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-seed-1337
results: []
phobert-human-finetune-seed-1337
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: 0.4071
- Accuracy: 0.8641
- Precision: 0.6832
- Recall: 0.6493
- F1: 0.6626
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 | 0.3907 | 0.8612 | 0.6775 | 0.6062 | 0.6331 |
| 0.4561 | 2.0 | 692 | 0.3802 | 0.8544 | 0.6457 | 0.6216 | 0.6237 |
| 0.2919 | 3.0 | 1038 | 0.4071 | 0.8641 | 0.6832 | 0.6493 | 0.6626 |
| 0.2919 | 4.0 | 1384 | 0.5535 | 0.8634 | 0.7034 | 0.5859 | 0.6197 |
| 0.1808 | 5.0 | 1730 | 0.6397 | 0.8372 | 0.6556 | 0.6194 | 0.6087 |
| 0.1251 | 6.0 | 2076 | 0.5417 | 0.8570 | 0.6550 | 0.6391 | 0.6467 |
| 0.1251 | 7.0 | 2422 | 0.6166 | 0.8608 | 0.6760 | 0.6321 | 0.6509 |
| 0.0932 | 8.0 | 2768 | 0.7020 | 0.8368 | 0.6254 | 0.6824 | 0.6496 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0