{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9972602739726028,
  "eval_steps": 500,
  "global_step": 182,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005479452054794521,
      "grad_norm": 749.8344019634822,
      "learning_rate": 5.263157894736841e-09,
      "logits/chosen": -0.7030794620513916,
      "logits/rejected": -0.3951629400253296,
      "logps/chosen": -341.73382568359375,
      "logps/rejected": -292.9862060546875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 712.5612854291265,
      "learning_rate": 5.2631578947368416e-08,
      "logits/chosen": -0.8543994426727295,
      "logits/rejected": -0.5004442930221558,
      "logps/chosen": -343.0475158691406,
      "logps/rejected": -297.69866943359375,
      "loss": 0.7047,
      "rewards/accuracies": 0.4652777910232544,
      "rewards/chosen": 0.028890050947666168,
      "rewards/margins": 0.015952428802847862,
      "rewards/rejected": 0.012937622144818306,
      "step": 10
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 633.132107951183,
      "learning_rate": 9.999071352056673e-08,
      "logits/chosen": -0.8784568905830383,
      "logits/rejected": -0.5061537027359009,
      "logps/chosen": -333.73223876953125,
      "logps/rejected": -288.03704833984375,
      "loss": 0.6532,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -0.058163970708847046,
      "rewards/margins": 0.1349145770072937,
      "rewards/rejected": -0.19307854771614075,
      "step": 20
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 498.73085461545014,
      "learning_rate": 9.888050389939171e-08,
      "logits/chosen": -0.9048949480056763,
      "logits/rejected": -0.5001607537269592,
      "logps/chosen": -331.8179626464844,
      "logps/rejected": -290.59527587890625,
      "loss": 0.5232,
      "rewards/accuracies": 0.7593749761581421,
      "rewards/chosen": 0.2456372082233429,
      "rewards/margins": 0.7688120603561401,
      "rewards/rejected": -0.5231748819351196,
      "step": 30
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 468.38328488591065,
      "learning_rate": 9.596014080776422e-08,
      "logits/chosen": -0.8753167986869812,
      "logits/rejected": -0.5111785531044006,
      "logps/chosen": -335.57745361328125,
      "logps/rejected": -306.9455261230469,
      "loss": 0.4522,
      "rewards/accuracies": 0.8218749761581421,
      "rewards/chosen": 1.0787924528121948,
      "rewards/margins": 1.3148835897445679,
      "rewards/rejected": -0.23609113693237305,
      "step": 40
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 405.49075569087563,
      "learning_rate": 9.133777176798013e-08,
      "logits/chosen": -0.9362503886222839,
      "logits/rejected": -0.493760883808136,
      "logps/chosen": -329.0995178222656,
      "logps/rejected": -294.7619323730469,
      "loss": 0.4065,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": 2.0607025623321533,
      "rewards/margins": 1.7504669427871704,
      "rewards/rejected": 0.3102358281612396,
      "step": 50
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 531.0849294440985,
      "learning_rate": 8.518457335743925e-08,
      "logits/chosen": -0.8332949876785278,
      "logits/rejected": -0.44049328565597534,
      "logps/chosen": -328.05059814453125,
      "logps/rejected": -295.0623474121094,
      "loss": 0.397,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": 1.8471581935882568,
      "rewards/margins": 1.8996388912200928,
      "rewards/rejected": -0.05248071998357773,
      "step": 60
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 410.01119928479034,
      "learning_rate": 7.772841216033532e-08,
      "logits/chosen": -1.053856611251831,
      "logits/rejected": -0.6151344776153564,
      "logps/chosen": -347.8240966796875,
      "logps/rejected": -304.7304382324219,
      "loss": 0.3992,
      "rewards/accuracies": 0.793749988079071,
      "rewards/chosen": 1.6472972631454468,
      "rewards/margins": 1.7940982580184937,
      "rewards/rejected": -0.14680106937885284,
      "step": 70
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 422.6505304779972,
      "learning_rate": 6.924540636266271e-08,
      "logits/chosen": -0.9396562576293945,
      "logits/rejected": -0.3743361532688141,
      "logps/chosen": -341.07342529296875,
      "logps/rejected": -294.79632568359375,
      "loss": 0.3788,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": 1.4693505764007568,
      "rewards/margins": 1.931475043296814,
      "rewards/rejected": -0.46212440729141235,
      "step": 80
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 435.4943837818754,
      "learning_rate": 6.004970048339225e-08,
      "logits/chosen": -1.0359487533569336,
      "logits/rejected": -0.6516568064689636,
      "logps/chosen": -337.1309509277344,
      "logps/rejected": -307.5055847167969,
      "loss": 0.3792,
      "rewards/accuracies": 0.8218749761581421,
      "rewards/chosen": 1.8926198482513428,
      "rewards/margins": 1.9282394647598267,
