| { | |
| "epoch": 1.0, | |
| "eval_logits/chosen": -0.2205861508846283, | |
| "eval_logits/rejected": 1.0736942291259766, | |
| "eval_logps/chosen": -415.36724853515625, | |
| "eval_logps/rejected": -497.4416198730469, | |
| "eval_loss": 0.7742469906806946, | |
| "eval_rewards/accuracies": 0.773809552192688, | |
| "eval_rewards/chosen": -1.33390212059021, | |
| "eval_rewards/margins": 1.0384857654571533, | |
| "eval_rewards/rejected": -2.3723878860473633, | |
| "eval_runtime": 423.4241, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 4.723, | |
| "eval_steps_per_second": 0.149, | |
| "total_flos": 0.0, | |
| "train_loss": 0.45257438286507334, | |
| "train_runtime": 23936.1745, | |
| "train_samples": 61134, | |
| "train_samples_per_second": 2.554, | |
| "train_steps_per_second": 0.08 | |
| } |