LLaDA-8B-Instruct-DLPO / train_results.json
howey's picture
Model save
0f31650 verified
{
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 1.5902,
"train_samples": 93733,
"train_samples_per_second": 72.319,
"train_steps_per_second": 15.722
}