OLMoE-1B-7B-0125-Instruct-grpo / train_results.json
chenggong1995's picture
Model save
a9a7e3c verified
raw
history blame contribute delete
195 Bytes
{
"total_flos": 0.0,
"train_loss": -42.93539375066757,
"train_runtime": 225.8365,
"train_samples": 20,
"train_samples_per_second": 0.177,
"train_steps_per_second": 0.009
}