relation_detection_textual

This model is a fine-tuned version of Musixmatch/umberto-commoncrawl-cased-v1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5247
• F1: 0.6071
• Roc Auc: 0.6769
• Accuracy: 0.5659

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	33	0.5783	0.2301	0.5	0.5271
No log	2.0	66	0.5327	0.4997	0.6312	0.5814
No log	3.0	99	0.5276	0.5688	0.6597	0.5969
No log	4.0	132	0.5228	0.4610	0.6262	0.6434
No log	5.0	165	0.5153	0.5762	0.6594	0.6124
No log	6.0	198	0.5153	0.5762	0.6594	0.6124
No log	7.0	231	0.5190	0.6032	0.6729	0.5659
No log	8.0	264	0.5240	0.6021	0.6728	0.5736
No log	9.0	297	0.5247	0.6071	0.6769	0.5659
No log	10.0	330	0.5257	0.5924	0.6672	0.5659

Framework versions

• Transformers 4.38.2
• Pytorch 2.0.0+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2