{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15808974886784685,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013174145738987238,
      "grad_norm": 0.7230468392372131,
      "learning_rate": 1.25e-07,
      "logits/chosen": 9.993395805358887,
      "logits/rejected": 10.444890022277832,
      "logps/chosen": -0.8203260898590088,
      "logps/rejected": -0.8579692840576172,
      "loss": 1.4012,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -1.6406521797180176,
      "rewards/margins": 0.07528629899024963,
      "rewards/rejected": -1.7159385681152344,
      "step": 1
    },
    {
      "epoch": 0.026348291477974475,
      "grad_norm": 1.0001572370529175,
      "learning_rate": 2.5e-07,
      "logits/chosen": 10.52372932434082,
      "logits/rejected": 10.788372993469238,
      "logps/chosen": -0.8189243078231812,
      "logps/rejected": -0.9178226590156555,
      "loss": 1.2834,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -1.6378486156463623,
      "rewards/margins": 0.19779649376869202,
      "rewards/rejected": -1.835645318031311,
      "step": 2
    },
    {
      "epoch": 0.03952243721696171,
      "grad_norm": 0.979387640953064,
      "learning_rate": 3.75e-07,
      "logits/chosen": 10.042590141296387,
      "logits/rejected": 10.521858215332031,
      "logps/chosen": -0.917183518409729,
      "logps/rejected": -0.9847703576087952,
      "loss": 1.3664,
      "rewards/accuracies": 0.5546875,
      "rewards/chosen": -1.834367036819458,
      "rewards/margins": 0.13517364859580994,
      "rewards/rejected": -1.9695407152175903,
      "step": 3
    },
    {
      "epoch": 0.05269658295594895,
      "grad_norm": 1.867851972579956,
      "learning_rate": 5e-07,
      "logits/chosen": 10.141695022583008,
      "logits/rejected": 10.483091354370117,
      "logps/chosen": -0.8512520790100098,
      "logps/rejected": -0.8865377902984619,
      "loss": 1.4018,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -1.7025041580200195,
      "rewards/margins": 0.0705714151263237,
      "rewards/rejected": -1.7730755805969238,
      "step": 4
    },
    {
      "epoch": 0.06587072869493618,
      "grad_norm": 0.5915809273719788,
      "learning_rate": 6.249999999999999e-07,
      "logits/chosen": 10.462024688720703,
      "logits/rejected": 11.114532470703125,
      "logps/chosen": -0.7721583247184753,
      "logps/rejected": -0.7985925078392029,
      "loss": 1.3829,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -1.5443166494369507,
      "rewards/margins": 0.052868396043777466,
      "rewards/rejected": -1.5971850156784058,
      "step": 5
    },
    {
      "epoch": 0.07904487443392343,
      "grad_norm": 0.6252888441085815,
      "learning_rate": 7.5e-07,
      "logits/chosen": 10.718672752380371,
      "logits/rejected": 11.112823486328125,
      "logps/chosen": -0.8559192419052124,
      "logps/rejected": -0.9305768013000488,
      "loss": 1.3618,
      "rewards/accuracies": 0.5859375,
      "rewards/chosen": -1.7118384838104248,
      "rewards/margins": 0.1493152379989624,
      "rewards/rejected": -1.8611536026000977,
      "step": 6
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": 0.7208986878395081,
      "learning_rate": 8.75e-07,
      "logits/chosen": 9.864439010620117,
      "logits/rejected": 10.09216022491455,
      "logps/chosen": -0.7553099393844604,
      "logps/rejected": -0.8098596930503845,
      "loss": 1.3613,
      "rewards/accuracies": 0.5859375,
      "rewards/chosen": -1.510619878768921,
      "rewards/margins": 0.10909969359636307,
      "rewards/rejected": -1.619719386100769,
      "step": 7
    },
    {
      "epoch": 0.1053931659118979,
      "grad_norm": 1.6331408023834229,
      "learning_rate": 1e-06,
      "logits/chosen": 10.65585994720459,
      "logits/rejected": 11.107338905334473,
      "logps/chosen": -0.774090051651001,
      "logps/rejected": -0.8291972279548645,
      "loss": 1.3462,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -1.548180103302002,
      "rewards/margins": 0.11021438986063004,
      "rewards/rejected": -1.658394455909729,
      "step": 8
    },
    {
      "epoch": 0.11856731165088513,
      "grad_norm": 1.0860488414764404,
      "learning_rate": 9.994504457428556e-07,
      "logits/chosen": 10.446334838867188,
      "logits/rejected": 10.82742691040039,
      "logps/chosen": -0.938445508480072,
      "logps/rejected": -0.8894600868225098,
      "loss": 1.5125,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -1.876891016960144,
      "rewards/margins": -0.09797099232673645,
      "rewards/rejected": -1.7789201736450195,
      "step": 9
    },
    {
      "epoch": 0.13174145738987236,
      "grad_norm": 1.3078101873397827,
      "learning_rate": 9.97802991010949e-07,
      "logits/chosen": 10.292729377746582,
      "logits/rejected": 10.629972457885742,
      "logps/chosen": -0.8660728931427002,
      "logps/rejected": -0.881781280040741,
      "loss": 1.4654,
      "rewards/accuracies": 0.5390625,
      "rewards/chosen": -1.7321457862854004,
      "rewards/margins": 0.0314166434109211,
      "rewards/rejected": -1.763562560081482,
      "step": 10
    },
    {
      "epoch": 0.14491560312885962,
      "grad_norm": 1.0685713291168213,
      "learning_rate": 9.950612572673255e-07,
      "logits/chosen": 10.143664360046387,
      "logits/rejected": 10.639056205749512,
      "logps/chosen": -0.8788573145866394,
      "logps/rejected": -0.9421562552452087,
      "loss": 1.3638,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -1.7577146291732788,
      "rewards/margins": 0.12659788131713867,
      "rewards/rejected": -1.8843125104904175,
      "step": 11
    },
    {
      "epoch": 0.15808974886784685,
      "grad_norm": 0.9801668524742126,
      "learning_rate": 9.912312714377879e-07,
      "logits/chosen": 10.19462776184082,
      "logits/rejected": 10.269098281860352,
      "logps/chosen": -0.8250212669372559,
      "logps/rejected": -0.8715258836746216,
      "loss": 1.3649,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -1.6500425338745117,
      "rewards/margins": 0.09300932288169861,
      "rewards/rejected": -1.7430517673492432,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 12,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}