mrpc_lemmatized_new

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: 1.4643
• Accuracy: 0.8058

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: 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
0.5449	1.0	255	0.4622	0.7925
0.3556	2.0	510	0.4824	0.7890
0.2135	3.0	765	0.6725	0.7826
0.1251	4.0	1020	0.9652	0.7994
0.0845	5.0	1275	0.9354	0.8023
0.0431	6.0	1530	1.0782	0.7959
0.0287	7.0	1785	1.2790	0.8052
0.0186	8.0	2040	1.1717	0.8075
0.0186	9.0	2295	1.2979	0.8104
0.0079	10.0	2550	1.4014	0.8070
0.0071	11.0	2805	1.4469	0.8029
0.0072	12.0	3060	1.4551	0.8064
0.0043	13.0	3315	1.4443	0.8081
0.0041	14.0	3570	1.4639	0.8093
0.0015	15.0	3825	1.4643	0.8058

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2