Files
axolotl/examples/deepseek-v2/fft-fsdp-16b.yaml

58 lines
1.2 KiB
YAML

base_model: deepseek-ai/DeepSeek-V2-Lite
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name
trust_remote_code: true
datasets:
- path: tatsu-lab/alpaca
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5
bf16: auto
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
warmup_steps: 100
evals_per_epoch: 2
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
fsdp:
- full_shard
- auto_wrap
fsdp_config:
fsdp_limit_all_gathers: true
fsdp_sync_module_states: true
fsdp_offload_params: true
fsdp_use_orig_params: false
fsdp_cpu_ram_efficient_loading: true
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_transformer_layer_cls_to_wrap: DeepseekV2DecoderLayer
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sharding_strategy: FULL_SHARD