Model: W-61/qwen3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 Source: Original Platform
15 lines
545 B
JSON
15 lines
545 B
JSON
{
|
|
"epoch": 0.9989528795811519,
|
|
"eval_beta_dpo/beta_used": 0.023646250367164612,
|
|
"eval_beta_dpo/beta_used_raw": -0.006221401505172253,
|
|
"eval_beta_dpo/gap_mean": 26.59384536743164,
|
|
"eval_beta_dpo/gap_std": 42.75540542602539,
|
|
"eval_beta_dpo/mask_keep_frac": 1.0,
|
|
"eval_logits/chosen": 1.3843175172805786,
|
|
"eval_logits/rejected": 1.4058036804199219,
|
|
"eval_loss": 0.5907628536224365,
|
|
"eval_runtime": 92.1432,
|
|
"eval_samples": 2000,
|
|
"eval_samples_per_second": 21.705,
|
|
"eval_steps_per_second": 1.357
|
|
} |