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
57 lines
986 B
YAML
57 lines
986 B
YAML
base_model: LnL-AI/dbrx-base-converted-v2
|
|
trust_remote_code: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: tatsu-lab/alpaca
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.0
|
|
output_dir: ./out
|
|
|
|
sequence_len: 512
|
|
sample_packing: false
|
|
pad_to_sequence_len: false
|
|
|
|
unfrozen_parameters:
|
|
- transformer.blocks.[0-7].
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: paged_adamw_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch:
|
|
saves_per_epoch: 1
|
|
debug:
|
|
weight_decay: 0.0
|
|
deepspeed: deepspeed_configs/zero3_bf16.json
|