Files
Qwen2.5-1.5B-DPO-Tulu3-deco…/train_results.json

9 lines
219 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 2.9490895759331788,
"train_runtime": 4813.8824,
"train_samples": 272585,
"train_samples_per_second": 56.625,
"train_steps_per_second": 0.442
}