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

experimental_skip_move_to_device: true  # prevent OOM by NOT putting model to GPU before sharding

datasets:
  - path: winglian/pirate-ultrachat-10k
    type: chat_template
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/qlora-out

sequence_len: 2048
sample_packing: true
eval_sample_packing: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

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

bf16: auto
tf32: false

# gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

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

fsdp_version: 2
fsdp_config:
  offload_params: false
  cpu_ram_efficient_loading: true
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Glm4MoeDecoderLayer
  state_dict_type: SHARDED_STATE_DICT
  reshard_after_forward: true
  activation_checkpointing: true