{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 436.30790272840835,
      "learning_rate": 3.125e-08,
      "logits/generated": -2.574023723602295,
      "logits/real": -2.507308006286621,
      "logps/generated": -396.6226806640625,
      "logps/real": -228.6820831298828,
      "loss": 1.1036,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06369426751592357,
      "grad_norm": 86.39288206954664,
      "learning_rate": 3.1249999999999997e-07,
      "logits/generated": -2.6174476146698,
      "logits/real": -2.577033042907715,
      "logps/generated": -314.8096923828125,
      "logps/real": -233.916259765625,
      "loss": 0.8432,
      "rewards/accuracies": 0.8055555820465088,
      "rewards/generated": -1.1551631689071655,
      "rewards/margins": 1.29329252243042,
      "rewards/real": 0.13812927901744843,
      "step": 10
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 23.096946473336036,
      "learning_rate": 4.858156028368794e-07,
      "logits/generated": -2.934861421585083,
      "logits/real": -2.8925399780273438,
      "logps/generated": -313.32012939453125,
      "logps/real": -235.418701171875,
      "loss": 0.4872,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.896754741668701,
      "rewards/margins": 6.176419258117676,
      "rewards/real": 2.2796645164489746,
      "step": 20
    },
    {
      "epoch": 0.1910828025477707,
      "grad_norm": 23.454945687282052,
      "learning_rate": 4.50354609929078e-07,
      "logits/generated": -2.9848690032958984,
      "logits/real": -2.9865798950195312,
      "logps/generated": -304.69854736328125,
      "logps/real": -152.80667114257812,
      "loss": 0.3868,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -3.0515201091766357,
      "rewards/margins": 7.164666652679443,
      "rewards/real": 4.113146781921387,
      "step": 30
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": 56.59285724233864,
      "learning_rate": 4.148936170212766e-07,
      "logits/generated": -2.821133852005005,
      "logits/real": -2.894505262374878,
      "logps/generated": -349.6683044433594,
      "logps/real": -201.2012176513672,
      "loss": 0.4438,
      "rewards/accuracies": 1.0,
      "rewards/generated": -5.3700079917907715,
      "rewards/margins": 9.444425582885742,
      "rewards/real": 4.074416637420654,
      "step": 40
    },
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 26.344052963980364,
      "learning_rate": 3.7943262411347514e-07,
      "logits/generated": -3.041593074798584,
      "logits/real": -2.9904277324676514,
      "logps/generated": -335.09942626953125,
      "logps/real": -158.0336151123047,
      "loss": 0.37,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -3.180644989013672,
      "rewards/margins": 8.93952751159668,
      "rewards/real": 5.758882999420166,
      "step": 50
    },
    {
      "epoch": 0.3821656050955414,
      "grad_norm": 47.871426260084256,
      "learning_rate": 3.4397163120567375e-07,
      "logits/generated": -2.9896843433380127,
      "logits/real": -3.0180420875549316,
      "logps/generated": -302.9552307128906,
      "logps/real": -140.7099151611328,
      "loss": 0.3324,
      "rewards/accuracies": 0.9750000238418579,
      "rewards/generated": -3.2430217266082764,
      "rewards/margins": 9.301046371459961,
      "rewards/real": 6.0580244064331055,
      "step": 60
    },
    {
      "epoch": 0.445859872611465,
      "grad_norm": 24.288240218254995,
      "learning_rate": 3.085106382978723e-07,
      "logits/generated": -3.0595779418945312,
      "logits/real": -2.9718518257141113,
      "logps/generated": -328.691650390625,
      "logps/real": -140.92660522460938,
      "loss": 0.333,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -3.642324447631836,
      "rewards/margins": 10.118036270141602,
      "rewards/real": 6.47571325302124,
      "step": 70
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 14.83120429808784,
      "learning_rate": 2.730496453900709e-07,
      "logits/generated": -2.996634006500244,
      "logits/real": -3.0401620864868164,
      "logps/generated": -322.6135559082031,
      "logps/real": -159.5257110595703,
      "loss": 0.3328,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/generated": -2.347047805786133,
      "rewards/margins": 10.133938789367676,
      "rewards/real": 7.786890506744385,
      "step": 80
    },
    {
      "epoch": 0.5732484076433121,
