metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilhubert-finetuned-mixed-data
results: []
distilhubert-finetuned-mixed-data
This model is a fine-tuned version of ntu-spml/distilhubert on an unknown dataset.
- Loss: 0.7808755040168762,
- Accuracy: 0.8644688644688645,
- F1: 0.8641694609590086,
- Precision: 0.8653356589517041,
- Recall: 0.8644688644688645,
- Confusion Matrix: [[71, 9, 0, 3], [5, 42, 12, 0], [0, 7, 55, 0], [1, 0, 0, 68]]
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: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 123
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 40
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Confusion Matrix |
|---|---|---|---|---|---|---|---|---|
| 0.5098 | 40.0000 | 50 | 0.7809 | 0.8645 | 0.8642 | 0.8653 | 0.8645 | [[71, 9, 0, 3], [5, 42, 12, 0], [0, 7, 55, 0], [1, 0, 0, 68]] |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1