base_model: zai-org/GLM-4.5-Air

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

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

load_in_8bit: false
load_in_4bit: true

quantize_moe_experts: true # important

datasets:
  - path: fozziethebeat/alpaca_messages_2k_test
    type: chat_template

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/lora-out

adapter: qlora
lora_model_dir:

sequence_len: 2048
sample_packing: true

lora_r: 16
lora_alpha: 8
lora_dropout: 0
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj

# lora_target_parameters:
#   - mlp.experts.gate_up_proj
#   - mlp.experts.down_proj

lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 1
saves_per_epoch: 1

# save_first_step: true  # uncomment this to validate checkpoint saving works with your config