lnm-classifier

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7829
• Accuracy: 0.3235

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.2846	1.0	17	3.2341	0.1176
3.1608	2.0	34	3.1803	0.0882
3.0471	3.0	51	3.1653	0.1471
2.9494	4.0	68	3.1728	0.0882
2.848	5.0	85	3.0685	0.1176
2.7737	6.0	102	3.1228	0.1765
2.6777	7.0	119	3.0640	0.2059
2.6111	8.0	136	3.0528	0.2059
2.5464	9.0	153	3.0111	0.2353
2.5201	10.0	170	2.9701	0.2059
2.4315	11.0	187	2.9234	0.2059
2.3571	12.0	204	2.8955	0.2941
2.3202	13.0	221	2.8774	0.2353
2.2824	14.0	238	2.8464	0.2647
2.2163	15.0	255	2.8285	0.2941
2.1859	16.0	272	2.8062	0.2941
2.1898	17.0	289	2.8084	0.3235
2.1454	18.0	306	2.7896	0.3235
2.1143	19.0	323	2.7821	0.3235
2.1219	20.0	340	2.7829	0.3235

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0