Closed elliotthwang closed 2 months ago
run_id
is just a string that uniquely identifies this run, it's only used for naming the output dir and the WANDB run. i have the bad habit of putting too much information in there.
these are the relevant lines where it is used:
training_arguments = TrainingArguments(
output_dir = f"out_{run_id}",
...
wandb.init(
project = "OpenELM",
name = run_id,
).log_code(include_fn=lambda path: path.endswith(".py") or path.endswith(".ipynb"))
Thanks for your replying promptly!
Is it I could ignore the run_id setting?
yes
How about the bnb_config peft_config, should I put them into your finetune codes?
Thanks!
How about the bnb_config peft_config, should I put them into your finetune codes?
None of those. The training code in the notebook is without quantization of the base model and no PEFT. It's a full finetune of a bfloat16 model
Got!
Thanks
Thank you your OPENELM ipynb tried a full finetune with HuggingFace SFTTrainer.
However, could you kind to advice how to set run_id = f"OpenELM-450M_LR-{lr}OA{str(uuid.uuid4())}" accordingly.
Regards