{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992709599027947,
  "eval_steps": 500,
  "global_step": 257,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038882138517618466,
      "grad_norm": 160.0573020755792,
      "learning_rate": 3.846153846153846e-08,
      "logits/chosen": -0.7651611566543579,
      "logits/rejected": -0.9917968511581421,
      "logps/chosen": -1039.6500244140625,
      "logps/rejected": -269.35626220703125,
      "loss": 0.7032,
      "rewards/accuracies": 0.17109374701976776,
      "rewards/chosen": -0.00718765240162611,
      "rewards/margins": -0.006218528840690851,
      "rewards/rejected": -0.0009794235229492188,
      "step": 10
    },
    {
      "epoch": 0.07776427703523693,
      "grad_norm": 160.5753020431693,
      "learning_rate": 7.692307692307692e-08,
      "logits/chosen": -0.7669433355331421,
      "logits/rejected": -0.991040050983429,
      "logps/chosen": -1027.425048828125,
      "logps/rejected": -273.2875061035156,
      "loss": 0.6959,
      "rewards/accuracies": 0.23593750596046448,
      "rewards/chosen": 0.008073806762695312,
      "rewards/margins": 0.009277725592255592,
      "rewards/rejected": -0.0012153625721111894,
      "step": 20
    },
    {
      "epoch": 0.1166464155528554,
      "grad_norm": 144.69837671419592,
      "learning_rate": 9.992603458948281e-08,
      "logits/chosen": -0.766284167766571,
      "logits/rejected": -0.9904540777206421,
      "logps/chosen": -1034.0250244140625,
      "logps/rejected": -269.0625,
      "loss": 0.6534,
      "rewards/accuracies": 0.4437499940395355,
      "rewards/chosen": 0.06487135589122772,
      "rewards/margins": 0.10399703681468964,
      "rewards/rejected": -0.03914298862218857,
      "step": 30
    },
    {
      "epoch": 0.15552855407047386,
      "grad_norm": 114.38616995997658,
      "learning_rate": 9.909643486313532e-08,
      "logits/chosen": -0.7626953125,
      "logits/rejected": -0.987060546875,
      "logps/chosen": -1035.2249755859375,
      "logps/rejected": -268.70001220703125,
      "loss": 0.5462,
      "rewards/accuracies": 0.81640625,
      "rewards/chosen": 0.22022247314453125,
      "rewards/margins": 0.36003416776657104,
      "rewards/rejected": -0.1398262083530426,
      "step": 40
    },
    {
      "epoch": 0.19441069258809235,
      "grad_norm": 95.18572051179285,
      "learning_rate": 9.73601505145955e-08,
      "logits/chosen": -0.7583252191543579,
      "logits/rejected": -0.9866698980331421,
      "logps/chosen": -1038.300048828125,
      "logps/rejected": -277.33123779296875,
      "loss": 0.4385,
      "rewards/accuracies": 0.983593761920929,
      "rewards/chosen": 0.379730224609375,
      "rewards/margins": 0.663256824016571,
      "rewards/rejected": -0.283303827047348,
      "step": 50
    },
    {
      "epoch": 0.2332928311057108,
      "grad_norm": 58.648166089179284,
      "learning_rate": 9.474924624108548e-08,
      "logits/chosen": -0.7514404058456421,
      "logits/rejected": -0.9781738519668579,
      "logps/chosen": -1039.574951171875,
      "logps/rejected": -274.51873779296875,
      "loss": 0.3168,
      "rewards/accuracies": 0.999218761920929,
      "rewards/chosen": 0.5596984624862671,
      "rewards/margins": 1.0992431640625,
      "rewards/rejected": -0.539135754108429,
      "step": 60
    },
    {
      "epoch": 0.27217496962332927,
      "grad_norm": 38.61380385007199,
      "learning_rate": 9.131193871579974e-08,
      "logits/chosen": -0.740234375,
      "logits/rejected": -0.972973644733429,
      "logps/chosen": -1028.800048828125,
      "logps/rejected": -280.6625061035156,
      "loss": 0.1797,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.835314929485321,
      "rewards/margins": 1.780029296875,
      "rewards/rejected": -0.9450439214706421,
      "step": 70
    },
    {
      "epoch": 0.3110571081409477,
      "grad_norm": 24.436947703379207,
      "learning_rate": 8.71117061502135e-08,
      "logits/chosen": -0.7481689453125,
      "logits/rejected": -0.9714599847793579,
      "logps/chosen": -1023.0499877929688,
      "logps/rejected": -284.95623779296875,
      "loss": 0.1221,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.9628051519393921,
      "rewards/margins": 2.2330079078674316,
      "rewards/rejected": -1.270166039466858,
