Qwen3-1.7B-MATH-GDPO / train_results.json
wzx111's picture
Model save
eb1d6cf verified
raw
history blame contribute delete
200 Bytes
{
"total_flos": 0.0,
"train_loss": -0.09854654141236097,
"train_runtime": 3102.2738,
"train_samples": 1348,
"train_samples_per_second": 0.869,
"train_steps_per_second": 0.054
}