all_results.json

{
    "epoch": 0.9880609304240429,
    "eval_logits/chosen": 9.224187850952148,
    "eval_logits/rejected": 10.039901733398438,
    "eval_logps/chosen": -0.3674238324165344,
    "eval_logps/rejected": -0.3802245259284973,
    "eval_loss": 1.378309726715088,
    "eval_rewards/accuracies": 0.5407407283782959,
    "eval_rewards/chosen": -0.7348476648330688,
    "eval_rewards/margins": 0.025601468980312347,
    "eval_rewards/rejected": -0.7604490518569946,
    "eval_runtime": 153.1014,
    "eval_samples": 1080,
    "eval_samples_per_second": 7.054,
    "eval_steps_per_second": 1.764,
    "total_flos": 0.0,
    "train_loss": 1.3904367176691692,
    "train_runtime": 8038.3927,
    "train_samples": 9715,
    "train_samples_per_second": 1.209,
    "train_steps_per_second": 0.009
}