apache-2.0
base_model: Geotrend/bert-base-th-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert-base-th-cased-intent-booking
results: []
bert-base-th-cased-intent-booking
This model is a fine-tuned version of Geotrend/bert-base-th-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2346
- Accuracy: 0.9369
- F1: 0.9340
- Precision: 0.9471
- Recall: 0.9369
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: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 64
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.9427 | 1.0 | 65 | 0.7129 | 0.8964 | 0.8947 | 0.9055 | 0.8964 |
| 0.48 | 2.0 | 130 | 0.2325 | 0.9369 | 0.9365 | 0.9390 | 0.9369 |
| 0.1783 | 3.0 | 195 | 0.2001 | 0.9505 | 0.9511 | 0.9578 | 0.9505 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1