Extractor_Adaptor_Qwen3_r64_v

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: 0.3280

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: 2
• total_train_batch_size: 8
• 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
0.547	0.0631	30	0.4545
0.4338	0.1262	60	0.4127
0.4446	0.1893	90	0.3988
0.4112	0.2524	120	0.3882
0.3833	0.3155	150	0.3803
0.3548	0.3785	180	0.3678
0.4313	0.4416	210	0.3595
0.3584	0.5047	240	0.3498
0.3297	0.5678	270	0.3457
0.3065	0.6309	300	0.3393
0.3325	0.6940	330	0.3360
0.412	0.7571	360	0.3322
0.2727	0.8202	390	0.3292
0.2804	0.8833	420	0.3284
0.2954	0.9464	450	0.3280

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1