base_model: Qwen/Qwen3.5-122B-A10B

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
quantize_moe_experts: true
adapter: qlora
lora_r: 16
lora_alpha: 32
lora_dropout: 0
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj

# Regex matching to target shared experts too
# lora_target_modules: 'model\.(language_model\.)?layers\.[\d]+\.(mlp|self_attn)\.(shared_expert\.)?(up|down|gate|gate_up|q|k|v|o)_proj'

# Target experts
# lora_target_parameters:
#   - mlp.experts.gate_up_proj
#   - mlp.experts.down_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

lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

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: