{ "epoch": 3.0, "eval_logits/chosen": -1.3942855596542358, "eval_logits/rejected": -1.1372073888778687, "eval_logps/chosen": -161.14675903320312, "eval_logps/rejected": -345.1051940917969, "eval_loss": 0.02538341097533703, "eval_rewards/accuracies": 0.980555534362793, "eval_rewards/chosen": -6.990954399108887, "eval_rewards/margins": 20.509109497070312, "eval_rewards/rejected": -27.500062942504883, "eval_runtime": 49.4371, "eval_samples": 2862, "eval_samples_per_second": 57.892, "eval_steps_per_second": 1.82, "train_loss": 0.026962732661432107, "train_runtime": 14195.2291, "train_samples": 140201, "train_samples_per_second": 29.63, "train_steps_per_second": 0.463 }