base_model: meta-llama/Llama-3.2-3B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: false
load_in_4bit: false
strict: false

plugins:
  - axolotl.integrations.liger.LigerPlugin

liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
liger_fused_linear_cross_entropy: true

datasets:
  - path: yahma/alpaca-cleaned
    type: alpaca

output_dir: ./outputs/fp8_out/

sample_packing: true
pad_to_sequence_len: true
sequence_len: 512

flex_attention: true
flex_attn_compile_kwargs:
  dynamic: false
  mode: max-autotune-no-cudagraphs
torch_compile: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 1
optimizer: adamw_torch_fused

cosine_constant_lr_ratio: 0
cosine_min_lr_ratio: 1.0
learning_rate: 2e-5
save_only_model: true

fp8: true
fp8_enable_fsdp_float8_all_gather: true

resume_from_checkpoint:
logging_steps: 1

evals_per_epoch: 1
saves_per_epoch: 1

warmup_steps: 10
weight_decay: 0.0

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

special_tokens:
  pad_token: <|end_of_text|>

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