training_args.json

{
  "_comment": "Sanitized excerpt of the training configuration. Local paths, tracking IDs, and base-model identity removed (see adapter_config.json for the base model required by PEFT).",
  "task_type": "causal_lm",
  "torch_dtype": "bfloat16",
  "max_length": 8192,
  "max_new_tokens": 64,
  "tuner": {
    "type": "lora",
    "lora_rank": 32,
    "lora_alpha": 64,
    "lora_dropout": 0.05,
    "lora_bias": "none",
    "target_modules": "all-linear (language model only; vision merger limited to linear_fc1/linear_fc2)",
    "use_dora": false,
    "use_rslora": false,
    "freeze_vit": true,
    "freeze_aligner": false
  },
  "optimizer": {
    "name": "adamw_torch_fused",
    "learning_rate": 1e-4,
    "weight_decay": 0.1,
    "adam_beta1": 0.9,
    "adam_beta2": 0.95,
    "adam_epsilon": 1e-8,
    "max_grad_norm": 1.0,
    "lr_scheduler_type": "cosine",
    "warmup_ratio": 0.05,
    "aligner_lr": 2e-6
  },
  "training": {
    "num_train_epochs": 1.0,
    "per_device_train_batch_size": 1,
    "gradient_accumulation_steps": 8,
    "world_size": 4,
    "global_batch_size": 32,
    "bf16": true,
    "gradient_checkpointing": true,
    "seed": 42,
    "data_seed": 42,
    "deepspeed_zero_stage": 2,
    "total_steps": 294,
    "best_eval_loss": 0.1063,
    "best_step": 294
  },
  "framework": {
    "ms_swift_version": "4.1.2",
    "peft_version": "0.19.1"
  }
}