bert-large-categorization-uncased-finetuned

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

• Loss: 2.9071
• Accuracy: 0.3889

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	87	3.2289	0.2222
No log	2.0	174	3.0978	0.2778
No log	3.0	261	2.7951	0.3333
No log	4.0	348	3.0421	0.3333
No log	5.0	435	2.9499	0.3333
1.5731	6.0	522	2.9071	0.3889
1.5731	7.0	609	2.8835	0.3333
1.5731	8.0	696	2.8715	0.3889
1.5731	9.0	783	2.9067	0.3889
1.5731	10.0	870	2.9629	0.3889
1.5731	11.0	957	2.8977	0.3889
0.8355	12.0	1044	3.0798	0.3333
0.8355	13.0	1131	2.9957	0.3889
0.8355	14.0	1218	2.9596	0.3889
0.8355	15.0	1305	2.9296	0.3889

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0