Qwen3-4B-lora-classifier

This model is a fine-tuned version of Qwen/Qwen3-4B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1299
• Accuracy: 0.3743
• F1 Macro: 0.3639
• F1 Weighted: 0.3678

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted
No log	1.0	22	1.5234	0.3086	0.1625	0.1565
No log	2.0	44	1.1338	0.3571	0.3526	0.3561
1.7772	3.0	66	1.1299	0.3743	0.3639	0.3678

Framework versions

• PEFT 0.17.1
• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 4.1.1
• Tokenizers 0.21.4