metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: trainer2
results: []
trainer2
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: 2.9503
- Precision: 0.6569
- Recall: 0.6071
- F1: 0.6119
- Accuracy: 0.6071
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: 6e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0002 | 0.57 | 30 | 2.6229 | 0.6545 | 0.6071 | 0.6066 | 0.6071 |
| 0.0001 | 1.13 | 60 | 2.6791 | 0.6866 | 0.6310 | 0.6362 | 0.6310 |
| 0.0001 | 1.7 | 90 | 2.8369 | 0.6569 | 0.6071 | 0.6119 | 0.6071 |
| 0.0001 | 2.26 | 120 | 2.9043 | 0.6569 | 0.6071 | 0.6119 | 0.6071 |
| 0.0001 | 2.83 | 150 | 2.9231 | 0.6569 | 0.6071 | 0.6119 | 0.6071 |
| 0.0001 | 3.4 | 180 | 2.9291 | 0.6569 | 0.6071 | 0.6119 | 0.6071 |
| 0.0001 | 3.96 | 210 | 2.9367 | 0.6569 | 0.6071 | 0.6119 | 0.6071 |
| 0.0001 | 4.53 | 240 | 2.9472 | 0.6569 | 0.6071 | 0.6119 | 0.6071 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2