RubricRM-4B-Judge / train_results.json
lliutianc's picture
upload curated artifacts (no checkpoint-* / logs / trainer_state) (batch 1/1)
5c9dec4 verified
raw
history blame contribute delete
202 Bytes
{
"epoch": 1.0,
"total_flos": 76410008076288.0,
"train_loss": 0.3865203571415717,
"train_runtime": 4256.8868,
"train_samples_per_second": 5.588,
"train_steps_per_second": 0.087
}