af8d257aa2
* make pad_to_sequence_len default to the same value as sample_packing * remove duplicate validation * fix test * update description meta Co-authored-by: NanoCode012 <nano@axolotl.ai> --------- Co-authored-by: NanoCode012 <nano@axolotl.ai>
80 lines
1.5 KiB
YAML
80 lines
1.5 KiB
YAML
base_model: neuralmagic/Sparse-Llama-3.1-8B-2of4
|
|
|
|
plugins:
|
|
- axolotl.integrations.llm_compressor.LLMCompressorPlugin
|
|
|
|
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: 0.05
|
|
output_dir: ./outputs/out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
eval_sample_packing: false
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 8
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: paged_adamw_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 2e-5
|
|
|
|
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:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 100
|
|
evals_per_epoch: 2
|
|
eval_table_size:
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
pad_token: <|end_of_text|>
|
|
|
|
llmcompressor:
|
|
recipe:
|
|
finetuning_stage:
|
|
finetuning_modifiers:
|
|
ConstantPruningModifier:
|
|
targets: [
|
|
're:.*q_proj.weight',
|
|
're:.*k_proj.weight',
|
|
're:.*v_proj.weight',
|
|
're:.*o_proj.weight',
|
|
're:.*gate_proj.weight',
|
|
're:.*up_proj.weight',
|
|
're:.*down_proj.weight',
|
|
]
|
|
start: 0
|
|
save_compressed: true
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|