DeepSeek-R1-Distill-Qwen-7B-S / train_results.json
leonMW's picture
Model save
fbfe451 verified
raw
history blame contribute delete
184 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 2.3434,
"train_samples": 3000,
"train_samples_per_second": 2560.359,
"train_steps_per_second": 78.518
}