metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
base_model: distilbert-base-uncased
model-index:
- name: FT_DistilBERT
results: []
FT_DistilBERT
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: 0.2519
- Accuracy: 0.8892
- F1: 0.8892
- Precision: 0.8904
- Recall: 0.8900
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: 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.3172 | 1.0 | 1000 | 0.2984 | 0.8745 | 0.8740 | 0.8772 | 0.8734 |
| 0.2419 | 2.0 | 2000 | 0.2519 | 0.8892 | 0.8892 | 0.8904 | 0.8900 |
| 0.2102 | 3.0 | 3000 | 0.2963 | 0.8955 | 0.8955 | 0.8960 | 0.8960 |
| 0.1679 | 4.0 | 4000 | 0.3012 | 0.9005 | 0.9004 | 0.9007 | 0.9002 |
| 0.1569 | 5.0 | 5000 | 0.3147 | 0.8958 | 0.8957 | 0.8958 | 0.8956 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2