Files
axolotl/examples/llama-3/3b-qat-fsdp2.yaml

80 lines
1.6 KiB
YAML

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
split: train[:95%]
output_dir: ./outputs/qat_out/
dataset_prepared_path: ./outputs/qat_out/dataset_prepared
sample_packing: false
sequence_len: 8192
flash_attention: true
qat:
activation_dtype: int8
weight_dtype: int4
group_size: 32
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
bf16: true
resume_from_checkpoint:
logging_steps: 1
evals_per_epoch: 1
saves_per_epoch: 1
warmup_ratio: 0.1
weight_decay: 0.0
fsdp:
- full_shard
- auto_wrap
fsdp_config:
fsdp_version: 2
fsdp_offload_params: false
fsdp_cpu_ram_efficient_loading: false
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sharding_strategy: FULL_SHARD
fsdp_reshard_after_forward: true
fsdp_activation_checkpointing: true
special_tokens:
pad_token: <|finetune_right_pad_id|>
# save_first_step: true # uncomment this to validate checkpoint saving works with your config