two_agent_1_epoch_2_rdpo_iter_6 / train_results.json
YYYYYYibo's picture
Model save
811d9fc verified
raw
history blame contribute delete
194 Bytes
{
"epoch": 1.0,
"train_loss": 0.688920441902045,
"train_runtime": 33857.0653,
"train_samples": 21135,
"train_samples_per_second": 0.624,
"train_steps_per_second": 0.005
}