{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 200,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 359.8308330892111,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -3.0665292739868164,
      "logits/real": -2.8827080726623535,
      "logps/generated": -260.97100830078125,
      "logps/real": -154.1412811279297,
      "loss": 0.8446,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 14.829707235996306,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -3.019892454147339,
      "logits/real": -2.6373720169067383,
      "logps/generated": -281.0638732910156,
      "logps/real": -134.65234375,
      "loss": 0.2963,
      "rewards/accuracies": 0.8888888955116272,
      "rewards/generated": -3.8116445541381836,
      "rewards/margins": 5.251079082489014,
      "rewards/real": 1.4394347667694092,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.2891537123618362,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -3.0050318241119385,
      "logits/real": -2.69225811958313,
      "logps/generated": -310.45654296875,
      "logps/real": -124.5722885131836,
      "loss": 0.1097,
      "rewards/accuracies": 1.0,
      "rewards/generated": -7.0854997634887695,
      "rewards/margins": 10.399068832397461,
      "rewards/real": 3.313570499420166,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.1473555762335221,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -3.005507707595825,
      "logits/real": -2.8163156509399414,
      "logps/generated": -333.9879150390625,
      "logps/real": -110.40803527832031,
      "loss": 0.1041,
      "rewards/accuracies": 1.0,
      "rewards/generated": -8.524462699890137,
      "rewards/margins": 12.605262756347656,
      "rewards/real": 4.080801486968994,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.345996994857361,
      "learning_rate": 2e-07,
      "logits/generated": -3.0229580402374268,
      "logits/real": -2.770540952682495,
      "logps/generated": -343.5229797363281,
      "logps/real": -96.39772033691406,
      "loss": 0.1087,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.872434616088867,
      "rewards/margins": 13.813318252563477,
      "rewards/real": 3.9408836364746094,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.2324237659279247,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -2.993199586868286,
      "logits/real": -2.768155574798584,
      "logps/generated": -336.2699279785156,
      "logps/real": -97.20591735839844,
      "loss": 0.0994,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.705252647399902,
      "rewards/margins": 13.57763671875,
      "rewards/real": 3.872384548187256,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.978037812560663,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -3.0415966510772705,
      "logits/real": -2.78061580657959,
      "logps/generated": -337.62353515625,
      "logps/real": -109.2850341796875,
      "loss": 0.1025,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.384114265441895,
      "rewards/margins": 13.61937141418457,
      "rewards/real": 4.235257625579834,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.1436174963751147,
      "train_runtime": 742.9089,
      "train_samples_per_second": 2.692,
      "train_steps_per_second": 0.083
    }
  ],
  "logging_steps": 10,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}