File size: 2,814 Bytes
28847d8
 
 
 
 
1
2
3
4
5
6
{"ts": "2025-12-26T16:09:16", "event": "eval", "step": 25, "epoch": 0.029197080291970802, "eval_loss": 0.6836819648742676, "eval_runtime": 454.4375, "eval_samples_per_second": 1.677, "eval_steps_per_second": 1.677, "eval_rewards/chosen": 0.024636391550302505, "eval_rewards/rejected": 0.005080964416265488, "eval_rewards/accuracies": 0.665354311466217, "eval_rewards/margins": 0.019555427134037018, "eval_logps/chosen": -370.1607666015625, "eval_logps/rejected": -395.7251892089844, "eval_logits/chosen": 5.295141220092773, "eval_logits/rejected": 5.345211029052734}
{"ts": "2025-12-26T16:20:56", "event": "eval", "step": 50, "epoch": 0.058394160583941604, "eval_loss": 0.4610801041126251, "eval_runtime": 454.5598, "eval_samples_per_second": 1.676, "eval_steps_per_second": 1.676, "eval_rewards/chosen": 0.8944254517555237, "eval_rewards/rejected": 0.3205168545246124, "eval_rewards/accuracies": 0.9619422554969788, "eval_rewards/margins": 0.5739086270332336, "eval_logps/chosen": -361.462890625, "eval_logps/rejected": -392.5708312988281, "eval_logits/chosen": 5.22359037399292, "eval_logits/rejected": 5.286833763122559}
{"ts": "2025-12-26T16:32:39", "event": "eval", "step": 75, "epoch": 0.08759124087591241, "eval_loss": 0.16020436584949493, "eval_runtime": 454.3435, "eval_samples_per_second": 1.677, "eval_steps_per_second": 1.677, "eval_rewards/chosen": 1.1210675239562988, "eval_rewards/rejected": -0.9336051344871521, "eval_rewards/accuracies": 0.9960629940032959, "eval_rewards/margins": 2.0546727180480957, "eval_logps/chosen": -359.19647216796875, "eval_logps/rejected": -405.1120300292969, "eval_logits/chosen": 4.930174827575684, "eval_logits/rejected": 5.032296657562256}
{"ts": "2025-12-26T16:44:21", "event": "eval", "step": 100, "epoch": 0.11678832116788321, "eval_loss": 0.04428481683135033, "eval_runtime": 454.7251, "eval_samples_per_second": 1.676, "eval_steps_per_second": 1.676, "eval_rewards/chosen": 1.7248634099960327, "eval_rewards/rejected": -2.863647222518921, "eval_rewards/accuracies": 0.9921259880065918, "eval_rewards/margins": 4.588510513305664, "eval_logps/chosen": -353.15850830078125, "eval_logps/rejected": -424.4124755859375, "eval_logits/chosen": 4.285891056060791, "eval_logits/rejected": 4.425926208496094}
{"ts": "2025-12-26T16:56:05", "event": "eval", "step": 125, "epoch": 0.145985401459854, "eval_loss": 0.024107323959469795, "eval_runtime": 454.8045, "eval_samples_per_second": 1.675, "eval_steps_per_second": 1.675, "eval_rewards/chosen": 0.5319492816925049, "eval_rewards/rejected": -6.150709629058838, "eval_rewards/accuracies": 0.9934383034706116, "eval_rewards/margins": 6.682660102844238, "eval_logps/chosen": -365.087646484375, "eval_logps/rejected": -457.28314208984375, "eval_logits/chosen": 3.6694726943969727, "eval_logits/rejected": 3.8436598777770996}