qwen35-397b-lora-sft-amdpilot-v5-1

This model is a fine-tuned version of Qwen/Qwen3.5-397B-A17B on the amdpilot_v5_1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1419

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Use 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_steps: 0.05
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0725	1.6667	10	0.2330
0.0588	3.3333	20	0.1855
0.0597	5.0	30	0.1570
0.0580	6.6667	40	0.1466
0.0494	8.3333	50	0.1447
0.0539	10.0	60	0.1419

Framework versions

• PEFT 0.18.1
• Transformers 5.2.0
• Pytorch 2.9.1+rocm7.2.0.git7e1940d4
• Datasets 4.0.0
• Tokenizers 0.22.2