132eb740f0
* wip for dbrx finetuning * add fastcore for parallel loading of sharded weights * fix dtype for load, use PartialState instead of accelerator to init process group, remove redundant wandb callback * update to use v2 of the converted model * more fixes for dbrx loras * make sure to enable fsdp activation checkpointing * fix support for 8bit loras too for dbrx * apply z3 leaf moe fix for DBRX with deepspeed * don't raise value error since child module searches could fail and be ok * revert a previous change to fix fsdp * update mistral/mistral qlora+fsdp yamls * fix qlora+fsdp quant storage type * more edge cases for qlora-fsdp * fixes for fsdp+qlora w optimizer in 8bit * add bigstral z3 config and make sure to use full_state_dict for fsdp
82 lines
1.5 KiB
YAML
82 lines
1.5 KiB
YAML
base_model: mistral-community/Mixtral-8x22B-v0.1
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: tatsu-lab/alpaca
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.02
|
|
output_dir: ./qlora-out
|
|
|
|
model_config:
|
|
output_router_logits: true
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 1024
|
|
sample_packing: false
|
|
pad_to_sequence_len: false
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
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
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
loss_watchdog_threshold: 5.0
|
|
loss_watchdog_patience: 3
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
eval_table_size:
|
|
eval_max_new_tokens: 128
|
|
saves_per_epoch: 1
|
|
debug:
|
|
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_transformer_layer_cls_to_wrap: MixtralSparseMoeBlock
|
|
fsdp_state_dict_type: FULL_STATE_DICT
|
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
|
special_tokens:
|