Files
qwen3-8b-base-margin-dpo-ul…/train_results.json

9 lines
231 B
JSON
Raw Normal View History

{
"epoch": 0.9989528795811519,
"total_flos": 0.0,
"train_loss": 4.779813265150698,
"train_runtime": 7822.2821,
"train_samples": 61135,
"train_samples_per_second": 7.815,
"train_steps_per_second": 0.061
}