{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032258064516129032,
      "grad_norm": 58.05511474609375,
      "learning_rate": 0.0,
      "loss": 1.9,
      "step": 1
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 21.915355682373047,
      "learning_rate": 2.580645161290323e-06,
      "loss": 1.7687,
      "step": 5
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 8.215951919555664,
      "learning_rate": 5.806451612903226e-06,
      "loss": 1.5337,
      "step": 10
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 4.512474060058594,
      "learning_rate": 9.03225806451613e-06,
      "loss": 1.4014,
      "step": 15
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 5.174832820892334,
      "learning_rate": 1.2258064516129034e-05,
      "loss": 1.3709,
      "step": 20
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 4.159119129180908,
      "learning_rate": 1.5483870967741936e-05,
      "loss": 1.3652,
      "step": 25
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 4.116876602172852,
      "learning_rate": 1.870967741935484e-05,
      "loss": 1.3885,
      "step": 30
    },
    {
      "epoch": 0.11290322580645161,
      "grad_norm": 3.840414047241211,
      "learning_rate": 1.999429490929718e-05,
      "loss": 1.3982,
      "step": 35
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 4.314554691314697,
      "learning_rate": 1.9959454037227215e-05,
      "loss": 1.3744,
      "step": 40
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 4.36101770401001,
      "learning_rate": 1.989305206325792e-05,
      "loss": 1.394,
      "step": 45
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 3.858530282974243,
      "learning_rate": 1.9795299412524948e-05,
      "loss": 1.3652,
      "step": 50
    },
    {
      "epoch": 0.1774193548387097,
      "grad_norm": 4.053957462310791,
      "learning_rate": 1.9666505859174462e-05,
      "loss": 1.3825,
      "step": 55
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 3.8405709266662598,
      "learning_rate": 1.9507079544701583e-05,
      "loss": 1.3449,
      "step": 60
    },
    {
      "epoch": 0.20967741935483872,
      "grad_norm": 3.8573291301727295,
      "learning_rate": 1.9317525684566686e-05,
      "loss": 1.3268,
      "step": 65
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 4.115865230560303,
      "learning_rate": 1.9098444967188308e-05,
      "loss": 1.3096,
      "step": 70
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 3.9826207160949707,
      "learning_rate": 1.8850531650386154e-05,
      "loss": 1.3243,
      "step": 75
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 8.022098541259766,
      "learning_rate": 1.857457136130651e-05,
      "loss": 1.309,
      "step": 80
    },
    {
      "epoch": 0.27419354838709675,
      "grad_norm": 3.8160018920898438,
      "learning_rate": 1.827143860680199e-05,
      "loss": 1.278,
      "step": 85
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 4.026176452636719,
      "learning_rate": 1.7942094002155122e-05,
      "loss": 1.2788,
      "step": 90
    },
    {
      "epoch": 0.3064516129032258,
      "grad_norm": 4.071281909942627,
      "learning_rate": 1.758758122692791e-05,
      "loss": 1.2412,
      "step": 95
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 3.6679961681365967,
      "learning_rate": 1.7209023717584013e-05,
      "loss": 1.1916,
      "step": 100
    },
    {
      "epoch": 0.3225806451612903,
      "eval_loss": 1.2297844886779785,
      "eval_runtime": 5.4527,
      "eval_samples_per_second": 196.965,
      "eval_steps_per_second": 6.235,
      "step": 100
    },
    {
      "epoch": 0.3387096774193548,
      "grad_norm": 3.7028727531433105,
      "learning_rate": 1.6807621107364613e-05,
      "loss": 1.2004,
      "step": 105
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 3.7159862518310547,
      "learning_rate": 1.6384645424699835e-05,
      "loss": 1.1933,
      "step": 110
    },
    {
      "epoch": 0.3709677419354839,
      "grad_norm": 3.5471580028533936,
      "learning_rate": 1.594143706220273e-05,
      "loss": 1.1913,
      "step": 115
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 4.138647079467773,
      "learning_rate": 1.5479400529019987e-05,
      "loss": 1.1872,
      "step": 120
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 3.7750704288482666,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.1359,
      "step": 125
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 3.429034948348999,
      "learning_rate": 1.4504754675782731e-05,
      "loss": 1.1518,
      "step": 130
    },
    {
      "epoch": 0.43548387096774194,
      "grad_norm": 3.416344404220581,
      "learning_rate": 1.3995233968515105e-05,
      "loss": 1.1405,
      "step": 135
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 4.399573802947998,
      "learning_rate": 1.3473052528448203e-05,
      "loss": 1.1137,
      "step": 140
    },
    {
      "epoch": 0.46774193548387094,
      "grad_norm": 3.7525525093078613,
      "learning_rate": 1.2939865127176771e-05,
      "loss": 1.1235,
      "step": 145
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 3.8501410484313965,
      "learning_rate": 1.2397361413735785e-05,
      "loss": 1.0858,
      "step": 150
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.5585899353027344,
      "learning_rate": 1.1847260560171895e-05,
      "loss": 1.0692,
      "step": 155
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 3.620709180831909,
      "learning_rate": 1.1291305813557616e-05,
      "loss": 1.0313,
      "step": 160
    },
    {
      "epoch": 0.532258064516129,
      "grad_norm": 3.7223265171051025,
