Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
49c0b46 verified
{
"epoch": 8.0,
"total_flos": 0.0,
"train_loss": 4636.829430179319,
"train_runtime": 15508.5423,
"train_samples": 17626,
"train_samples_per_second": 9.092,
"train_steps_per_second": 0.142
}