Files
mistral-7b-base-beta-dpo-hh…/train_results.json

9 lines
217 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 4.511853932745809,
"train_runtime": 2770.5528,
"train_samples": 43598,
"train_samples_per_second": 15.736,
"train_steps_per_second": 0.246
}