      "learning_rate": 1.0731258971712762e-05,
      "loss": 1.0268,
      "step": 165
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 3.67724871635437,
      "learning_rate": 1.0168894800139311e-05,
      "loss": 1.0123,
      "step": 170
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 4.000744342803955,
      "learning_rate": 9.605995407862248e-06,
      "loss": 0.9905,
      "step": 175
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 3.4585959911346436,
      "learning_rate": 9.04434459999902e-06,
      "loss": 0.9682,
      "step": 180
    },
    {
      "epoch": 0.5967741935483871,
      "grad_norm": 3.573272466659546,
      "learning_rate": 8.485722224954237e-06,
      "loss": 0.9364,
      "step": 185
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 3.517512083053589,
      "learning_rate": 7.93189853415293e-06,
      "loss": 0.9559,
      "step": 190
    },
    {
      "epoch": 0.6290322580645161,
      "grad_norm": 3.629652500152588,
      "learning_rate": 7.384628572186334e-06,
      "loss": 0.9376,
      "step": 195
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 3.6871094703674316,
      "learning_rate": 6.845646615147445e-06,
      "loss": 0.9281,
      "step": 200
    },
    {
      "epoch": 0.6451612903225806,
      "eval_loss": 0.9366754293441772,
      "eval_runtime": 5.3925,
      "eval_samples_per_second": 199.164,
      "eval_steps_per_second": 6.305,
      "step": 200
    },
    {
      "epoch": 0.6612903225806451,
      "grad_norm": 3.7159454822540283,
      "learning_rate": 6.31666067478113e-06,
      "loss": 0.9359,
      "step": 205
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 3.5741474628448486,
      "learning_rate": 5.799347085864851e-06,
      "loss": 0.8788,
      "step": 210
    },
    {
      "epoch": 0.6935483870967742,
      "grad_norm": 3.8699448108673096,
      "learning_rate": 5.295345193972445e-06,
      "loss": 0.8994,
      "step": 215
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 3.681175470352173,
      "learning_rate": 4.8062521604551245e-06,
      "loss": 0.8894,
      "step": 220
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 4.077960968017578,
      "learning_rate": 4.333617901102592e-06,
      "loss": 0.8478,
      "step": 225
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 4.131643772125244,
      "learning_rate": 3.878940174523371e-06,
      "loss": 0.8409,
      "step": 230
    },
    {
      "epoch": 0.7580645161290323,
      "grad_norm": 3.835108995437622,
      "learning_rate": 3.4436598358091577e-06,
      "loss": 0.878,
      "step": 235
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 3.9890787601470947,
      "learning_rate": 3.0291562705240107e-06,
      "loss": 0.8321,
      "step": 240
    },
    {
      "epoch": 0.7903225806451613,
      "grad_norm": 3.728030204772949,
      "learning_rate": 2.6367430234880286e-06,
      "loss": 0.8269,
      "step": 245
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 3.8121144771575928,
      "learning_rate": 2.2676636362076075e-06,
      "loss": 0.7872,
      "step": 250
    },
    {
      "epoch": 0.8225806451612904,
      "grad_norm": 3.7709388732910156,
      "learning_rate": 1.9230877061433505e-06,
      "loss": 0.8187,
      "step": 255
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 3.6049516201019287,
      "learning_rate": 1.60410718030361e-06,
      "loss": 0.8195,
      "step": 260
    },
    {
      "epoch": 0.8548387096774194,
      "grad_norm": 3.6554863452911377,
      "learning_rate": 1.3117328949091634e-06,
      "loss": 0.8091,
      "step": 265
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 3.8024368286132812,
      "learning_rate": 1.0468913720946084e-06,
      "loss": 0.7855,
      "step": 270
    },
    {
      "epoch": 0.8870967741935484,
      "grad_norm": 3.79064679145813,
      "learning_rate": 8.10421883797694e-07,
      "loss": 0.7959,
      "step": 275
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 3.7366783618927,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.7824,
      "step": 280
    },
    {
      "epoch": 0.9193548387096774,
      "grad_norm": 3.792200803756714,
      "learning_rate": 4.2550417473364524e-07,
      "loss": 0.7653,
      "step": 285
    },
    {
      "epoch": 0.9354838709677419,
      "grad_norm": 3.850405216217041,
      "learning_rate": 2.7827574242009434e-07,
      "loss": 0.759,
      "step": 290
    },
    {
      "epoch": 0.9516129032258065,
      "grad_norm": 3.8457884788513184,
      "learning_rate": 1.6185505607171027e-07,
      "loss": 0.7866,
      "step": 295
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 3.824265241622925,
      "learning_rate": 7.661104807487607e-08,
      "loss": 0.7683,
      "step": 300
    },
    {
      "epoch": 0.967741935483871,
      "eval_loss": 0.7902069091796875,
      "eval_runtime": 5.4529,
      "eval_samples_per_second": 196.96,
      "eval_steps_per_second": 6.235,
      "step": 300
    },
    {
      "epoch": 0.9838709677419355,
      "grad_norm": 3.8102200031280518,
      "learning_rate": 2.2813853199292745e-08,
      "loss": 0.778,
      "step": 305
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.923637628555298,
      "learning_rate": 6.339525519594159e-10,
      "loss": 0.7865,
      "step": 310
    },
    {
      "epoch": 1.0,
      "step": 310,
      "total_flos": 1.0839391709062758e+17,
      "train_loss": 1.0778046692571333,
      "train_runtime": 974.833,
      "train_samples_per_second": 20.339,
      "train_steps_per_second": 0.318
    }
  ],
  "logging_steps": 5,
  "max_steps": 310,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0839391709062758e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}