final_classification

This model is a fine-tuned version of yhavinga/t5-small-24L-ccmatrix-multi on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0945
• F1: {'f1': 0.9405940594059407}
• Precision: {'precision': 0.9134615384615384}
• Recall: {'recall': 0.9693877551020408}

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: 0.0001
• 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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
No log	1.0	110	0.2338	{'f1': 0.6845637583892618}	{'precision': 1.0}	{'recall': 0.5204081632653061}
No log	2.0	220	0.0828	{'f1': 0.9387755102040817}	{'precision': 0.9387755102040817}	{'recall': 0.9387755102040817}
No log	3.0	330	0.0891	{'f1': 0.9359605911330049}	{'precision': 0.9047619047619048}	{'recall': 0.9693877551020408}
No log	4.0	440	0.0744	{'f1': 0.95}	{'precision': 0.9313725490196079}	{'recall': 0.9693877551020408}
0.1529	5.0	550	0.1012	{'f1': 0.9405940594059407}	{'precision': 0.9134615384615384}	{'recall': 0.9693877551020408}
0.1529	6.0	660	0.0945	{'f1': 0.9405940594059407}	{'precision': 0.9134615384615384}	{'recall': 0.9693877551020408}

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1