all_results.json

{
    "epoch": 2.9976381672177608,
    "eval_dpo_loss": 0.918109118938446,
    "eval_dpo_wo_beta": -6.42689847946167,
    "eval_logits": -2.2913548946380615,
    "eval_logps": -122.37532806396484,
    "eval_loss": 0.8842386603355408,
    "eval_objective": 0.918109118938446,
    "eval_ranking_idealized": 0.6045548915863037,
    "eval_ranking_idealized_expo": 0.5279502868652344,
    "eval_ranking_simple": 0.5641822218894958,
    "eval_regularize": 0.918109118938446,
    "eval_runtime": 319.8808,
    "eval_samples": 5790,
    "eval_samples_per_second": 18.1,
    "eval_steps_per_second": 1.51,
    "total_flos": 0.0,
    "train_loss": 0.022545777056648425,
    "train_runtime": 4386.5835,
    "train_samples": 50802,
    "train_samples_per_second": 34.744,
    "train_steps_per_second": 0.241
}