test_yelp_classification

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

• Loss: 1.6214
• Accuracy: 0.2812

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: 8
• eval_batch_size: 8
• seed: 42
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5984	0.25	1	1.6315	0.1875
1.6923	0.5	2	1.6576	0.1562
1.687	0.75	3	1.6407	0.2188
1.4926	1.0	4	1.6337	0.1875
1.6151	1.25	5	1.6170	0.1875
1.4544	1.5	6	1.6112	0.25
1.3246	1.75	7	1.6068	0.2812
1.3425	2.0	8	1.6180	0.25
1.3521	2.25	9	1.6271	0.25
1.2995	2.5	10	1.6251	0.25
1.3522	2.75	11	1.6227	0.2812
1.3706	3.0	12	1.6214	0.2812

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0
• Datasets 3.3.2
• Tokenizers 0.21.0