Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
a9cd984 verified
{
"epoch": 8.0,
"total_flos": 0.0,
"train_loss": 5009.442099750906,
"train_runtime": 15540.9203,
"train_samples": 17626,
"train_samples_per_second": 9.073,
"train_steps_per_second": 0.142
}