9f824ef76a
* simplify the example configs to be more minimal and less daunting * drop empty s2_attention from example yamls
64 lines
1.4 KiB
YAML
64 lines
1.4 KiB
YAML
base_model: hugging-quants/Meta-Llama-3.1-405B-BNB-NF4-BF16
|
|
# optionally might have model_type or tokenizer_type
|
|
tokenizer_type: AutoTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_4bit: true
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: tatsu-lab/alpaca
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out/qlora-llama3_1-405b
|
|
save_safetensors: true
|
|
|
|
adapter: qlora
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
lora_r: 16
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 2
|
|
optimizer: adamw_torch_fused
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.00001
|
|
|
|
bf16: true
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: true
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
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: LlamaDecoderLayer
|
|
fsdp_state_dict_type: FULL_STATE_DICT
|
|
fsdp_sharding_strategy: FULL_SHARD
|
|
special_tokens:
|
|
pad_token: <|finetune_right_pad_id|>
|