transformers_config.json

{
  "model": {
    "name": "unsloth/phi-4-unsloth-bnb-4bit",
    "trust_remote_code": true,
    "use_fast_tokenizer": true
  },

  "tokenizer": {
    "chat_template": "phi",
    "max_seq_length": 2048,
    "padding_side": "right",
    "add_eos_token": true
  },

  "training": {
    "per_device_train_batch_size": 24,
    "gradient_accumulation_steps": 2,
    "learning_rate": 3e-5,
    "num_train_epochs": 3,
    "max_steps": -1,
    "logging_steps": 10,
    "save_steps": 200,
    "save_total_limit": 5,
    "push_to_hub": true,
    "hub_strategy": "every_save",
    "gradient_checkpointing": true,
    "optim": "adamw_torch",
    "lr_scheduler_type": "cosine",
    "warmup_ratio": 0.05,
    "weight_decay": 0.01,
    "max_grad_norm": 1.0,
    "neftune_noise_alpha": 5
  },

  "checkpointing": {
    "output_dir": "./results",
    "save_strategy": "steps",
    "save_steps": 100,
    "save_total_limit": 3,
    "hub_strategy": "every_save"
  },

  "unsloth": {
    "enabled": true,
    "r": 32,
    "alpha": 16,
    "dropout": 0.05,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ]
  },

  "distributed_training": {
    "fsdp_config": {
      "enabled": true,
      "sharding_strategy": "FULL_SHARD",
      "mixed_precision": "BF16",
      "activation_checkpointing": true,
      "offload_params": false
    },
    "ddp_find_unused_parameters": false,
    "dataloader_num_workers": 8
  },

  "logging": {
    "logging_steps": 50,
    "log_level": "info"
  },

  "huggingface_hub": {
    "push_to_hub": true,
    "hub_model_id": "phi-4-research-assistant",
    "hub_private_repo": true
  },

  "model_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
  "model_revision": "main",
  "use_flash_attention": true,
  "torch_dtype": "bfloat16",
  "bf16": true
}