metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-12-classes
results: []
distilbert-12-classes
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3754
- Accuracy: 0.9266
- F1: 0.9264
- Precision: 0.9349
- Recall: 0.9287
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 2.4155 | 0.96 | 50 | 2.1453 | 0.4432 | 0.3707 | 0.5871 | 0.4659 |
| 1.5038 | 1.92 | 100 | 0.7723 | 0.9261 | 0.9238 | 0.9369 | 0.9402 |
| 0.4892 | 2.88 | 150 | 0.3246 | 0.9318 | 0.9274 | 0.9356 | 0.9374 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2