arg-quality-regression

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

• Loss: 0.0342
• Mse: 0.0342
• Mae: 0.1359
• R2: 0.1353
• Accuracy: 0.9808

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: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2	Accuracy
0.0277	1.0	1512	0.0398	0.0398	0.1450	-0.0046	0.9736
0.0218	2.0	3024	0.0342	0.0342	0.1359	0.1353	0.9808
0.0169	3.0	4536	0.0367	0.0367	0.1409	0.0717	0.9783
0.0114	4.0	6048	0.0400	0.0400	0.1477	-0.0108	0.9751
0.0075	5.0	7560	0.0439	0.0439	0.1564	-0.1093	0.9704
0.006	6.0	9072	0.0465	0.0465	0.1626	-0.1749	0.9661
0.0051	7.0	10584	0.0429	0.0429	0.1574	-0.0851	0.9729
0.0037	8.0	12096	0.0440	0.0440	0.1590	-0.1123	0.9720
0.0035	9.0	13608	0.0412	0.0412	0.1534	-0.0401	0.9755
0.0029	10.0	15120	0.0415	0.0415	0.1537	-0.0487	0.9743
0.0028	11.0	16632	0.0438	0.0438	0.1589	-0.1080	0.9712

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1