      "step": 80
    },
    {
      "epoch": 0.34993924665856624,
      "grad_norm": 31.163290960443195,
      "learning_rate": 8.222611601511082e-08,
      "logits/chosen": -0.7407470941543579,
      "logits/rejected": -0.968579113483429,
      "logps/chosen": -1046.9000244140625,
      "logps/rejected": -283.3500061035156,
      "loss": 0.0878,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.033911108970642,
      "rewards/margins": 2.625439405441284,
      "rewards/rejected": -1.591650366783142,
      "step": 90
    },
    {
      "epoch": 0.3888213851761847,
      "grad_norm": 10.132641150484275,
      "learning_rate": 7.674539256930362e-08,
      "logits/chosen": -0.73974609375,
      "logits/rejected": -0.960034191608429,
      "logps/chosen": -1007.0999755859375,
      "logps/rejected": -294.1812438964844,
      "loss": 0.0515,
      "rewards/accuracies": 0.999218761920929,
      "rewards/chosen": 1.075415015220642,
      "rewards/margins": 3.2860350608825684,
      "rewards/rejected": -2.210693359375,
      "step": 100
    },
    {
      "epoch": 0.42770352369380316,
      "grad_norm": 3.381766003891569,
      "learning_rate": 7.077075065009432e-08,
      "logits/chosen": -0.735546886920929,
      "logits/rejected": -0.957446277141571,
      "logps/chosen": -1014.7249755859375,
      "logps/rejected": -305.45623779296875,
      "loss": 0.0199,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.205664038658142,
      "rewards/margins": 4.345410346984863,
      "rewards/rejected": -3.1407227516174316,
      "step": 110
    },
    {
      "epoch": 0.4665856622114216,
      "grad_norm": 2.9204173229145636,
      "learning_rate": 6.441252649607854e-08,
      "logits/chosen": -0.729931652545929,
      "logits/rejected": -0.951171875,
      "logps/chosen": -1013.6749877929688,
      "logps/rejected": -311.09375,
      "loss": 0.0101,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.242578148841858,
      "rewards/margins": 5.182031154632568,
      "rewards/rejected": -3.9403319358825684,
      "step": 120
    },
    {
      "epoch": 0.5054678007290401,
      "grad_norm": 1.4356612196732965,
      "learning_rate": 5.7788140121173145e-08,
      "logits/chosen": -0.7265380620956421,
      "logits/rejected": -0.9493408203125,
      "logps/chosen": -1042.8499755859375,
      "logps/rejected": -315.17498779296875,
      "loss": 0.0053,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3319091796875,
      "rewards/margins": 5.879687309265137,
      "rewards/rejected": -4.5478515625,
      "step": 130
    },
    {
      "epoch": 0.5443499392466585,
      "grad_norm": 1.344341217145263,
      "learning_rate": 5.1019926869570276e-08,
      "logits/chosen": -0.7250732183456421,
      "logits/rejected": -0.9361572265625,
      "logps/chosen": -1033.800048828125,
      "logps/rejected": -322.75,
      "loss": 0.0038,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.329248070716858,
      "rewards/margins": 6.33203125,
      "rewards/rejected": -5.001562595367432,
      "step": 140
    },
    {
      "epoch": 0.583232077764277,
      "grad_norm": 0.5751713296126671,
      "learning_rate": 4.4232878197208657e-08,
      "logits/chosen": -0.720263659954071,
      "logits/rejected": -0.9346923828125,
      "logps/chosen": -1047.300048828125,
      "logps/rejected": -326.04998779296875,
      "loss": 0.0028,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3618042469024658,
      "rewards/margins": 6.713671684265137,
      "rewards/rejected": -5.349413871765137,
      "step": 150
    },
    {
      "epoch": 0.6221142162818954,
      "grad_norm": 0.8087854397697334,
      "learning_rate": 3.75523334017065e-08,
      "logits/chosen": -0.7223144769668579,
      "logits/rejected": -0.9326171875,
      "logps/chosen": -1028.300048828125,
      "logps/rejected": -328.9125061035156,
      "loss": 0.0021,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3705565929412842,
      "rewards/margins": 6.984765529632568,
      "rewards/rejected": -5.613085746765137,
      "step": 160
    },
    {
      "epoch": 0.660996354799514,
      "grad_norm": 1.4449125849513227,
      "learning_rate": 3.1101664928554675e-08,
      "logits/chosen": -0.729809582233429,
      "logits/rejected": -0.9361816644668579,
