RubricRM-8B-Judge-v2 / train_results.json
lliutianc's picture
upload curated artifacts (no checkpoint-* / logs / trainer_state) (batch 1/1)
4a88f57 verified
raw
history blame contribute delete
204 Bytes
{
"epoch": 1.0,
"total_flos": 433769168437248.0,
"train_loss": 0.5062215363358648,
"train_runtime": 20851.2905,
"train_samples_per_second": 4.008,
"train_steps_per_second": 0.063
}