SELM-Llama-3-8B-Instruct-iter-3 / train_results.json
ZhangShenao's picture
Model save
6c053f3 verified
raw
history blame contribute delete
231 Bytes
{
"epoch": 0.9984301412872841,
"total_flos": 0.0,
"train_loss": 0.5769100609065602,
"train_runtime": 4399.847,
"train_samples": 20378,
"train_samples_per_second": 4.632,
"train_steps_per_second": 0.036
}