{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 1000,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 5.490324960115022,
      "learning_rate": 3.846153846153847e-07,
      "logits/chosen": -1.73323655128479,
      "logits/rejected": -1.963712453842163,
      "logps/chosen": -64.71795654296875,
      "logps/rejected": -92.56527709960938,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.946222324869374,
      "learning_rate": 3.846153846153847e-06,
      "logits/chosen": -1.728408694267273,
      "logits/rejected": -1.9020811319351196,
      "logps/chosen": -72.22079467773438,
      "logps/rejected": -116.01087951660156,
      "loss": 0.6242,
      "rewards/accuracies": 0.6041666865348816,
      "rewards/chosen": -0.08828946202993393,
      "rewards/margins": 0.1939040869474411,
      "rewards/rejected": -0.28219354152679443,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.522682391478169,
      "learning_rate": 4.9519632010080765e-06,
      "logits/chosen": -1.5478551387786865,
      "logits/rejected": -1.8321882486343384,
      "logps/chosen": -64.30168914794922,
      "logps/rejected": -259.0096435546875,
      "loss": 0.4142,
      "rewards/accuracies": 0.768750011920929,
      "rewards/chosen": -0.03247198835015297,
      "rewards/margins": 1.648101806640625,
      "rewards/rejected": -1.6805737018585205,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.068578740455024,
      "learning_rate": 4.721114089947181e-06,
      "logits/chosen": -1.21674382686615,
      "logits/rejected": -1.6157382726669312,
      "logps/chosen": -70.33782958984375,
      "logps/rejected": -497.0357360839844,
      "loss": 0.189,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -0.08688753098249435,
      "rewards/margins": 3.9799323081970215,
      "rewards/rejected": -4.066819667816162,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.22868786429214566,
      "learning_rate": 4.316650805085068e-06,
      "logits/chosen": -1.0377681255340576,
      "logits/rejected": -1.4782741069793701,
      "logps/chosen": -146.58694458007812,
      "logps/rejected": -769.5899658203125,
      "loss": 0.0266,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.891402542591095,
      "rewards/margins": 5.863120079040527,
      "rewards/rejected": -6.754522800445557,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.80554513563544,
      "learning_rate": 3.770188363116324e-06,
      "logits/chosen": -1.2781574726104736,
      "logits/rejected": -1.560027837753296,
      "logps/chosen": -180.29161071777344,
      "logps/rejected": -1096.177001953125,
      "loss": 0.042,
      "rewards/accuracies": 0.981249988079071,
      "rewards/chosen": -1.180869460105896,
      "rewards/margins": 8.900360107421875,
      "rewards/rejected": -10.081230163574219,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.27603672981693994,
      "learning_rate": 3.1244411954180677e-06,
      "logits/chosen": -0.9170042276382446,
      "logits/rejected": -1.313642978668213,
      "logps/chosen": -199.44625854492188,
      "logps/rejected": -1061.7119140625,
      "loss": 0.0072,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.4110476970672607,
      "rewards/margins": 8.259212493896484,
      "rewards/rejected": -9.67026138305664,
      "step": 60
    },
    {
      "epoch": 2.8,
      "grad_norm": 4.0781788867244595,
      "learning_rate": 2.429884359310328e-06,
      "logits/chosen": -1.0711753368377686,
      "logits/rejected": -1.4404046535491943,
      "logps/chosen": -216.3368377685547,
      "logps/rejected": -1323.527587890625,
      "loss": 0.003,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.5303722620010376,
      "rewards/margins": 10.808874130249023,
      "rewards/rejected": -12.33924674987793,
      "step": 70
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.058123220019245296,
      "learning_rate": 1.7408081372259633e-06,
      "logits/chosen": -0.8975645899772644,
      "logits/rejected": -1.296263337135315,
      "logps/chosen": -145.1630859375,
      "logps/rejected": -1060.802734375,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.8476600646972656,
      "rewards/margins": 8.854598045349121,
      "rewards/rejected": -9.702258110046387,
      "step": 80
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.09682108714448862,
      "learning_rate": 1.1110744174509952e-06,
      "logits/chosen": -1.0131741762161255,
      "logits/rejected": -1.4304622411727905,
      "logps/chosen": -159.85574340820312,
      "logps/rejected": -1194.8968505859375,
      "loss": 0.0013,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.978173553943634,
      "rewards/margins": 10.080551147460938,
      "rewards/rejected": -11.058725357055664,
      "step": 90
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.004709132530498062,
      "learning_rate": 5.899065604459814e-07,
      "logits/chosen": -0.9850813150405884,
      "logits/rejected": -1.3841135501861572,
      "logps/chosen": -170.55239868164062,
      "logps/rejected": -1331.4459228515625,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.085587739944458,
      "rewards/margins": 11.312799453735352,
      "rewards/rejected": -12.398386001586914,
      "step": 100
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.004246194962367942,
      "learning_rate": 2.1804183734670277e-07,
      "logits/chosen": -1.1493442058563232,
      "logits/rejected": -1.5497456789016724,
      "logps/chosen": -195.21815490722656,
      "logps/rejected": -1428.41064453125,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.3281663656234741,
      "rewards/margins": 12.071850776672363,
      "rewards/rejected": -13.400018692016602,
      "step": 110
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.010996089792622345,
      "learning_rate": 2.454718665888589e-08,
      "logits/chosen": -1.056302785873413,
      "logits/rejected": -1.4732356071472168,
      "logps/chosen": -179.13990783691406,
      "logps/rejected": -1402.2952880859375,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.1820361614227295,
      "rewards/margins": 11.938187599182129,
      "rewards/rejected": -13.120223999023438,
      "step": 120
    },
    {
      "epoch": 5.0,
      "step": 125,
      "total_flos": 0.0,
      "train_loss": 0.10525495952181518,
      "train_runtime": 12485.2526,
      "train_samples_per_second": 0.641,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "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
}