metadata
library_name: transformers
license: mit
base_model: vinai/phobert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: phobert-human-finetune-seg-seed-6960
results: []
phobert-human-finetune-seg-seed-6960
This model is a fine-tuned version of vinai/phobert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5298
- Accuracy: 0.8578
- Precision: 0.6727
- Recall: 0.6734
- F1: 0.6699
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 346 | 0.4193 | 0.8417 | 0.6207 | 0.6366 | 0.6191 |
| 0.461 | 2.0 | 692 | 0.3603 | 0.8668 | 0.6783 | 0.6527 | 0.6589 |
| 0.2821 | 3.0 | 1038 | 0.4674 | 0.8323 | 0.5692 | 0.5625 | 0.5657 |
| 0.2821 | 4.0 | 1384 | 0.5683 | 0.8675 | 0.7121 | 0.5963 | 0.6240 |
| 0.1664 | 5.0 | 1730 | 0.5298 | 0.8578 | 0.6727 | 0.6734 | 0.6699 |
| 0.1125 | 6.0 | 2076 | 0.6659 | 0.8391 | 0.6285 | 0.6851 | 0.6527 |
| 0.1125 | 7.0 | 2422 | 0.7109 | 0.8634 | 0.6862 | 0.5978 | 0.6292 |
| 0.0863 | 8.0 | 2768 | 0.7702 | 0.8638 | 0.6980 | 0.5886 | 0.6282 |
| 0.0739 | 9.0 | 3114 | 0.6283 | 0.8574 | 0.6609 | 0.6352 | 0.6472 |
| 0.0739 | 10.0 | 3460 | 0.8402 | 0.8537 | 0.6689 | 0.6275 | 0.6441 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0