Files
qwen3-8b-base-kto-ultrafeed…/train_results.json

9 lines
220 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 1.4430672781629712,
"train_runtime": 11696.6719,
"train_samples": 122270,
"train_samples_per_second": 10.453,
"train_steps_per_second": 0.082
}