Qwen2.5-1.5B-Open-R1-Distill-bi / train_results.json
a-F1's picture
Model save
d445ca3 verified
raw
history blame contribute delete
198 Bytes
{
"total_flos": 0.0,
"train_loss": 2.0463369701511103,
"train_runtime": 33791.3424,
"train_samples": 16610,
"train_samples_per_second": 0.64,
"train_steps_per_second": 0.08
}