Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Model save
a3f00a6 verified
raw
history blame contribute delete
216 Bytes
{
"epoch": 8.0,
"total_flos": 0.0,
"train_loss": 4648.314686650815,
"train_runtime": 15546.5095,
"train_samples": 17626,
"train_samples_per_second": 9.07,
"train_steps_per_second": 0.142
}