Qwen2.5-1.5B-Open-R1-Distill / train_results.json
DeeLearning's picture
Model save
f3667a6 verified
raw
history blame
232 Bytes
{
"epoch": 4.0,
"total_flos": 308009150447616.0,
"train_loss": 0.7185798888728463,
"train_runtime": 4924.3182,
"train_samples": 16610,
"train_samples_per_second": 17.554,
"train_steps_per_second": 0.137
}