nash_dpo_rank4_on_vanilla_iter_1 / train_results.json
YYYYYYibo's picture
Model save
5ef9bc7 verified
raw
history blame
No virus
193 Bytes
{
"epoch": 1.0,
"train_loss": 0.6885996239307599,
"train_runtime": 7326.9096,
"train_samples": 20000,
"train_samples_per_second": 2.73,
"train_steps_per_second": 0.021
}