Qwen_Qwen2_5-3B_StereoDetect_Model

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3857
• Accuracy: 0.9366
• Balanced Accuracy: 0.9382
• F1 Weighted: 0.9367
• F1 Macro: 0.9374
• Precision: 0.9372
• Recall: 0.9366

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced Accuracy	F1 Weighted	F1 Macro	Precision	Recall
0.5779	1.0	760	0.4713	0.8848	0.8865	0.8806	0.8827	0.9045	0.8848
0.1986	2.0	1520	0.2265	0.9355	0.9353	0.9358	0.9364	0.9364	0.9355
0.1017	3.0	2280	0.3531	0.9274	0.9284	0.9273	0.9282	0.9299	0.9274
0.0493	4.0	3040	0.3236	0.9366	0.9374	0.9368	0.9376	0.9372	0.9366
0.0175	5.0	3800	0.3460	0.9389	0.9395	0.9392	0.9401	0.9396	0.9389
0.0065	6.0	4560	0.3857	0.9366	0.9382	0.9367	0.9374	0.9372	0.9366

Framework versions

• PEFT 0.19.1
• Transformers 4.51.3
• Pytorch 2.5.1+cu121
• Datasets 4.8.5
• Tokenizers 0.21.4