{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15991471215351813,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010660980810234541,
      "grad_norm": 0.051327500492334366,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.755006790161133,
      "logits/rejected": 14.735244750976562,
      "logps/chosen": -0.29377540946006775,
      "logps/rejected": -0.30969956517219543,
      "loss": 0.952,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.44066309928894043,
      "rewards/margins": 0.023886267095804214,
      "rewards/rejected": -0.46454939246177673,
      "step": 10
    },
    {
      "epoch": 0.021321961620469083,
      "grad_norm": 0.04346882924437523,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.513801574707031,
      "logits/rejected": 14.946454048156738,
      "logps/chosen": -0.27995699644088745,
      "logps/rejected": -0.30138006806373596,
      "loss": 0.9726,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.4199354648590088,
      "rewards/margins": 0.03213457390666008,
      "rewards/rejected": -0.45207005739212036,
      "step": 20
    },
    {
      "epoch": 0.031982942430703626,
      "grad_norm": 0.05228634551167488,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.266324043273926,
      "logits/rejected": 14.423965454101562,
      "logps/chosen": -0.2919609546661377,
      "logps/rejected": -0.32358455657958984,
      "loss": 0.9622,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.43794146180152893,
      "rewards/margins": 0.047435395419597626,
      "rewards/rejected": -0.48537683486938477,
      "step": 30
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 0.05487598106265068,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.965211868286133,
      "logits/rejected": 15.058088302612305,
      "logps/chosen": -0.277716726064682,
      "logps/rejected": -0.3055034577846527,
      "loss": 0.9403,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": -0.4165751039981842,
      "rewards/margins": 0.04168009012937546,
      "rewards/rejected": -0.4582551419734955,
      "step": 40
    },
    {
      "epoch": 0.053304904051172705,
      "grad_norm": 0.057255037128925323,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.539288520812988,
      "logits/rejected": 15.174041748046875,
      "logps/chosen": -0.26362231373786926,
      "logps/rejected": -0.3325727581977844,
      "loss": 0.9588,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.3954334557056427,
      "rewards/margins": 0.10342560708522797,
      "rewards/rejected": -0.49885907769203186,
      "step": 50
    },
    {
      "epoch": 0.053304904051172705,
      "eval_logits/chosen": 14.618952751159668,
      "eval_logits/rejected": 15.176809310913086,
      "eval_logps/chosen": -0.2685677409172058,
      "eval_logps/rejected": -0.3283654451370239,
      "eval_loss": 0.9551004767417908,
      "eval_rewards/accuracies": 0.5131579041481018,
      "eval_rewards/chosen": -0.4028516113758087,
      "eval_rewards/margins": 0.08969658613204956,
      "eval_rewards/rejected": -0.4925481975078583,
      "eval_runtime": 21.4453,
      "eval_samples_per_second": 28.305,
      "eval_steps_per_second": 3.544,
      "step": 50
    },
    {
      "epoch": 0.06396588486140725,
      "grad_norm": 0.05227242782711983,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.787714004516602,
      "logits/rejected": 15.379422187805176,
      "logps/chosen": -0.3143109679222107,
      "logps/rejected": -0.3425135612487793,
      "loss": 0.9636,
      "rewards/accuracies": 0.4625000059604645,
      "rewards/chosen": -0.4714665412902832,
      "rewards/margins": 0.042303841561079025,
      "rewards/rejected": -0.513770341873169,
      "step": 60
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 0.0658508762717247,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 15.149365425109863,
      "logits/rejected": 15.115835189819336,
      "logps/chosen": -0.31501108407974243,
      "logps/rejected": -0.2854115962982178,
      "loss": 0.9677,
      "rewards/accuracies": 0.36250001192092896,
      "rewards/chosen": -0.47251659631729126,
      "rewards/margins": -0.04439922422170639,
      "rewards/rejected": -0.4281173646450043,
      "step": 70
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 0.06567618995904922,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 15.393908500671387,
      "logits/rejected": 15.454248428344727,
      "logps/chosen": -0.31166282296180725,
      "logps/rejected": -0.3178747594356537,
      "loss": 0.9609,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": -0.4674941897392273,
      "rewards/margins": 0.009317949414253235,
      "rewards/rejected": -0.47681212425231934,
      "step": 80
    },
    {
      "epoch": 0.09594882729211088,
