Qwen3-8B_14367368

This model is a fine-tuned version of Qwen/Qwen3-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6188
• Accuracy: 0.6615

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.05
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6957	0.1001	283	0.6942	0.5765
0.7	0.2001	566	0.6455	0.6316
0.6356	0.3002	849	0.6433	0.6380
0.6399	0.4003	1132	0.6376	0.6445
0.5947	0.5004	1415	0.6328	0.6482
0.6299	0.6004	1698	0.6258	0.6551
0.6279	0.7005	1981	0.6252	0.6586
0.6263	0.8006	2264	0.6205	0.6603
0.593	0.9006	2547	0.6188	0.6615

Framework versions

• PEFT 0.18.0
• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.2
• Tokenizers 0.22.1