topic_classification

This model is a fine-tuned version of bert-base-uncased on the yahoo_answers_topics dataset. It achieves the following results on the evaluation set:

• Loss: 1.1769
• Accuracy: 0.6518

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.005	1.0	625	1.0478	0.6519
0.7717	2.0	1250	1.0482	0.6557
0.4566	3.0	1875	1.1769	0.6518

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0