Qwen2.5-R1-Distill-GRPO-em / train_results.json
samitizerxu's picture
Model save
dc9c4a2 verified
raw
history blame contribute delete
201 Bytes
{
"total_flos": 0.0,
"train_loss": 2.769587171291079e-05,
"train_runtime": 35654.1932,
"train_samples": 179,
"train_samples_per_second": 0.005,
"train_steps_per_second": 0.002
}