library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	apache-2.0	Qwen/Qwen3-1.7B	generated_from_trainer	name results unsup-Qwen3-1.7B-datav3

unsup-Qwen3-1.7B-datav3

This model is a fine-tuned version of Qwen/Qwen3-1.7B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2568

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: 0.0003
• train_batch_size: 128
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
4.2641	0.0624	1000	0.3924
4.2102	0.1247	2000	0.3755
3.6754	0.1871	3000	0.3278
3.4875	0.2494	4000	0.3120
3.4383	0.3118	5000	0.2955
3.0117	0.3741	6000	0.2865
2.9805	0.4365	7000	0.2790
2.5125	0.4988	8000	0.2720
2.4559	0.5612	9000	0.2633
2.5172	0.6235	10000	0.2570
2.2059	0.6859	11000	0.2528
1.973	0.7482	12000	0.2564
1.9219	0.8106	13000	0.2556
1.643	0.8729	14000	0.2570
1.9918	0.9353	15000	0.2564
1.8969	0.9976	16000	0.2568

Framework versions

• Transformers 4.51.0
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.0