Extractor_Adaptor_Qwen3_QA_zero

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

• Loss: 0.6387

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: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• total_eval_batch_size: 4
• 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: 0.1
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7459	0.1264	50	0.7653
0.6676	0.2528	100	0.7142
0.7094	0.3791	150	0.6856
0.6612	0.5055	200	0.6661
0.6349	0.6319	250	0.6527
0.6486	0.7583	300	0.6433
0.617	0.8847	350	0.6387

Framework versions

• PEFT 0.15.2
• Transformers 4.57.1
• Pytorch 2.9.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.1