      "grad_norm": 16.65278970025503,
      "learning_rate": 2.375886524822695e-07,
      "logits/generated": -3.0264060497283936,
      "logits/real": -2.979038715362549,
      "logps/generated": -360.536376953125,
      "logps/real": -162.26622009277344,
      "loss": 0.3387,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -4.7210164070129395,
      "rewards/margins": 12.409219741821289,
      "rewards/real": 7.68820333480835,
      "step": 90
    },
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 7.324308799399964,
      "learning_rate": 2.0212765957446807e-07,
      "logits/generated": -2.968139410018921,
      "logits/real": -3.0011098384857178,
      "logps/generated": -325.79107666015625,
      "logps/real": -162.4396514892578,
      "loss": 0.3429,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -2.580188512802124,
      "rewards/margins": 10.546457290649414,
      "rewards/real": 7.966268062591553,
      "step": 100
    },
    {
      "epoch": 0.6369426751592356,
      "eval_logits/generated": -2.6921370029449463,
      "eval_logits/real": -2.418954372406006,
      "eval_logps/generated": -57.74082565307617,
      "eval_logps/real": -16.818851470947266,
      "eval_loss": 1.018080234527588,
      "eval_rewards/accuracies": 0.0812101885676384,
      "eval_rewards/generated": 1.4157419204711914,
      "eval_rewards/margins": 0.06545643508434296,
      "eval_rewards/real": 1.4811984300613403,
      "eval_runtime": 325.124,
      "eval_samples_per_second": 15.379,
      "eval_steps_per_second": 0.483,
      "step": 100
    },
    {
      "epoch": 0.7006369426751592,
      "grad_norm": 44.79401383111945,
      "learning_rate": 1.6666666666666665e-07,
      "logits/generated": -2.966001033782959,
      "logits/real": -2.9780120849609375,
      "logps/generated": -347.74993896484375,
      "logps/real": -158.44979858398438,
      "loss": 0.365,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -3.206289768218994,
      "rewards/margins": 11.313484191894531,
      "rewards/real": 8.107194900512695,
      "step": 110
    },
    {
      "epoch": 0.7643312101910829,
      "grad_norm": 7.15542526632935,
      "learning_rate": 1.3120567375886523e-07,
      "logits/generated": -2.9361348152160645,
      "logits/real": -2.991243839263916,
      "logps/generated": -340.3627014160156,
      "logps/real": -145.40615844726562,
      "loss": 0.3243,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.4838199615478516,
      "rewards/margins": 10.616706848144531,
      "rewards/real": 7.132887363433838,
      "step": 120
    },
    {
      "epoch": 0.8280254777070064,
      "grad_norm": 28.617693401838523,
      "learning_rate": 9.574468085106382e-08,
      "logits/generated": -2.880622386932373,
      "logits/real": -2.873990774154663,
      "logps/generated": -284.91949462890625,
      "logps/real": -130.95306396484375,
      "loss": 0.3022,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -1.7718982696533203,
      "rewards/margins": 8.987956047058105,
      "rewards/real": 7.216057777404785,
      "step": 130
    },
    {
      "epoch": 0.89171974522293,
      "grad_norm": 11.2855453725489,
      "learning_rate": 6.02836879432624e-08,
      "logits/generated": -2.893979549407959,
      "logits/real": -2.919368028640747,
      "logps/generated": -334.3547058105469,
      "logps/real": -154.1964569091797,
      "loss": 0.3389,
      "rewards/accuracies": 0.9750000238418579,
      "rewards/generated": -3.628894090652466,
      "rewards/margins": 11.9329252243042,
      "rewards/real": 8.304032325744629,
      "step": 140
    },
    {
      "epoch": 0.9554140127388535,
      "grad_norm": 31.41907953329688,
      "learning_rate": 2.4822695035460993e-08,
      "logits/generated": -2.864701747894287,
      "logits/real": -2.9138083457946777,
      "logps/generated": -315.903564453125,
      "logps/real": -138.75643920898438,
      "loss": 0.3255,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -2.897620677947998,
      "rewards/margins": 9.965813636779785,
      "rewards/real": 7.068192958831787,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 157,
      "total_flos": 0.0,
      "train_loss": 0.3886139180250229,
      "train_runtime": 1518.6555,
      "train_samples_per_second": 3.292,
      "train_steps_per_second": 0.103
    }
  ],
  "logging_steps": 10,
  "max_steps": 157,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}