Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
cameronphchen's picture
Model save
2c24b82 verified
raw
history blame contribute delete
196 Bytes
{
"total_flos": 0.0,
"train_loss": 0.11724991016089917,
"train_runtime": 482.6536,
"train_samples": 16,
"train_samples_per_second": 0.332,
"train_steps_per_second": 0.021
}