mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
30 lines
No EOL
564 B
YAML
30 lines
No EOL
564 B
YAML
output_dir: "" # just a placeholder
|
|
bf16: true
|
|
model_name_or_path: meta-llama/Llama-3.2-1B-Instruct
|
|
label_names: ["labels"]
|
|
eval_on_start: True
|
|
eval_strategy: "steps"
|
|
eval_steps: 500
|
|
save_strategy: "no"
|
|
# save_steps: 500
|
|
logging_strategy: "steps"
|
|
logging_steps: 100
|
|
use_liger_kernel: true
|
|
remove_unused_columns: false
|
|
|
|
optim: schedule_free_adamw
|
|
learning_rate: 0.0001
|
|
lr_scheduler_type: "constant_with_warmup"
|
|
neftune_noise_alpha: 0
|
|
weight_decay: 0.01
|
|
warmup_ratio: 0.1
|
|
|
|
|
|
|
|
# LoRA
|
|
lora_r: 8
|
|
lora_dropout: 0.05
|
|
target_modules:
|
|
- down_proj
|
|
- up_proj
|
|
- gate_proj |