Model: W-61/llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260421-213851 Source: Original Platform
26 lines
980 B
JSON
26 lines
980 B
JSON
{
|
|
"epoch": 0.999244142101285,
|
|
"eval_fcm_dpo/beta": 0.012392759323120117,
|
|
"eval_fcm_dpo/delta": 0.0019851326942443848,
|
|
"eval_fcm_dpo/margin": 47.219032287597656,
|
|
"eval_fcm_dpo/q_t": 0.38107597827911377,
|
|
"eval_logits/chosen": 0.6821600794792175,
|
|
"eval_logits/rejected": 0.6312314867973328,
|
|
"eval_logps/chosen": -177.92359924316406,
|
|
"eval_logps/ref_chosen": -74.85946655273438,
|
|
"eval_logps/ref_rejected": -79.54898834228516,
|
|
"eval_logps/rejected": -229.83216857910156,
|
|
"eval_loss": 0.5434512495994568,
|
|
"eval_margin_dpo/margin_mean": 47.219032287597656,
|
|
"eval_margin_dpo/margin_std": 76.86046600341797,
|
|
"eval_runtime": 38.3131,
|
|
"eval_samples": 2303,
|
|
"eval_samples_per_second": 60.11,
|
|
"eval_steps_per_second": 1.879,
|
|
"total_flos": 0.0,
|
|
"train_loss": 1.103111317586971,
|
|
"train_runtime": 1749.744,
|
|
"train_samples": 42336,
|
|
"train_samples_per_second": 24.196,
|
|
"train_steps_per_second": 0.378
|
|
} |