Model: W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919 Source: Original Platform
27 lines
1013 B
JSON
27 lines
1013 B
JSON
{
|
|
"epoch": 0.9989528795811519,
|
|
"eval_KL/chosen_KL_mean": -41.21664810180664,
|
|
"eval_KL/mean": -67.3493423461914,
|
|
"eval_KL/rejected_KL_mean": -93.48201751708984,
|
|
"eval_KL/std": 70.3880615234375,
|
|
"eval_fcm_dpo/beta": 0.0053137075155973434,
|
|
"eval_logits/chosen": 1.460174798965454,
|
|
"eval_logits/rejected": 1.5262725353240967,
|
|
"eval_logps/chosen": -321.63330078125,
|
|
"eval_logps/ref_chosen": -280.41668701171875,
|
|
"eval_logps/ref_rejected": -264.6455383300781,
|
|
"eval_logps/rejected": -358.1275634765625,
|
|
"eval_loss": 0.5907121896743774,
|
|
"eval_margin_dpo/margin_mean": 52.26537322998047,
|
|
"eval_margin_dpo/margin_std": 81.09150695800781,
|
|
"eval_runtime": 88.7294,
|
|
"eval_samples": 2000,
|
|
"eval_samples_per_second": 22.54,
|
|
"eval_steps_per_second": 2.818,
|
|
"total_flos": 0.0,
|
|
"train_loss": 4.881076782754382,
|
|
"train_runtime": 7384.286,
|
|
"train_samples": 61135,
|
|
"train_samples_per_second": 8.279,
|
|
"train_steps_per_second": 0.065
|
|
} |