Qwen3-0.6B-classifier

This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2290
• Accuracy: 0.9236
• F1: 0.8515

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0	0	0.7202	0.6830	0.2254
No log	0.2020	79	0.3226	0.8631	0.7293
No log	0.4041	158	0.2625	0.8948	0.7955
No log	0.6061	237	0.2433	0.9020	0.7964
No log	0.8082	316	0.2294	0.8919	0.7774
No log	1.0102	395	0.2312	0.9078	0.8232
No log	1.2123	474	0.3678	0.8905	0.8
0.3067	1.4143	553	0.2314	0.9164	0.8362
0.3067	1.6164	632	0.2346	0.9207	0.8415
0.3067	1.8184	711	0.2290	0.9236	0.8515

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2