{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.951219512195122,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.4831,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.2367,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 1e-05,
      "loss": 0.192,
      "step": 3
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.994504457428557e-06,
      "loss": 0.1773,
      "step": 4
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.978029910109491e-06,
      "loss": 0.1399,
      "step": 5
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.950612572673255e-06,
      "loss": 0.172,
      "step": 6
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.91231271437788e-06,
      "loss": 0.148,
      "step": 7
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.863214526624065e-06,
      "loss": 0.166,
      "step": 8
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.803425937884202e-06,
      "loss": 0.1081,
      "step": 9
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.733078376452172e-06,
      "loss": 0.1554,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 9.652326481535434e-06,
      "loss": 0.1714,
      "step": 11
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.561347763324484e-06,
      "loss": 0.1608,
      "step": 12
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.460342212786933e-06,
      "loss": 0.1586,
      "step": 13
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.349531862043952e-06,
      "loss": 0.1403,
      "step": 14
    },
    {
      "epoch": 0.42,
      "learning_rate": 9.229160296295488e-06,
      "loss": 0.137,
      "step": 15
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.099492118367123e-06,
      "loss": 0.1308,
      "step": 16
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.960812367055646e-06,
      "loss": 0.1385,
      "step": 17
    },
    {
      "epoch": 0.5,
      "learning_rate": 8.81342589055191e-06,
      "loss": 0.1818,
      "step": 18
    },
    {
      "epoch": 0.53,
      "learning_rate": 8.657656676318346e-06,
      "loss": 0.1461,
      "step": 19
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.49384713889421e-06,
      "loss": 0.1356,
      "step": 20
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.32235736719411e-06,
      "loss": 0.1245,
      "step": 21
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.143564332954426e-06,
      "loss": 0.1268,
      "step": 22
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.957861062067614e-06,
      "loss": 0.1559,
      "step": 23
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.765655770625997e-06,
      "loss": 0.1185,
      "step": 24
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.56737096757421e-06,
      "loss": 0.1108,
      "step": 25
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.363442525942827e-06,
      "loss": 0.1487,
      "step": 26
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.1543187247048525e-06,
      "loss": 0.1298,
      "step": 27
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.9404592633612486e-06,
      "loss": 0.153,
      "step": 28
    },
    {
      "epoch": 0.81,
      "learning_rate": 6.722334251421665e-06,
      "loss": 0.1564,
      "step": 29
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.500423175001705e-06,
      "loss": 0.1358,
      "step": 30
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.275213842808383e-06,
      "loss": 0.1357,
      "step": 31
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.047201313830724e-06,
      "loss": 0.1258,
      "step": 32
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.816886809092651e-06,
      "loss": 0.106,
      "step": 33
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.584776609860414e-06,
      "loss": 0.1308,
      "step": 34
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.351380944726465e-06,
      "loss": 0.1471,
      "step": 35
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.117212868016303e-06,
      "loss": 0.1277,
      "step": 36
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.882787131983698e-06,
      "loss": 0.0926,
      "step": 37
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.6486190552735375e-06,
      "loss": 0.0784,
      "step": 38
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.415223390139588e-06,
      "loss": 0.0768,
      "step": 39
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.183113190907349e-06,
      "loss": 0.0671,
      "step": 40
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.952798686169279e-06,
      "loss": 0.0946,
      "step": 41
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.7247861571916183e-06,
      "loss": 0.086,
      "step": 42
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.4995768249982975e-06,
      "loss": 0.0633,
      "step": 43
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.2776657485783357e-06,
      "loss": 0.0694,
      "step": 44
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.059540736638751e-06,
      "loss": 0.0669,
      "step": 45
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.8456812752951483e-06,
      "loss": 0.0866,
      "step": 46
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.636557474057173e-06,
      "loss": 0.0697,
      "step": 47
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.4326290324257896e-06,
      "loss": 0.0601,
      "step": 48
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.234344229374003e-06,
      "loss": 0.0828,
      "step": 49
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.042138937932388e-06,
      "loss": 0.0597,
      "step": 50
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.856435667045577e-06,
      "loss": 0.0553,
      "step": 51
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.677642632805892e-06,
      "loss": 0.0713,
      "step": 52
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.5061528611057917e-06,
      "loss": 0.0874,
      "step": 53
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.3423433236816563e-06,
      "loss": 0.0603,
      "step": 54
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.186574109448091e-06,
      "loss": 0.0717,
      "step": 55
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.0391876329443534e-06,
      "loss": 0.0699,
      "step": 56
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.005078816328772e-07,
      "loss": 0.0767,
      "step": 57
    },
    {
      "epoch": 1.62,
      "learning_rate": 7.708397037045129e-07,
      "loss": 0.0824,
      "step": 58
    },
    {
      "epoch": 1.64,
      "learning_rate": 6.50468137956049e-07,
      "loss": 0.0718,
      "step": 59
    },
    {
      "epoch": 1.67,
      "learning_rate": 5.396577872130676e-07,
      "loss": 0.0745,
      "step": 60
    },
    {
      "epoch": 1.7,
      "learning_rate": 4.386522366755169e-07,
      "loss": 0.0743,
      "step": 61
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.4767351846456744e-07,
      "loss": 0.0769,
      "step": 62
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.669216235478295e-07,
      "loss": 0.0686,
      "step": 63
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.9657406211579966e-07,
      "loss": 0.0889,
      "step": 64
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.3678547337593494e-07,
      "loss": 0.0935,
      "step": 65
    },
    {
      "epoch": 1.84,
      "learning_rate": 8.768728562211948e-08,
      "loss": 0.0764,
      "step": 66
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.9387427326745287e-08,
      "loss": 0.0831,
      "step": 67
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.1970089890509527e-08,
      "loss": 0.0757,
      "step": 68
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.495542571443135e-09,
      "loss": 0.0682,
      "step": 69
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0,
      "loss": 0.0806,
      "step": 70
    },
    {
      "epoch": 1.95,
      "step": 70,
      "total_flos": 1.8547569844027392e+17,
      "train_loss": 0.11677362551646574,
      "train_runtime": 2542.2323,
      "train_samples_per_second": 3.609,
      "train_steps_per_second": 0.028
    }
  ],
  "max_steps": 70,
  "num_train_epochs": 2,
  "total_flos": 1.8547569844027392e+17,
  "trial_name": null,
  "trial_params": null
}