base_model: zai-org/GLM-4.7-Flash

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

load_in_8bit: true
quantize_moe_experts: true

datasets:
  - path: fozziethebeat/alpaca_messages_2k_test
    type: chat_template

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/glm4.7-flash-lora-8bit-fsdp-out

adapter: lora
lora_model_dir:

sequence_len: 2048
sample_packing: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj

# Uncomment to also target MoE expert weights:
# lora_target_parameters:
#   - mlp.experts.gate_up_proj
#   - mlp.experts.down_proj

# LoRA kernels incompatible with DSA attention
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_torch_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 1
saves_per_epoch: 1

fsdp_config:
  fsdp_version: 2
  offload_params: false
  cpu_ram_efficient_loading: false
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Glm4MoeLiteDecoderLayer
  state_dict_type: FULL_STATE_DICT
  sharding_strategy: FULL_SHARD
  reshard_after_forward: true
  activation_checkpointing: true