metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: augmented_model_fast_2
results: []
augmented_model_fast_2
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: 1.3594
- Accuracy: 0.5430
- F1: 0.5448
- Precision: 0.5556
- Recall: 0.5421
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: 3e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.4925 | 0.1566 | 500 | 0.8184 | 0.7290 | 0.7187 | 0.7234 | 0.7203 |
0.4276 | 0.3133 | 1000 | 0.8397 | 0.7281 | 0.7154 | 0.7210 | 0.7184 |
0.4067 | 0.4699 | 1500 | 0.8337 | 0.7281 | 0.7182 | 0.7214 | 0.7198 |
0.3826 | 0.6266 | 2000 | 0.8869 | 0.7286 | 0.7170 | 0.7246 | 0.7191 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1