{
  "model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
  "per_device_train_batch_size": 8,
  "gradient_accumulation_steps": 4,
  "max_seq_length": 4096,
  "learning_rate": 0.0003,
  "warmup_steps": 200,
  "bf16": true,
  "optim": "adamw_torch_fused",
  "gradient_checkpointing": true,
  "torch_compile": true,
  "dataloader_num_workers": 4,
  "dataloader_pin_memory": true,
  "dataloader_prefetch_factor": 4,
  "dataloader_persistent_workers": true,
  "attn_implementation": "flash",
  "num_train_epochs": 3,
  "save_steps": 500,
  "logging_steps": 25,
  "output_dir": "./out",
  "hub_token": "hf_jsonsamplehfabcdefghijklmnopqrs",
  "checkpoint_uri": "s3://team-bucket/runs/qwen-lora-001/",
  "env_vars": {
    "HSA_FORCE_FINE_GRAIN_PCIE": "1",
    "NCCL_MIN_NCHANNELS": "112"
  }
}