Quick Links
multi_task_model_content_freeze_encoder_2048_8_v2
This model is a fine-tuned version of RonTon05/model_content_V2_test on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6475
- Accuracy: 0.8393
- F1: 0.7943
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: 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8455 | 1.0 | 330 | 0.5639 | 0.8173 | 0.6339 |
| 0.4627 | 2.0 | 660 | 0.4889 | 0.8336 | 0.8008 |
| 0.3243 | 3.0 | 990 | 0.4974 | 0.8462 | 0.8006 |
| 0.2389 | 4.0 | 1320 | 0.4918 | 0.8517 | 0.8113 |
| 0.1751 | 5.0 | 1650 | 0.5684 | 0.8458 | 0.7990 |
| 0.1284 | 6.0 | 1980 | 0.6475 | 0.8393 | 0.7943 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoTokenizer, PhoBERTMultiTask tokenizer = AutoTokenizer.from_pretrained("phunganhsang/multi_task_model_content_freeze_encoder_2048_8_v2") model = PhoBERTMultiTask.from_pretrained("phunganhsang/multi_task_model_content_freeze_encoder_2048_8_v2")