Model: W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 Source: Original Platform
15 lines
546 B
JSON
15 lines
546 B
JSON
{
|
|
"epoch": 0.9989528795811519,
|
|
"eval_beta_dpo/beta_used": 0.026403456926345825,
|
|
"eval_beta_dpo/beta_used_raw": -0.012573433108627796,
|
|
"eval_beta_dpo/gap_mean": 33.88580322265625,
|
|
"eval_beta_dpo/gap_std": 54.5393180847168,
|
|
"eval_beta_dpo/mask_keep_frac": 1.0,
|
|
"eval_logits/chosen": -0.8373056650161743,
|
|
"eval_logits/rejected": -0.8195577263832092,
|
|
"eval_loss": 0.6150403618812561,
|
|
"eval_runtime": 81.4443,
|
|
"eval_samples": 2000,
|
|
"eval_samples_per_second": 24.557,
|
|
"eval_steps_per_second": 1.535
|
|
} |