{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05315967838394578,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002657983919197289,
      "eval_loss": 3.3747382164001465,
      "eval_runtime": 116.3735,
      "eval_samples_per_second": 13.62,
      "eval_steps_per_second": 6.814,
      "step": 1
    },
    {
      "epoch": 0.0013289919595986443,
      "grad_norm": 0.19273613393306732,
      "learning_rate": 5e-05,
      "loss": 3.2518,
      "step": 5
    },
    {
      "epoch": 0.0026579839191972886,
      "grad_norm": 0.24546188116073608,
      "learning_rate": 0.0001,
      "loss": 3.3946,
      "step": 10
    },
    {
      "epoch": 0.003986975878795933,
      "grad_norm": 0.3712539076805115,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.3423,
      "step": 15
    },
    {
      "epoch": 0.005315967838394577,
      "grad_norm": 0.440332293510437,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.2702,
      "step": 20
    },
    {
      "epoch": 0.0066449597979932225,
      "grad_norm": 0.44500812888145447,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.1532,
      "step": 25
    },
    {
      "epoch": 0.007973951757591866,
      "grad_norm": 0.45136186480522156,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.1822,
      "step": 30
    },
    {
      "epoch": 0.009302943717190511,
      "grad_norm": 0.5240881443023682,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.2693,
      "step": 35
    },
    {
      "epoch": 0.010631935676789155,
      "grad_norm": 0.45544329285621643,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.2418,
      "step": 40
    },
    {
      "epoch": 0.0119609276363878,
      "grad_norm": 0.622912585735321,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.2255,
      "step": 45
    },
    {
      "epoch": 0.013289919595986445,
      "grad_norm": 0.759652316570282,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.3534,
      "step": 50
    },
    {
      "epoch": 0.013289919595986445,
      "eval_loss": 3.2474777698516846,
      "eval_runtime": 117.843,
      "eval_samples_per_second": 13.45,
      "eval_steps_per_second": 6.729,
      "step": 50
    },
    {
      "epoch": 0.014618911555585088,
      "grad_norm": 0.36193954944610596,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.3303,
      "step": 55
    },
    {
      "epoch": 0.015947903515183732,
      "grad_norm": 0.4073311686515808,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.1379,
      "step": 60
    },
    {
      "epoch": 0.017276895474782377,
      "grad_norm": 0.37899190187454224,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.1246,
      "step": 65
    },
    {
      "epoch": 0.018605887434381022,
      "grad_norm": 0.3801954984664917,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.2062,
      "step": 70
    },
    {
      "epoch": 0.019934879393979667,
      "grad_norm": 0.418718546628952,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.1172,
      "step": 75
    },
    {
      "epoch": 0.02126387135357831,
      "grad_norm": 0.4203377962112427,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.1633,
      "step": 80
    },
    {
      "epoch": 0.022592863313176954,
      "grad_norm": 0.45516136288642883,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.1142,
      "step": 85
    },
    {
      "epoch": 0.0239218552727756,
      "grad_norm": 0.4883389472961426,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.125,
      "step": 90
    },
    {
      "epoch": 0.025250847232374245,
      "grad_norm": 0.6239806413650513,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.1914,
      "step": 95
    },
    {
      "epoch": 0.02657983919197289,
      "grad_norm": 0.8938126564025879,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.3532,
      "step": 100
    },
    {
      "epoch": 0.02657983919197289,
      "eval_loss": 3.226165771484375,
      "eval_runtime": 118.0147,
      "eval_samples_per_second": 13.431,
      "eval_steps_per_second": 6.72,
      "step": 100
    },
    {
      "epoch": 0.02790883115157153,
      "grad_norm": 0.40662944316864014,
      "learning_rate": 5e-05,
      "loss": 3.3708,
      "step": 105
    },
    {
      "epoch": 0.029237823111170177,
      "grad_norm": 0.49958688020706177,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.2421,
      "step": 110
    },
    {
      "epoch": 0.030566815070768822,
      "grad_norm": 0.42382222414016724,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.2441,
      "step": 115
    },
    {
      "epoch": 0.031895807030367464,
      "grad_norm": 0.42244333028793335,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.1328,
      "step": 120
    },
    {
      "epoch": 0.03322479898996611,
      "grad_norm": 0.5140597820281982,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.235,
      "step": 125
    },
    {
      "epoch": 0.034553790949564754,
      "grad_norm": 0.5386475324630737,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.0768,
      "step": 130
    },
    {
      "epoch": 0.0358827829091634,
      "grad_norm": 0.5116773247718811,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.2749,
      "step": 135
    },
    {
      "epoch": 0.037211774868762044,
      "grad_norm": 0.5770620703697205,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 3.1097,
      "step": 140
    },
    {
      "epoch": 0.03854076682836069,
      "grad_norm": 0.685364305973053,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.2481,
      "step": 145
    },
    {
      "epoch": 0.039869758787959335,
      "grad_norm": 1.0047972202301025,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.4641,
      "step": 150
    },
    {
      "epoch": 0.039869758787959335,
      "eval_loss": 3.2148067951202393,
      "eval_runtime": 118.0135,
      "eval_samples_per_second": 13.431,
      "eval_steps_per_second": 6.72,
      "step": 150
    },
    {
      "epoch": 0.04119875074755798,
      "grad_norm": 0.4244877099990845,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.1716,
      "step": 155
    },
    {
      "epoch": 0.04252774270715662,
      "grad_norm": 0.424883633852005,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.1719,
      "step": 160
    },
    {
      "epoch": 0.043856734666755263,
      "grad_norm": 0.42046844959259033,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.2414,
      "step": 165
    },
    {
      "epoch": 0.04518572662635391,
      "grad_norm": 0.46279048919677734,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.1362,
      "step": 170
    },
    {
      "epoch": 0.046514718585952554,
      "grad_norm": 0.47510379552841187,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.0648,
      "step": 175
    },
    {
      "epoch": 0.0478437105455512,
      "grad_norm": 0.459209144115448,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.1999,
      "step": 180
    },
    {
      "epoch": 0.049172702505149844,
      "grad_norm": 0.5207657814025879,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.1076,
      "step": 185
    },
    {
      "epoch": 0.05050169446474849,
      "grad_norm": 0.5179470777511597,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.1441,
      "step": 190
    },
    {
      "epoch": 0.051830686424347135,
      "grad_norm": 0.6202439069747925,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.1897,
      "step": 195
    },
    {
      "epoch": 0.05315967838394578,
      "grad_norm": 0.8030288815498352,
      "learning_rate": 0.0,
      "loss": 3.3938,
      "step": 200
    },
    {
      "epoch": 0.05315967838394578,
      "eval_loss": 3.2137556076049805,
      "eval_runtime": 117.9329,
      "eval_samples_per_second": 13.44,
      "eval_steps_per_second": 6.724,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "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": 6.97054418436096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}