Model: W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 Source: Original Platform
16 lines
597 B
JSON
16 lines
597 B
JSON
{
|
|
"epoch": 0.9989528795811519,
|
|
"eval_logits/chosen": 1.1346925497055054,
|
|
"eval_logits/rejected": 1.1706666946411133,
|
|
"eval_logps/chosen": -313.02630615234375,
|
|
"eval_logps/ref_chosen": -281.4588928222656,
|
|
"eval_logps/ref_rejected": -261.84954833984375,
|
|
"eval_logps/rejected": -342.32696533203125,
|
|
"eval_loss": 0.5572407245635986,
|
|
"eval_margin_dpo/margin_mean": 48.91001510620117,
|
|
"eval_margin_dpo/margin_std": 68.51956176757812,
|
|
"eval_runtime": 92.7227,
|
|
"eval_samples": 2000,
|
|
"eval_samples_per_second": 21.57,
|
|
"eval_steps_per_second": 1.348
|
|
} |