{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 500,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0064,
      "grad_norm": 1341.948853106591,
      "learning_rate": 3.125e-09,
      "logits/chosen": -3.9499800205230713,
      "logits/rejected": -4.237819194793701,
      "logps/chosen": -300.693115234375,
      "logps/rejected": -249.96307373046875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.064,
      "grad_norm": 1338.549586928997,
      "learning_rate": 3.125e-08,
      "logits/chosen": -4.129465579986572,
      "logits/rejected": -4.351754188537598,
      "logps/chosen": -351.4585266113281,
      "logps/rejected": -308.89202880859375,
      "loss": 0.7278,
      "rewards/accuracies": 0.375,
      "rewards/chosen": -0.016052477061748505,
      "rewards/margins": -0.04994054138660431,
      "rewards/rejected": 0.033888060599565506,
      "step": 10
    },
    {
      "epoch": 0.128,
      "grad_norm": 1285.3502810697903,
      "learning_rate": 4.9899357349880975e-08,
      "logits/chosen": -4.195886611938477,
      "logits/rejected": -4.383217811584473,
      "logps/chosen": -334.9483337402344,
      "logps/rejected": -293.82867431640625,
      "loss": 0.6803,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": 0.20189008116722107,
      "rewards/margins": 0.08841639757156372,
      "rewards/rejected": 0.11347369104623795,
      "step": 20
    },
    {
      "epoch": 0.192,
      "grad_norm": 938.2936106934807,
      "learning_rate": 4.877641290737884e-08,
      "logits/chosen": -4.2334418296813965,
      "logits/rejected": -4.3670477867126465,
      "logps/chosen": -327.77716064453125,
      "logps/rejected": -295.27203369140625,
      "loss": 0.5536,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": 0.9395688772201538,
      "rewards/margins": 0.4487342834472656,
      "rewards/rejected": 0.49083465337753296,
      "step": 30
    },
    {
      "epoch": 0.256,
      "grad_norm": 899.5533271284629,
      "learning_rate": 4.646121984004665e-08,
      "logits/chosen": -4.14696741104126,
      "logits/rejected": -4.348996162414551,
      "logps/chosen": -330.3467712402344,
      "logps/rejected": -288.37066650390625,
      "loss": 0.4332,
      "rewards/accuracies": 0.8218749761581421,
      "rewards/chosen": 1.8148998022079468,
      "rewards/margins": 1.0534685850143433,
      "rewards/rejected": 0.7614310383796692,
      "step": 40
    },
    {
      "epoch": 0.32,
      "grad_norm": 737.601892593307,
      "learning_rate": 4.3069871595684784e-08,
      "logits/chosen": -4.238839149475098,
      "logits/rejected": -4.417731285095215,
      "logps/chosen": -329.99560546875,
      "logps/rejected": -291.286865234375,
      "loss": 0.3783,
      "rewards/accuracies": 0.8531249761581421,
      "rewards/chosen": 2.4285898208618164,
      "rewards/margins": 1.3909423351287842,
      "rewards/rejected": 1.0376476049423218,
      "step": 50
    },
    {
      "epoch": 0.384,
      "grad_norm": 725.6613657693058,
      "learning_rate": 3.8772424536302564e-08,
      "logits/chosen": -4.256905555725098,
      "logits/rejected": -4.42824125289917,
      "logps/chosen": -321.1641845703125,
      "logps/rejected": -291.2255859375,
      "loss": 0.3554,
      "rewards/accuracies": 0.846875011920929,
      "rewards/chosen": 2.799910306930542,
      "rewards/margins": 1.64876389503479,
      "rewards/rejected": 1.151146411895752,
      "step": 60
    },
    {
      "epoch": 0.448,
      "grad_norm": 650.256008502672,
      "learning_rate": 3.378437060203357e-08,
      "logits/chosen": -4.1877875328063965,
      "logits/rejected": -4.377414703369141,
      "logps/chosen": -320.77117919921875,
      "logps/rejected": -288.512451171875,
      "loss": 0.3377,
      "rewards/accuracies": 0.7906249761581421,
      "rewards/chosen": 3.0348763465881348,
      "rewards/margins": 1.8613855838775635,
      "rewards/rejected": 1.1734905242919922,
      "step": 70
    },
    {
      "epoch": 0.512,
      "grad_norm": 643.4652639779088,
      "learning_rate": 2.8355831645441387e-08,
      "logits/chosen": -4.054490089416504,
      "logits/rejected": -4.3433709144592285,
