{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.971563981042654,
  "eval_steps": 500,
  "global_step": 104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 135.46242416026297,
      "learning_rate": 4.545454545454545e-08,
      "logits/chosen": 203.78909301757812,
      "logits/rejected": 182.07696533203125,
      "logps/chosen": -434.955322265625,
      "logps/rejected": -429.50384521484375,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 153.21007203142685,
      "learning_rate": 4.545454545454545e-07,
      "logits/chosen": 172.51792907714844,
      "logits/rejected": 181.91905212402344,
      "logps/chosen": -379.5159912109375,
      "logps/rejected": -448.1414794921875,
      "loss": 0.7124,
      "rewards/accuracies": 0.4861111044883728,
      "rewards/chosen": 0.027371780946850777,
      "rewards/margins": 0.008838895708322525,
      "rewards/rejected": 0.01853288896381855,
      "step": 10
    },
    {
      "epoch": 0.3791469194312796,
      "grad_norm": 142.08069477633126,
      "learning_rate": 4.885348141000122e-07,
      "logits/chosen": 173.6682891845703,
      "logits/rejected": 175.75106811523438,
      "logps/chosen": -381.7967834472656,
      "logps/rejected": -430.2057189941406,
      "loss": 0.6304,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": 0.19567528367042542,
      "rewards/margins": 0.36299628019332886,
      "rewards/rejected": -0.16732101142406464,
      "step": 20
    },
    {
      "epoch": 0.5687203791469194,
      "grad_norm": 120.91669313906786,
      "learning_rate": 4.5025027361734613e-07,
      "logits/chosen": 164.82431030273438,
      "logits/rejected": 173.40679931640625,
      "logps/chosen": -365.9583740234375,
      "logps/rejected": -445.6947326660156,
      "loss": 0.5761,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -1.0274367332458496,
      "rewards/margins": 1.1871185302734375,
      "rewards/rejected": -2.214555263519287,
      "step": 30
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 99.23172159300925,
      "learning_rate": 3.893311157806091e-07,
      "logits/chosen": 170.08607482910156,
      "logits/rejected": 162.03958129882812,
      "logps/chosen": -414.80340576171875,
      "logps/rejected": -454.820556640625,
      "loss": 0.5641,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -2.624403715133667,
      "rewards/margins": 0.9876155853271484,
      "rewards/rejected": -3.6120193004608154,
      "step": 40
    },
    {
      "epoch": 0.9478672985781991,
      "grad_norm": 107.79387973262907,
      "learning_rate": 3.126631330646801e-07,
      "logits/chosen": 177.14224243164062,
      "logits/rejected": 174.7544708251953,
      "logps/chosen": -459.03759765625,
      "logps/rejected": -512.6439208984375,
      "loss": 0.5158,
      "rewards/accuracies": 0.78125,
      "rewards/chosen": -3.4753570556640625,
      "rewards/margins": 1.3291194438934326,
      "rewards/rejected": -4.804476737976074,
      "step": 50
    },
    {
      "epoch": 1.1374407582938388,
      "grad_norm": 53.02406081573369,
      "learning_rate": 2.2891223348923882e-07,
      "logits/chosen": 167.0361328125,
      "logits/rejected": 171.70101928710938,
      "logps/chosen": -414.3773498535156,
      "logps/rejected": -524.4793701171875,
      "loss": 0.3097,
      "rewards/accuracies": 0.8687499761581421,
      "rewards/chosen": -3.200485944747925,
      "rewards/margins": 2.440056085586548,
      "rewards/rejected": -5.6405415534973145,
      "step": 60
    },
    {
      "epoch": 1.3270142180094786,
      "grad_norm": 62.10149124492704,
      "learning_rate": 1.4754491880085317e-07,
      "logits/chosen": 157.87100219726562,
      "logits/rejected": 165.49331665039062,
      "logps/chosen": -453.851318359375,
      "logps/rejected": -509.77960205078125,
      "loss": 0.2085,
      "rewards/accuracies": 0.956250011920929,
      "rewards/chosen": -3.4425768852233887,
      "rewards/margins": 2.912635326385498,
      "rewards/rejected": -6.355212211608887,
      "step": 70
    },
    {
      "epoch": 1.5165876777251186,
      "grad_norm": 92.48557214337542,
      "learning_rate": 7.775827023107834e-08,
      "logits/chosen": 155.17611694335938,
      "logits/rejected": 170.6410369873047,
      "logps/chosen": -473.2515563964844,
      "logps/rejected": -549.7650146484375,
      "loss": 0.187,
      "rewards/accuracies": 0.9312499761581421,
      "rewards/chosen": -3.7577788829803467,
      "rewards/margins": 2.7696285247802734,
      "rewards/rejected": -6.527407646179199,
      "step": 80
    },
    {
      "epoch": 1.7061611374407581,
      "grad_norm": 50.507688635772325,
      "learning_rate": 2.7440387297912122e-08,
      "logits/chosen": 160.5852508544922,
      "logits/rejected": 169.7069854736328,
      "logps/chosen": -444.99725341796875,
      "logps/rejected": -585.0924072265625,
      "loss": 0.1675,
      "rewards/accuracies": 0.96875,
      "rewards/chosen": -3.7263991832733154,
      "rewards/margins": 3.2523887157440186,
      "rewards/rejected": -6.97878885269165,
      "step": 90
    },
    {
      "epoch": 1.8957345971563981,
      "grad_norm": 44.901315947621455,
      "learning_rate": 2.27878296044029e-09,
      "logits/chosen": 160.45559692382812,
      "logits/rejected": 161.6788330078125,
      "logps/chosen": -444.6620178222656,
      "logps/rejected": -523.9886474609375,
      "loss": 0.1723,
      "rewards/accuracies": 0.9437500238418579,
      "rewards/chosen": -3.935753583908081,
      "rewards/margins": 3.035583734512329,
      "rewards/rejected": -6.971337795257568,
      "step": 100
    },
    {
      "epoch": 1.971563981042654,
      "step": 104,
      "total_flos": 0.0,
      "train_loss": 0.39618923515081406,
      "train_runtime": 6217.6844,
      "train_samples_per_second": 2.171,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 104,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}