DeepSeek-R1-Distill-Qwen-1.5B-DPO / train_results.json
LuyiCui's picture
Model save
96b27a6 verified
raw
history blame contribute delete
231 Bytes
{
"epoch": 0.9523809523809523,
"total_flos": 0.0,
"train_loss": 0.6895670831203461,
"train_runtime": 273.9395,
"train_samples": 4000,
"train_samples_per_second": 14.602,
"train_steps_per_second": 0.037
}