{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 53,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "debug/losses": 0.17192834615707397,
      "debug/policy_weights": 0.24804016947746277,
      "debug/raw_losses": 0.6931471824645996,
      "epoch": 0.018867924528301886,
      "grad_norm": 3.079222482298495,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": -2.855412006378174,
      "logits/rejected": -2.8797199726104736,
      "logps/chosen": -320.43853759765625,
      "logps/rejected": -340.07073974609375,
      "loss": 0.2116,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "debug/losses": 0.20364493131637573,
      "debug/policy_weights": 0.2948070466518402,
      "debug/raw_losses": 0.6907545924186707,
      "epoch": 0.18867924528301888,
      "grad_norm": 3.193404567956391,
      "learning_rate": 4.911172937635942e-07,
      "logits/chosen": -2.865929126739502,
      "logits/rejected": -2.8918821811676025,
      "logps/chosen": -305.75299072265625,
      "logps/rejected": -332.2339172363281,
      "loss": 0.2033,
      "rewards/accuracies": 0.5069444179534912,
      "rewards/chosen": 0.0007104460964910686,
      "rewards/margins": 0.004878002218902111,
      "rewards/rejected": -0.0041675567626953125,
      "step": 10
    },
    {
      "debug/losses": 0.2036052942276001,
      "debug/policy_weights": 0.3014451563358307,
      "debug/raw_losses": 0.6749827265739441,
      "epoch": 0.37735849056603776,
      "grad_norm": 3.0715644454401403,
      "learning_rate": 3.982949361823388e-07,
      "logits/chosen": -2.8559136390686035,
      "logits/rejected": -2.8577218055725098,
      "logps/chosen": -324.2321472167969,
      "logps/rejected": -331.00140380859375,
      "loss": 0.2069,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": 0.003850350622087717,
      "rewards/margins": 0.040756504982709885,
      "rewards/rejected": -0.036906156688928604,
      "step": 20
    },
    {
      "debug/losses": 0.2083912342786789,
      "debug/policy_weights": 0.3206340968608856,
      "debug/raw_losses": 0.6488931775093079,
      "epoch": 0.5660377358490566,
      "grad_norm": 3.2842987687808507,
      "learning_rate": 2.416462557480814e-07,
      "logits/chosen": -2.839723825454712,
      "logits/rejected": -2.842979907989502,
      "logps/chosen": -298.1597595214844,
      "logps/rejected": -313.3924560546875,
      "loss": 0.2009,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": -0.01345623005181551,
      "rewards/margins": 0.11617596447467804,
      "rewards/rejected": -0.12963220477104187,
      "step": 30
    },
    {
      "debug/losses": 0.18273566663265228,
      "debug/policy_weights": 0.3026610016822815,
      "debug/raw_losses": 0.5847629904747009,
      "epoch": 0.7547169811320755,
      "grad_norm": 2.7988373684679493,
      "learning_rate": 8.859303711029939e-08,
      "logits/chosen": -2.8427796363830566,
      "logits/rejected": -2.839672327041626,
      "logps/chosen": -290.6694641113281,
      "logps/rejected": -320.8838806152344,
      "loss": 0.1964,
      "rewards/accuracies": 0.737500011920929,
      "rewards/chosen": -0.011360697448253632,
      "rewards/margins": 0.3060683310031891,
      "rewards/rejected": -0.3174290060997009,
      "step": 40
    },
    {
      "debug/losses": 0.23139193654060364,
      "debug/policy_weights": 0.35352057218551636,
      "debug/raw_losses": 0.6475176811218262,
      "epoch": 0.9433962264150944,
      "grad_norm": 3.0097008369658336,
      "learning_rate": 5.009573740853313e-09,
      "logits/chosen": -2.877237319946289,
      "logits/rejected": -2.864227533340454,
      "logps/chosen": -282.114501953125,
      "logps/rejected": -316.05438232421875,
      "loss": 0.1937,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.02784130536019802,
      "rewards/margins": 0.15437331795692444,
      "rewards/rejected": -0.1822146326303482,
      "step": 50
    },
    {
      "epoch": 1.0,
      "step": 53,
      "total_flos": 0.0,
      "train_loss": 0.2009538251836345,
      "train_runtime": 384.7218,
      "train_samples_per_second": 17.545,
      "train_steps_per_second": 0.138
    }
  ],
  "logging_steps": 10,
  "max_steps": 53,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}