metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- yelp_review_full
metrics:
- accuracy
model-index:
- name: bbc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: yelp_review_full
type: yelp_review_full
config: yelp_review_full
split: test
args: yelp_review_full
metrics:
- name: Accuracy
type: accuracy
value: 0.22
bbc
This model is a fine-tuned version of bert-base-cased on the yelp_review_full dataset. It achieves the following results on the evaluation set:
- Loss: 1.6089
- Accuracy: 0.22
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6639 | 1.0 | 1000 | 1.6370 | 0.166 |
| 1.6549 | 2.0 | 2000 | 1.6164 | 0.22 |
| 1.6264 | 3.0 | 3000 | 1.6089 | 0.22 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3