Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
23ecbd4 verified
{
"epoch": 8.0,
"total_flos": 0.0,
"train_loss": 0.5009988050205983,
"train_runtime": 15591.8911,
"train_samples": 17626,
"train_samples_per_second": 9.044,
"train_steps_per_second": 0.142
}