Qwen-2.5-7B-Simple-RL-debug / train_results.json
alterego238's picture
Model save
841231f verified
raw
history blame contribute delete
197 Bytes
{
"total_flos": 0.0,
"train_loss": -0.062465423718094826,
"train_runtime": 165.9317,
"train_samples": 8,
"train_samples_per_second": 0.048,
"train_steps_per_second": 0.048
}