Qwen2.5-1.5B-Open-R1-GRPO-1 / train_results.json
gemelom's picture
Model save
ca94f16 verified
{
"total_flos": 0.0,
"train_loss": 2288579868.0720563,
"train_runtime": 9778.7532,
"train_samples": 1000,
"train_samples_per_second": 0.307,
"train_steps_per_second": 0.077
}