Files
llama-3-8b-base-margin-dpo-…/train_results.json

9 lines
218 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.4133688477908864,
"train_runtime": 1436.8705,
"train_samples": 43598,
"train_samples_per_second": 30.342,
"train_steps_per_second": 0.237
}