zephyr-7b-gpo-v4-i2 / train_results.json
lole25's picture
Model save
bc4c4d5 verified
{
"epoch": 1.0,
"train_loss": 0.07767095326809656,
"train_runtime": 21725.9611,
"train_samples": 21000,
"train_samples_per_second": 0.967,
"train_steps_per_second": 0.242
}