Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
cf6a0e7 verified
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.44511839181562013,
"train_runtime": 1281.3009,
"train_samples": 10080,
"train_samples_per_second": 7.867,
"train_steps_per_second": 0.123
}