mamba_text_classification

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2292
• 1: {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}
• 4: {'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}
• 5: {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}
• 6: {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}
• 9: {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}
• 10: {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}
• Accuracy: 0.9091
• Macro avg: {'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}
• Weighted avg: {'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}

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: 4
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	0	1	4	5	6	9	10	Accuracy	Macro avg	Weighted avg
1.0038	0.4	459	0.7923	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 0}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1-score': 0.8, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.8182	{'precision': 0.6666666666666666, 'recall': 0.6666666666666666, 'f1-score': 0.6571428571428571, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.8181818181818182, 'f1-score': 0.8181818181818182, 'support': 11}
1.0341	0.8	918	0.0965	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	1.0	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 11}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 11}
0.0006	1.2	1377	0.1084	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.9091	{'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}
0.1193	1.6	1836	0.7853	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.9091	{'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}
0.007	2.0	2295	0.0076	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	1.0	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 11}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 11}
0.0001	2.4	2754	0.3204	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.9091	{'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}
0.0001	2.8	3213	0.0948	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.9091	{'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}
0.0001	3.2	3672	0.1412	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.9091	{'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}
0.0	3.6	4131	0.2292	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 1}	{'precision': 0.6666666666666666, 'recall': 1.0, 'f1-score': 0.8, 'support': 2}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 3}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 2}	0.9091	{'precision': 0.7777777777777777, 'recall': 0.8333333333333334, 'f1-score': 0.7999999999999999, 'support': 11}	{'precision': 0.8484848484848484, 'recall': 0.9090909090909091, 'f1-score': 0.8727272727272727, 'support': 11}

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2