base_model: meta-llama/Llama-4-Scout-17B-16E
model_type: Llama4ForConditionalGeneration
  # Automatically upload checkpoint and final model to HF
  # hub_model_id: username/custom_model_name

strict: false

  # torch_compile: true

adapter: lora
lora_r: 32
lora_alpha: 64
lora_target_modules:
  - self_attn.q_proj
  - self_attn.k_proj
  - self_attn.v_proj
  - self_attn.o_proj
lora_modules_to_save:
  - lm_head
  - embed_tokens

chat_template: llama4
datasets:
  - path: mlabonne/FineTome-100k
    type: chat_template
    split: train[:20%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch_8bit
lr_scheduler: cosine
learning_rate: 2e-5

bf16: true
tf32: true

# gradient_checkpointing: true
# gradient_checkpointing_kwargs:
#   use_reentrant: false
logging_steps: 1
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
saves_per_epoch: 1
weight_decay: 0.0
fsdp:
  - auto_wrap
  - full_shard
fsdp_config:
  fsdp_version: 2
  fsdp_offload_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: Llama4TextDecoderLayer
  fsdp_state_dict_type: SHARDED_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_reshard_after_forward: true
  fsdp_activation_checkpointing: true
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot|>