      "grad_norm": 0.07566913962364197,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 15.229632377624512,
      "logits/rejected": 15.477168083190918,
      "logps/chosen": -0.3294064998626709,
      "logps/rejected": -0.3528878390789032,
      "loss": 0.9587,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.49410971999168396,
      "rewards/margins": 0.03522203490138054,
      "rewards/rejected": -0.5293318033218384,
      "step": 90
    },
    {
      "epoch": 0.10660980810234541,
      "grad_norm": 0.09082464128732681,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 14.481330871582031,
      "logits/rejected": 15.092982292175293,
      "logps/chosen": -0.2656436562538147,
      "logps/rejected": -0.33982905745506287,
      "loss": 0.9548,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.39846545457839966,
      "rewards/margins": 0.11127817630767822,
      "rewards/rejected": -0.5097435712814331,
      "step": 100
    },
    {
      "epoch": 0.10660980810234541,
      "eval_logits/chosen": 14.7100830078125,
      "eval_logits/rejected": 15.274725914001465,
      "eval_logps/chosen": -0.26462864875793457,
      "eval_logps/rejected": -0.331702321767807,
      "eval_loss": 0.947841465473175,
      "eval_rewards/accuracies": 0.5394737124443054,
      "eval_rewards/chosen": -0.39694297313690186,
      "eval_rewards/margins": 0.10061051696538925,
      "eval_rewards/rejected": -0.4975534677505493,
      "eval_runtime": 21.4421,
      "eval_samples_per_second": 28.309,
      "eval_steps_per_second": 3.544,
      "step": 100
    },
    {
      "epoch": 0.11727078891257996,
      "grad_norm": 0.20198923349380493,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 14.932653427124023,
      "logits/rejected": 15.476409912109375,
      "logps/chosen": -0.27830976247787476,
      "logps/rejected": -0.34150317311286926,
      "loss": 0.9487,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.41746464371681213,
      "rewards/margins": 0.09479012340307236,
      "rewards/rejected": -0.5122548341751099,
      "step": 110
    },
    {
      "epoch": 0.1279317697228145,
      "grad_norm": 0.31938356161117554,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 15.280967712402344,
      "logits/rejected": 15.5416259765625,
      "logps/chosen": -0.2816022038459778,
      "logps/rejected": -0.3262938857078552,
      "loss": 0.9483,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.4224032461643219,
      "rewards/margins": 0.06703753769397736,
      "rewards/rejected": -0.48944082856178284,
      "step": 120
    },
    {
      "epoch": 0.13859275053304904,
      "grad_norm": 0.12567812204360962,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 14.967382431030273,
      "logits/rejected": 15.351877212524414,
      "logps/chosen": -0.3148510456085205,
      "logps/rejected": -0.3488944172859192,
      "loss": 0.957,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.47227659821510315,
      "rewards/margins": 0.05106503888964653,
      "rewards/rejected": -0.5233416557312012,
      "step": 130
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.09151162207126617,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 14.900466918945312,
      "logits/rejected": 15.075350761413574,
      "logps/chosen": -0.2766302227973938,
      "logps/rejected": -0.312236487865448,
      "loss": 0.9373,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": -0.4149452745914459,
      "rewards/margins": 0.05340944975614548,
      "rewards/rejected": -0.4683547616004944,
      "step": 140
    },
    {
      "epoch": 0.15991471215351813,
      "grad_norm": 0.1259378045797348,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 14.528109550476074,
      "logits/rejected": 14.861102104187012,
      "logps/chosen": -0.2683579921722412,
      "logps/rejected": -0.33838269114494324,
      "loss": 0.9388,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.40253695845603943,
      "rewards/margins": 0.10503707826137543,
      "rewards/rejected": -0.5075740218162537,
      "step": 150
    },
    {
      "epoch": 0.15991471215351813,
      "eval_logits/chosen": 14.12246036529541,
      "eval_logits/rejected": 14.733266830444336,
      "eval_logps/chosen": -0.2611957788467407,
      "eval_logps/rejected": -0.3492279350757599,
      "eval_loss": 0.9302574396133423,
      "eval_rewards/accuracies": 0.5657894611358643,
      "eval_rewards/chosen": -0.3917936384677887,
      "eval_rewards/margins": 0.13204820454120636,
      "eval_rewards/rejected": -0.5238418579101562,
      "eval_runtime": 21.4406,
      "eval_samples_per_second": 28.311,
      "eval_steps_per_second": 3.545,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.602224826757939e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}