yelp_review_classifier

This model is a fine-tuned version of google-bert/bert-base-cased on Yelp/yelp_review_full dataset. It achieves the following results on the evaluation set:

• Loss: 0.7121
• Accuracy: 0.6864

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3664	0.0985	500	0.8323	0.6359
0.8124	0.1969	1000	0.7954	0.6487
0.7915	0.2954	1500	0.7846	0.6562
0.7693	0.3938	2000	0.7509	0.6699
0.7591	0.4923	2500	0.7425	0.6719
0.7456	0.5907	3000	0.7323	0.6773
0.744	0.6892	3500	0.7282	0.6806
0.7347	0.7876	4000	0.7181	0.6838
0.7277	0.8861	4500	0.7158	0.6841
0.719	0.9845	5000	0.7121	0.6864

Framework versions

• Transformers 4.55.4
• Pytorch 2.7.0+gitf717b2a
• Datasets 3.6.0
• Tokenizers 0.21.4