Files
llama-3-8b-base-beta-dpo-ul…/all_results.json

21 lines
742 B
JSON
Raw Permalink Normal View History

{
"epoch": 0.9989528795811519,
"eval_beta_dpo/beta_used": 0.12717531621456146,
"eval_beta_dpo/beta_used_raw": 0.07513566315174103,
"eval_beta_dpo/gap_mean": 16.700754165649414,
"eval_beta_dpo/gap_std": 26.765077590942383,
"eval_beta_dpo/mask_keep_frac": 1.0,
"eval_logits/chosen": -0.787127673625946,
"eval_logits/rejected": -0.7806017398834229,
"eval_loss": 0.7446804642677307,
"eval_runtime": 50.7623,
"eval_samples": 2000,
"eval_samples_per_second": 39.399,
"eval_steps_per_second": 0.63,
"total_flos": 0.0,
"train_loss": 1.1642480231431045,
"train_runtime": 4421.8255,
"train_samples": 61135,
"train_samples_per_second": 13.826,
"train_steps_per_second": 0.108
}