nash_dpo_rank4_iter_2 / train_results.json
YYYYYYibo's picture
Model save
fe74021 verified
raw
history blame
193 Bytes
{
"epoch": 1.0,
"train_loss": 0.6237345188091963,
"train_runtime": 8932.105,
"train_samples": 25000,
"train_samples_per_second": 2.799,
"train_steps_per_second": 0.022
}