max_steps = 200
learning_rate = 1e-6
warmup_ratio = 0.1
dpo_beta = 0.4
use_rslora = True
use_loftq = False
lora_rank = 128
lora_alpha = 256
load_separate_reference_model = False
optim = "paged_lion_32bit"
- Downloads last month
- 1,885
max_steps = 200
learning_rate = 1e-6
warmup_ratio = 0.1
dpo_beta = 0.4
use_rslora = True
use_loftq = False
lora_rank = 128
lora_alpha = 256
load_separate_reference_model = False
optim = "paged_lion_32bit"