      "rewards/rejected": -0.03561948612332344,
      "step": 90
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 424.3608116994891,
      "learning_rate": 5.0481831906199036e-08,
      "logits/chosen": -0.8561469316482544,
      "logits/rejected": -0.5456556081771851,
      "logps/chosen": -315.7440185546875,
      "logps/rejected": -284.4901428222656,
      "loss": 0.3607,
      "rewards/accuracies": 0.796875,
      "rewards/chosen": 1.5119119882583618,
      "rewards/margins": 1.8389956951141357,
      "rewards/rejected": -0.3270837962627411,
      "step": 100
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 376.9480565248481,
      "learning_rate": 4.0896120024874283e-08,
      "logits/chosen": -0.7713192105293274,
      "logits/rejected": -0.4743874967098236,
      "logps/chosen": -332.10638427734375,
      "logps/rejected": -302.2787780761719,
      "loss": 0.3675,
      "rewards/accuracies": 0.831250011920929,
      "rewards/chosen": 1.8271310329437256,
      "rewards/margins": 1.9777942895889282,
      "rewards/rejected": -0.15066327154636383,
      "step": 110
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 452.4360162863762,
      "learning_rate": 3.1647545010335394e-08,
      "logits/chosen": -0.8479810953140259,
      "logits/rejected": -0.47955965995788574,
      "logps/chosen": -345.54071044921875,
      "logps/rejected": -308.65179443359375,
      "loss": 0.3527,
      "rewards/accuracies": 0.840624988079071,
      "rewards/chosen": 1.8864860534667969,
      "rewards/margins": 2.1840381622314453,
      "rewards/rejected": -0.2975522577762604,
      "step": 120
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 315.5021095438557,
      "learning_rate": 2.3078602107593897e-08,
      "logits/chosen": -0.8250066041946411,
      "logits/rejected": -0.49061331152915955,
      "logps/chosen": -325.8185119628906,
      "logps/rejected": -298.6694030761719,
      "loss": 0.3638,
      "rewards/accuracies": 0.7906249761581421,
      "rewards/chosen": 1.3761605024337769,
      "rewards/margins": 1.7671406269073486,
      "rewards/rejected": -0.3909802734851837,
      "step": 130
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 420.91275678465917,
      "learning_rate": 1.5506618277219406e-08,
      "logits/chosen": -1.0089247226715088,
      "logits/rejected": -0.5239464044570923,
      "logps/chosen": -334.70111083984375,
      "logps/rejected": -293.3878479003906,
      "loss": 0.3607,
      "rewards/accuracies": 0.8343750238418579,
      "rewards/chosen": 1.8048830032348633,
      "rewards/margins": 2.049487829208374,
      "rewards/rejected": -0.2446049153804779,
      "step": 140
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 450.70186106616944,
      "learning_rate": 9.212000874196951e-09,
      "logits/chosen": -0.9020761251449585,
      "logits/rejected": -0.5833565592765808,
      "logps/chosen": -328.1164245605469,
      "logps/rejected": -298.4231872558594,
      "loss": 0.349,
      "rewards/accuracies": 0.84375,
      "rewards/chosen": 1.6165488958358765,
      "rewards/margins": 1.8227107524871826,
      "rewards/rejected": -0.20616202056407928,
      "step": 150
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 399.4981855057766,
      "learning_rate": 4.427853541662091e-09,
      "logits/chosen": -0.9409669041633606,
      "logits/rejected": -0.5335644483566284,
      "logps/chosen": -337.31488037109375,
      "logps/rejected": -302.06365966796875,
      "loss": 0.3548,
      "rewards/accuracies": 0.846875011920929,
      "rewards/chosen": 1.994319200515747,
      "rewards/margins": 2.289970636367798,
      "rewards/rejected": -0.29565146565437317,
      "step": 160
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 381.8223301695622,
      "learning_rate": 1.3313438659999398e-09,
      "logits/chosen": -0.6689538955688477,
      "logits/rejected": -0.37201908230781555,
      "logps/chosen": -323.4323425292969,
      "logps/rejected": -292.47857666015625,
      "loss": 0.3629,
      "rewards/accuracies": 0.840624988079071,
      "rewards/chosen": 2.0121166706085205,
      "rewards/margins": 2.282526731491089,
      "rewards/rejected": -0.2704099416732788,
      "step": 170
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 380.7644210750603,
      "learning_rate": 3.7142468185014095e-11,
      "logits/chosen": -0.8619197010993958,
      "logits/rejected": -0.5339924097061157,
      "logps/chosen": -319.94158935546875,
      "logps/rejected": -290.5792236328125,
      "loss": 0.367,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": 1.9236304759979248,
      "rewards/margins": 2.2062630653381348,
      "rewards/rejected": -0.2826324701309204,
      "step": 180
    },
    {
      "epoch": 0.9972602739726028,
      "step": 182,
      "total_flos": 0.0,
      "train_loss": 0.41821049595927146,
      "train_runtime": 5820.0845,
      "train_samples_per_second": 8.019,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 182,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}