bert-large-cased-topic_classification

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

• Loss: 0.6996
• Precision: 0.9000
• Recall: 0.8902
• F1: 0.8941
• Accuracy: 0.8922

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	44	0.6240	0.8483	0.8532	0.8411	0.8480
No log	2.0	88	0.3887	0.9054	0.8660	0.8792	0.8873
No log	3.0	132	0.4416	0.9015	0.9034	0.9022	0.9020
No log	4.0	176	0.6620	0.9290	0.8847	0.8991	0.9020
No log	5.0	220	0.6337	0.9148	0.8880	0.8970	0.8971
No log	6.0	264	0.6673	0.8965	0.8875	0.8905	0.8922
No log	7.0	308	0.6857	0.9000	0.8902	0.8941	0.8922
No log	8.0	352	0.6921	0.9000	0.8902	0.8941	0.8922
No log	9.0	396	0.6976	0.9000	0.8902	0.8941	0.8922
No log	10.0	440	0.6996	0.9000	0.8902	0.8941	0.8922

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1