Files
zephyr-7b-dpo-iter3/train_results.json

9 lines
218 B
JSON
Raw Normal View History

{
"epoch": 2.0,
"total_flos": 0.0,
"train_loss": 0.4729907219554042,
"train_runtime": 6750.8442,
"train_samples": 40756,
"train_samples_per_second": 12.074,
"train_steps_per_second": 0.377
}