Model: jackf857/qwen3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.85 Source: Original Platform
23 lines
829 B
JSON
23 lines
829 B
JSON
{
|
|
"epoch": 1.0,
|
|
"eval_fcm_dpo/beta": 0.011290068738162518,
|
|
"eval_logits/chosen": -1.8993860483169556,
|
|
"eval_logits/rejected": -1.5321727991104126,
|
|
"eval_logps/chosen": -239.60226440429688,
|
|
"eval_logps/ref_chosen": -100.49356842041016,
|
|
"eval_logps/ref_rejected": -94.06775665283203,
|
|
"eval_logps/rejected": -292.7149963378906,
|
|
"eval_loss": 0.49325719475746155,
|
|
"eval_margin_dpo/margin_mean": 59.53855895996094,
|
|
"eval_margin_dpo/margin_std": 76.0225830078125,
|
|
"eval_runtime": 43.8024,
|
|
"eval_samples": 2339,
|
|
"eval_samples_per_second": 53.399,
|
|
"eval_steps_per_second": 1.689,
|
|
"total_flos": 0.0,
|
|
"train_loss": 0.9292974616462438,
|
|
"train_runtime": 2239.8819,
|
|
"train_samples": 43598,
|
|
"train_samples_per_second": 19.464,
|
|
"train_steps_per_second": 0.304
|
|
} |