Pruner_Adaptor_Qwen_3_r64

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: 0.4629

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: 0.2
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6014	0.1129	25	0.4629
0.614	0.2257	50	0.5950
0.7895	0.3386	75	0.5972
0.6122	0.4515	100	0.5506
0.5736	0.5643	125	0.5917
0.5476	0.6772	150	0.5218
0.504	0.7901	175	0.5084
0.4437	0.9029	200	0.4692

Framework versions

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