👨🔥🍜PhoBERT human finetune word (segmented)
Collection
PhoBERT finetune for HSD - with human-reference annotated data, in word-level (using vncorenlp segmentation). Numbers denote different seeds • 5 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("trhgquan/phobert-human-finetune-seg-seed-69")
model = AutoModelForSequenceClassification.from_pretrained("trhgquan/phobert-human-finetune-seg-seed-69")Quick Links
phobert-human-finetune-seg-seed-69
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: 0.3980
- Accuracy: 0.8683
- Precision: 0.6929
- Recall: 0.6500
- F1: 0.6658
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 | 0.4182 | 0.8406 | 0.6133 | 0.6124 | 0.5936 |
| 0.4634 | 2.0 | 692 | 0.4766 | 0.8353 | 0.6370 | 0.5809 | 0.5147 |
| 0.291 | 3.0 | 1038 | 0.3980 | 0.8683 | 0.6929 | 0.6500 | 0.6658 |
| 0.291 | 4.0 | 1384 | 0.5448 | 0.8537 | 0.6428 | 0.6282 | 0.6269 |
| 0.1759 | 5.0 | 1730 | 0.5188 | 0.8372 | 0.6457 | 0.6572 | 0.6379 |
| 0.1243 | 6.0 | 2076 | 0.5866 | 0.8518 | 0.6448 | 0.6292 | 0.6357 |
| 0.1243 | 7.0 | 2422 | 0.6440 | 0.8630 | 0.6778 | 0.6128 | 0.6404 |
| 0.1005 | 8.0 | 2768 | 0.6986 | 0.8593 | 0.6667 | 0.6217 | 0.6341 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Model tree for trhgquan/phobert-human-finetune-seg-seed-69
Base model
vinai/phobert-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="trhgquan/phobert-human-finetune-seg-seed-69")