base_model: Qwen/Qwen3.5-27B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

# Full fine-tune (FFT) of the text-only path of Qwen3.5-27B.

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

# Freeze vision encoder
unfrozen_parameters:
  - model.language_model.*
  - lm_head.*

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
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
flash_attention: true

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