{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.0,
      "learning_rate": 1.9607843137254903e-05,
      "loss": 2.2836,
      "step": 10
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.0,
      "learning_rate": 3.9215686274509805e-05,
      "loss": 2.0531,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.0,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.0231,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.0,
      "learning_rate": 7.843137254901961e-05,
      "loss": 2.0226,
      "step": 40
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 0.0,
      "learning_rate": 9.80392156862745e-05,
      "loss": 2.1214,
      "step": 50
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.0,
      "learning_rate": 9.990263847374976e-05,
      "loss": 2.1241,
      "step": 60
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.0,
      "learning_rate": 9.956656688041808e-05,
      "loss": 2.225,
      "step": 70
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.0,
      "learning_rate": 9.899219854168429e-05,
      "loss": 2.1955,
      "step": 80
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.0,
      "learning_rate": 9.818229479678158e-05,
      "loss": 2.0837,
      "step": 90
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.0,
      "learning_rate": 9.714074934742556e-05,
      "loss": 2.0915,
      "step": 100
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 0.0,
      "learning_rate": 9.587256953841317e-05,
      "loss": 2.1907,
      "step": 110
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.0,
      "learning_rate": 9.438385228425938e-05,
      "loss": 2.1822,
      "step": 120
    },
    {
      "epoch": 0.7738095238095238,
      "grad_norm": 0.0,
      "learning_rate": 9.268175475760734e-05,
      "loss": 2.1324,
      "step": 130
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.0,
      "learning_rate": 9.077445998033015e-05,
      "loss": 2.1216,
      "step": 140
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.0,
      "learning_rate": 8.86711374827494e-05,
      "loss": 2.1736,
      "step": 150
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.0,
      "learning_rate": 8.638189922010529e-05,
      "loss": 2.161,
      "step": 160
    },
    {
      "epoch": 1.0119047619047619,
      "grad_norm": 0.0,
      "learning_rate": 8.391775095821482e-05,
      "loss": 1.9752,
      "step": 170
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.0,
      "learning_rate": 8.129053936203687e-05,
      "loss": 1.1203,
      "step": 180
    },
    {
      "epoch": 1.130952380952381,
      "grad_norm": 0.0,
      "learning_rate": 7.851289504152201e-05,
      "loss": 1.1102,
      "step": 190
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.0,
      "learning_rate": 7.559817182855977e-05,
      "loss": 1.0731,
      "step": 200
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.0,
      "learning_rate": 7.256038257695687e-05,
      "loss": 1.0537,
      "step": 210
    },
    {
      "epoch": 1.3095238095238095,
      "grad_norm": 0.0,
      "learning_rate": 6.941413179409468e-05,
      "loss": 1.1446,
      "step": 220
    },
    {
      "epoch": 1.369047619047619,
      "grad_norm": 0.0,
      "learning_rate": 6.61745454281468e-05,
      "loss": 1.0612,
      "step": 230
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.0,
      "learning_rate": 6.28571981484123e-05,
      "loss": 1.0517,
      "step": 240
    },
    {
      "epoch": 1.4880952380952381,
      "grad_norm": 0.0,
      "learning_rate": 5.94780384683728e-05,
      "loss": 1.0755,
      "step": 250
    },
    {
      "epoch": 1.5476190476190477,
      "grad_norm": 0.0,
      "learning_rate": 5.605331207145219e-05,
      "loss": 1.1604,
      "step": 260
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.0,
      "learning_rate": 5.2599483708099016e-05,
      "loss": 1.0858,
      "step": 270
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0,
      "learning_rate": 4.913315803968012e-05,
      "loss": 1.3748,
      "step": 280
    },
    {
      "epoch": 1.7261904761904763,
      "grad_norm": 0.0,
      "learning_rate": 4.567099980973684e-05,
      "loss": 1.1309,
      "step": 290
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.0,
      "learning_rate": 4.2229653726389765e-05,
      "loss": 0.9784,
      "step": 300
    },
    {
      "epoch": 1.8452380952380953,
      "grad_norm": 0.0,
      "learning_rate": 3.8825664441065734e-05,
      "loss": 1.2982,
      "step": 310
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.0,
      "learning_rate": 3.547539700825874e-05,
      "loss": 1.0105,
      "step": 320
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.0,
      "learning_rate": 3.219495820872265e-05,
      "loss": 1.0056,
      "step": 330
    },
    {
      "epoch": 2.0238095238095237,
      "grad_norm": 0.0,
      "learning_rate": 2.9000119114343582e-05,
      "loss": 0.7399,
      "step": 340
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 0.0,
      "learning_rate": 2.5906239266969805e-05,
      "loss": 0.3847,
      "step": 350
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.0,
      "learning_rate": 2.2928192835717644e-05,
      "loss": 0.4477,
      "step": 360
    },
    {
      "epoch": 2.2023809523809526,
      "grad_norm": 0.0,
      "learning_rate": 2.008029710776041e-05,
      "loss": 0.3674,
      "step": 370
    },
    {
      "epoch": 2.261904761904762,
      "grad_norm": 0.0,
      "learning_rate": 1.7376243656388923e-05,
      "loss": 0.4358,
      "step": 380
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 0.0,
      "learning_rate": 1.4829032517260489e-05,
      "loss": 0.4029,
      "step": 390
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.0,
      "learning_rate": 1.245090968929148e-05,
      "loss": 0.3537,
      "step": 400
    },
    {
      "epoch": 2.4404761904761907,
      "grad_norm": 0.0,
      "learning_rate": 1.0253308260664902e-05,
      "loss": 0.3583,
      "step": 410
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0,
      "learning_rate": 8.246793442995954e-06,
      "loss": 0.3662,
      "step": 420
    },
    {
      "epoch": 2.5595238095238093,
      "grad_norm": 0.0,
      "learning_rate": 6.4410117779103e-06,
      "loss": 0.354,
      "step": 430
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.0,
      "learning_rate": 4.844644760229544e-06,
      "loss": 0.4411,
      "step": 440
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.0,
      "learning_rate": 3.465367100725908e-06,
      "loss": 0.4508,
      "step": 450
    },
    {
      "epoch": 2.738095238095238,
      "grad_norm": 0.0,
      "learning_rate": 2.3098098291025273e-06,
      "loss": 0.3551,
      "step": 460
    },
    {
      "epoch": 2.7976190476190474,
      "grad_norm": 0.0,
      "learning_rate": 1.3835284145856275e-06,
      "loss": 0.3454,
      "step": 470
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.0,
      "learning_rate": 6.909760573925561e-07,
      "loss": 0.3835,
      "step": 480
    },
    {
      "epoch": 2.9166666666666665,
      "grad_norm": 0.0,
      "learning_rate": 2.3548227947988167e-07,
      "loss": 0.3762,
      "step": 490
    },
    {
      "epoch": 2.9761904761904763,
      "grad_norm": 0.0,
      "learning_rate": 1.9236917498782758e-08,
      "loss": 0.3555,
      "step": 500
    },
    {
      "epoch": 3.0,
      "step": 504,
      "total_flos": 1.7456931048259584e+16,
      "train_loss": 1.2097263981898625,
      "train_runtime": 180.7007,
      "train_samples_per_second": 2.789,
      "train_steps_per_second": 2.789
    }
  ],
  "logging_steps": 10,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1660,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7456931048259584e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}