metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: results
results: []
results
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0452
- Precision: 0.8809
- Recall: 0.9161
- F1: 0.8982
- Accuracy: 0.9860
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1732 | 1.0 | 2180 | 0.1202 | 0.5106 | 0.6557 | 0.5741 | 0.9612 |
0.1057 | 2.0 | 4360 | 0.0821 | 0.6500 | 0.7866 | 0.7118 | 0.9728 |
0.0639 | 3.0 | 6540 | 0.0573 | 0.7953 | 0.8256 | 0.8102 | 0.9812 |
0.0347 | 4.0 | 8720 | 0.0482 | 0.8531 | 0.9030 | 0.8773 | 0.9846 |
0.0212 | 5.0 | 10900 | 0.0452 | 0.8809 | 0.9161 | 0.8982 | 0.9860 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1