base_model: Qwen/Qwen3.5-27B

# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
strict: false

chat_template: qwen3_5
datasets:
  - path: mlabonne/FineTome-100k
    type: chat_template
    split: train[:20%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value
val_set_size: 0.0
output_dir: ./outputs/out
dataset_prepared_path: last_run_prepared

sequence_len: 2048
sample_packing: true

load_in_4bit: true
adapter: qlora
lora_r: 16
lora_alpha: 32
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - down_proj
  - up_proj
  # Uncomment below to also target the linear attention projections.
  # These use separate in_proj_qkv / in_proj_z / out_proj (Qwen3.5-specific).
  # - linear_attn.in_proj_qkv
  # - linear_attn.in_proj_z
  # - linear_attn.out_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch_4bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
attn_implementation: flash_attention_2

warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:

fsdp_version: 2
fsdp_config:
  offload_params: false
  cpu_ram_efficient_loading: false
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Qwen3_5DecoderLayer
  state_dict_type: FULL_STATE_DICT
  reshard_after_forward: true
  activation_checkpointing: true