metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: aspect_extraction_restaurant_reviews
results: []
aspect_extraction_restaurant_reviews
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: 0.1048
- Precision: 0.7375
- Recall: 0.8194
- F1: 0.7763
- Accuracy: 0.9650
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: 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 232 | 0.1149 | 0.6062 | 0.8125 | 0.6944 | 0.9500 |
| No log | 2.0 | 464 | 0.0942 | 0.7267 | 0.8125 | 0.7672 | 0.9630 |
| 0.1371 | 3.0 | 696 | 0.0981 | 0.7152 | 0.8194 | 0.7638 | 0.9638 |
| 0.1371 | 4.0 | 928 | 0.1048 | 0.7375 | 0.8194 | 0.7763 | 0.9650 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3