two_agent_1_rdpo_iter_3 / all_results.json
YYYYYYibo's picture
Model save
bae8ef4 verified
raw
history blame contribute delete
195 Bytes
{
"epoch": 1.0,
"train_loss": 0.6794387264016234,
"train_runtime": 24793.2905,
"train_samples": 21135,
"train_samples_per_second": 0.852,
"train_steps_per_second": 0.007
}