      "logps/chosen": -1021.7249755859375,
      "logps/rejected": -330.04998779296875,
      "loss": 0.0019,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3477783203125,
      "rewards/margins": 7.177734375,
      "rewards/rejected": -5.828906059265137,
      "step": 170
    },
    {
      "epoch": 0.6998784933171325,
      "grad_norm": 1.1450098797738104,
      "learning_rate": 2.500000000000001e-08,
      "logits/chosen": -0.722607433795929,
      "logits/rejected": -0.932812511920929,
      "logps/chosen": -1011.75,
      "logps/rejected": -328.375,
      "loss": 0.0016,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.342016577720642,
      "rewards/margins": 7.329297065734863,
      "rewards/rejected": -5.984179496765137,
      "step": 180
    },
    {
      "epoch": 0.7387606318347509,
      "grad_norm": 0.43432731079566683,
      "learning_rate": 1.9360020642261153e-08,
      "logits/chosen": -0.7257324457168579,
      "logits/rejected": -0.9291747808456421,
      "logps/chosen": -1048.449951171875,
      "logps/rejected": -332.2875061035156,
      "loss": 0.0021,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.404748558998108,
      "rewards/margins": 7.463281154632568,
      "rewards/rejected": -6.056640625,
      "step": 190
    },
    {
      "epoch": 0.7776427703523694,
      "grad_norm": 0.42312272714084886,
      "learning_rate": 1.428588273890482e-08,
      "logits/chosen": -0.725415050983429,
      "logits/rejected": -0.9350341558456421,
      "logps/chosen": -1040.5999755859375,
      "logps/rejected": -332.82501220703125,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.384423851966858,
      "rewards/margins": 7.4599609375,
      "rewards/rejected": -6.073828220367432,
      "step": 200
    },
    {
      "epoch": 0.8165249088699879,
      "grad_norm": 2.545449065189939,
      "learning_rate": 9.871292540103377e-09,
      "logits/chosen": -0.722412109375,
      "logits/rejected": -0.929858386516571,
      "logps/chosen": -1036.6500244140625,
      "logps/rejected": -329.54998779296875,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.4049561023712158,
      "rewards/margins": 7.583984375,
      "rewards/rejected": -6.179296970367432,
      "step": 210
    },
    {
      "epoch": 0.8554070473876063,
      "grad_norm": 0.43163218586837404,
      "learning_rate": 6.1977761496908695e-09,
      "logits/chosen": -0.7271728515625,
      "logits/rejected": -0.9333740472793579,
      "logps/chosen": -1029.324951171875,
      "logps/rejected": -330.95001220703125,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.387841820716858,
      "rewards/margins": 7.583984375,
      "rewards/rejected": -6.195703029632568,
      "step": 220
    },
    {
      "epoch": 0.8942891859052248,
      "grad_norm": 1.1334297545543626,
      "learning_rate": 3.3331739481316624e-09,
      "logits/chosen": -0.7221924066543579,
      "logits/rejected": -0.9290771484375,
      "logps/chosen": -1033.625,
      "logps/rejected": -335.51251220703125,
      "loss": 0.0015,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.386499047279358,
      "rewards/margins": 7.572070121765137,
      "rewards/rejected": -6.1845703125,
      "step": 230
    },
    {
      "epoch": 0.9331713244228432,
      "grad_norm": 0.2245653138567375,
      "learning_rate": 1.3303877555292442e-09,
      "logits/chosen": -0.725512683391571,
      "logits/rejected": -0.934619128704071,
      "logps/chosen": -1013.4249877929688,
      "logps/rejected": -333.98748779296875,
      "loss": 0.0012,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3474853038787842,
      "rewards/margins": 7.607226371765137,
      "rewards/rejected": -6.259961128234863,
      "step": 240
    },
    {
      "epoch": 0.9720534629404617,
      "grad_norm": 0.34410802938606294,
      "learning_rate": 2.2640387134577055e-10,
      "logits/chosen": -0.724291980266571,
      "logits/rejected": -0.932788074016571,
      "logps/chosen": -1036.6500244140625,
      "logps/rejected": -330.67498779296875,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.348962426185608,
      "rewards/margins": 7.596093654632568,
      "rewards/rejected": -6.248437404632568,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 257,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}