lambda-qwen2.5-14b-dpo-test / all_results.json
tanliboy's picture
End of training
96607ee verified
raw
history blame
775 Bytes
{
"epoch": 0.998691442030882,
"eval_logits/chosen": -1.2559658288955688,
"eval_logits/rejected": -1.27387535572052,
"eval_logps/chosen": -737.5234375,
"eval_logps/rejected": -832.0723876953125,
"eval_loss": 0.4919165074825287,
"eval_rewards/accuracies": 0.7400000095367432,
"eval_rewards/chosen": -2.4745123386383057,
"eval_rewards/margins": 0.8984242081642151,
"eval_rewards/rejected": -3.372936964035034,
"eval_runtime": 171.7011,
"eval_samples": 2000,
"eval_samples_per_second": 11.648,
"eval_steps_per_second": 0.728,
"total_flos": 0.0,
"train_loss": 0.5192520058629898,
"train_runtime": 13862.6582,
"train_samples": 61134,
"train_samples_per_second": 4.41,
"train_steps_per_second": 0.034
}