hybrid_lexical_hosting_64_15_v5_8_7_2026
This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2308
- Accuracy: 0.9017
- F1: 0.9024
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 865
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 345 | 0.2005 | 0.8655 | 0.8665 |
| 0.2274 | 2.0 | 690 | 0.1840 | 0.8833 | 0.8837 |
| 0.2274 | 3.0 | 1035 | 0.1690 | 0.9020 | 0.9013 |
| 0.1639 | 4.0 | 1380 | 0.1622 | 0.9008 | 0.9019 |
| 0.1639 | 5.0 | 1725 | 0.1623 | 0.9027 | 0.9031 |
| 0.1267 | 6.0 | 2070 | 0.1671 | 0.9081 | 0.9085 |
| 0.1267 | 7.0 | 2415 | 0.1669 | 0.9084 | 0.9087 |
| 0.1026 | 8.0 | 2760 | 0.1850 | 0.9049 | 0.9055 |
| 0.1026 | 9.0 | 3105 | 0.2107 | 0.9060 | 0.9068 |
| 0.0852 | 10.0 | 3450 | 0.2308 | 0.9017 | 0.9024 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.10.0+cu128
- Datasets 3.0.1
- Tokenizers 0.22.1