multi_cls_mamba2-130m

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1613
• Flat Accuracy: 0.9595
• Accuracy: 0.7031
• Micro Precision: 0.8246
• Micro Recall: 0.8889
• Micro F1: 0.8555
• Macro Precision: 0.7352
• Macro Recall: 0.8847
• Macro F1: 0.7905
• Weighted Precision: 0.8319
• Weighted Recall: 0.8889
• Weighted F1: 0.8581

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Flat Accuracy	Accuracy	Micro Precision	Micro Recall	Micro F1	Macro Precision	Macro Recall	Macro F1	Weighted Precision	Weighted Recall	Weighted F1
0.1308	1.0	2500	0.1074	0.9615	0.7195	0.8570	0.8581	0.8576	0.7462	0.8695	0.7858	0.8712	0.8581	0.8612
0.0736	2.0	5000	0.1125	0.9612	0.7148	0.8367	0.8854	0.8603	0.7499	0.8830	0.7981	0.8433	0.8854	0.8626
0.0232	3.0	7500	0.1460	0.9588	0.6978	0.8220	0.8867	0.8531	0.7210	0.8855	0.7787	0.8319	0.8867	0.8566
0.005	4.0	10000	0.1613	0.9595	0.7031	0.8246	0.8889	0.8555	0.7352	0.8847	0.7905	0.8319	0.8889	0.8581
0.0017	5.0	12500	0.1626	0.9610	0.7114	0.8375	0.8822	0.8593	0.7442	0.8809	0.7940	0.8451	0.8822	0.8618

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.1+cu118
• Datasets 3.1.0
• Tokenizers 0.19.1