mamba2-370m

This model is a fine-tuned version of state-spaces/mamba2-370m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1239
• Accuracy: 0.9792
• Precision: 0.9795
• Recall: 0.9792
• F1: 0.9793
• Auroc: 0.9969

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: 16
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• label_smoothing_factor: 0.03

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Auroc
0.3764	0.1930	500	0.2099	0.9392	0.9385	0.9392	0.9375	0.9822
0.197	0.3861	1000	0.2205	0.9315	0.9462	0.9315	0.9344	0.9929
0.1748	0.5791	1500	0.1453	0.9690	0.9690	0.9690	0.9690	0.9942
0.1601	0.7721	2000	0.1352	0.9750	0.9756	0.9750	0.9752	0.9954
0.1542	0.9652	2500	0.2024	0.9428	0.9450	0.9428	0.9400	0.9935

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.4.0+cu124
• Datasets 2.19.1
• Tokenizers 0.19.1