Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
616cbaf verified
{
"epoch": 8.0,
"total_flos": 0.0,
"train_loss": 5001.436384560406,
"train_runtime": 15532.4918,
"train_samples": 17626,
"train_samples_per_second": 9.078,
"train_steps_per_second": 0.142
}