convnext-mlo-512-breat_composition

This model is a fine-tuned version of on the preprocessed1024_config dataset. It achieves the following results on the evaluation set:

• Loss: 1.1521
• Accuracy: {'accuracy': 0.5785175879396985}
• F1: {'f1': 0.565251065728165}

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.3433	1.0	796	1.1893	{'accuracy': 0.4566582914572864}	{'f1': 0.32080438921262083}
1.1242	2.0	1592	1.0867	{'accuracy': 0.48555276381909546}	{'f1': 0.4061780745199038}
1.0569	3.0	2388	1.1587	{'accuracy': 0.49120603015075376}	{'f1': 0.40970823779940124}
0.9327	4.0	3184	0.9901	{'accuracy': 0.5452261306532663}	{'f1': 0.4885626990630958}
0.8723	5.0	3980	0.9824	{'accuracy': 0.5728643216080402}	{'f1': 0.5365052338942904}
0.7803	6.0	4776	1.0071	{'accuracy': 0.571608040201005}	{'f1': 0.5246756181464156}
0.7198	7.0	5572	1.0233	{'accuracy': 0.5741206030150754}	{'f1': 0.5405969058526473}
0.6589	8.0	6368	1.0902	{'accuracy': 0.5816582914572864}	{'f1': 0.5421523761661359}
0.6055	9.0	7164	1.0980	{'accuracy': 0.5835427135678392}	{'f1': 0.5601877104043351}
0.5722	10.0	7960	1.1521	{'accuracy': 0.5785175879396985}	{'f1': 0.565251065728165}

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0
• Datasets 2.1.0
• Tokenizers 0.12.1