      "logps/chosen": -346.53253173828125,
      "logps/rejected": -307.34930419921875,
      "loss": 0.3369,
      "rewards/accuracies": 0.8656250238418579,
      "rewards/chosen": 3.375593662261963,
      "rewards/margins": 2.1429190635681152,
      "rewards/rejected": 1.2326747179031372,
      "step": 80
    },
    {
      "epoch": 0.576,
      "grad_norm": 658.4601656800384,
      "learning_rate": 2.2759017277414164e-08,
      "logits/chosen": -4.182233810424805,
      "logits/rejected": -4.391860485076904,
      "logps/chosen": -333.4163513183594,
      "logps/rejected": -295.03515625,
      "loss": 0.3301,
      "rewards/accuracies": 0.859375,
      "rewards/chosen": 2.9584574699401855,
      "rewards/margins": 1.9474881887435913,
      "rewards/rejected": 1.0109691619873047,
      "step": 90
    },
    {
      "epoch": 0.64,
      "grad_norm": 716.6222925151064,
      "learning_rate": 1.7274575140626317e-08,
      "logits/chosen": -4.168593406677246,
      "logits/rejected": -4.387479305267334,
      "logps/chosen": -330.75775146484375,
      "logps/rejected": -285.5531311035156,
      "loss": 0.3315,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": 3.267747163772583,
      "rewards/margins": 2.245748281478882,
      "rewards/rejected": 1.0219987630844116,
      "step": 100
    },
    {
      "epoch": 0.704,
      "grad_norm": 660.4496184068971,
      "learning_rate": 1.217751806485235e-08,
      "logits/chosen": -4.1479597091674805,
      "logits/rejected": -4.388964653015137,
      "logps/chosen": -312.3727722167969,
      "logps/rejected": -276.13372802734375,
      "loss": 0.3225,
      "rewards/accuracies": 0.8656250238418579,
      "rewards/chosen": 3.277716875076294,
      "rewards/margins": 2.2097737789154053,
      "rewards/rejected": 1.0679429769515991,
      "step": 110
    },
    {
      "epoch": 0.768,
      "grad_norm": 637.7261383555538,
      "learning_rate": 7.723433775328384e-09,
      "logits/chosen": -4.145724296569824,
      "logits/rejected": -4.354761123657227,
      "logps/chosen": -326.25091552734375,
      "logps/rejected": -280.4151916503906,
      "loss": 0.3134,
      "rewards/accuracies": 0.8531249761581421,
      "rewards/chosen": 3.3363654613494873,
      "rewards/margins": 2.202853202819824,
      "rewards/rejected": 1.1335121393203735,
      "step": 120
    },
    {
      "epoch": 0.832,
      "grad_norm": 768.5710075733069,
      "learning_rate": 4.135668656967433e-09,
      "logits/chosen": -4.2324018478393555,
      "logits/rejected": -4.393607139587402,
      "logps/chosen": -331.71051025390625,
      "logps/rejected": -286.67938232421875,
      "loss": 0.3203,
      "rewards/accuracies": 0.875,
      "rewards/chosen": 3.384364604949951,
      "rewards/margins": 2.2786831855773926,
      "rewards/rejected": 1.1056816577911377,
      "step": 130
    },
    {
      "epoch": 0.896,
      "grad_norm": 742.2155895768275,
      "learning_rate": 1.5941282340065698e-09,
      "logits/chosen": -4.18549919128418,
      "logits/rejected": -4.4001359939575195,
      "logps/chosen": -333.18035888671875,
      "logps/rejected": -303.45220947265625,
      "loss": 0.3282,
      "rewards/accuracies": 0.84375,
      "rewards/chosen": 3.2540221214294434,
      "rewards/margins": 2.2057249546051025,
      "rewards/rejected": 1.048297643661499,
      "step": 140
    },
    {
      "epoch": 0.96,
      "grad_norm": 668.7483012920786,
      "learning_rate": 2.262559558016325e-10,
      "logits/chosen": -4.1221604347229,
      "logits/rejected": -4.351316452026367,
      "logps/chosen": -339.6897888183594,
      "logps/rejected": -295.03692626953125,
      "loss": 0.3208,
      "rewards/accuracies": 0.859375,
      "rewards/chosen": 3.4081547260284424,
      "rewards/margins": 2.2413132190704346,
      "rewards/rejected": 1.1668416261672974,
      "step": 150
    },
    {
      "epoch": 0.9984,
      "step": 156,
      "total_flos": 0.0,
      "train_loss": 0.4014626894241724,
      "train_runtime": 5052.0322,
      "train_samples_per_second": 7.906,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 156,
  "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
}