llama3-8b-dpo / train_results.json
PeterJinGo's picture
Model save
6d0d94d verified
raw
history blame
218 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 1.1650768583289748,
"train_runtime": 3769.2146,
"train_samples": 61134,
"train_samples_per_second": 16.219,
"train_steps_per_second": 0.127
}