{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9607843137254903,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.2929,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.8823529411764707e-05,
      "loss": 1.3741,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.823529411764706e-05,
      "loss": 0.9937,
      "step": 30
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.764705882352941e-05,
      "loss": 0.7573,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.7058823529411766e-05,
      "loss": 1.4795,
      "step": 50
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.2939,
      "step": 60
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.5882352941176472e-05,
      "loss": 0.7816,
      "step": 70
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.5294117647058825e-05,
      "loss": 3.2073,
      "step": 80
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.4705882352941174e-05,
      "loss": 1.9018,
      "step": 90
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.411764705882353e-05,
      "loss": 1.7244,
      "step": 100
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.3282,
      "step": 110
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.2941176470588233e-05,
      "loss": 0.7277,
      "step": 120
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.235294117647059e-05,
      "loss": 0.9595,
      "step": 130
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.1764705882352943e-05,
      "loss": 1.5087,
      "step": 140
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.1413,
      "step": 150
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.7349,
      "step": 160
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 1.2754,
      "step": 170
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 0.4958,
      "step": 180
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.2852,
      "step": 190
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.8235294117647057e-05,
      "loss": 2.063,
      "step": 200
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8745,
      "step": 210
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.7058823529411763e-05,
      "loss": 1.6477,
      "step": 220
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.4984,
      "step": 230
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 2.1564,
      "step": 240
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5294117647058822e-05,
      "loss": 1.5632,
      "step": 250
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.0398,
      "step": 260
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.411764705882353e-05,
      "loss": 2.0072,
      "step": 270
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.3529411764705883e-05,
      "loss": 0.4885,
      "step": 280
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.2941176470588236e-05,
      "loss": 1.3477,
      "step": 290
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.2352941176470587e-05,
      "loss": 2.0612,
      "step": 300
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.1766,
      "step": 310
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.1176470588235295e-05,
      "loss": 1.5938,
      "step": 320
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 1.7661,
      "step": 330
    },
    {
      "epoch": 1.33,
      "learning_rate": 9.999999999999999e-06,
      "loss": 2.1266,
      "step": 340
    },
    {
      "epoch": 1.37,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.0121,
      "step": 350
    },
    {
      "epoch": 1.41,
      "learning_rate": 8.823529411764707e-06,
      "loss": 2.1273,
      "step": 360
    },
    {
      "epoch": 1.45,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.6538,
      "step": 370
    },
    {
      "epoch": 1.49,
      "learning_rate": 7.647058823529411e-06,
      "loss": 3.7878,
      "step": 380
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.058823529411765e-06,
      "loss": 2.1304,
      "step": 390
    },
    {
      "epoch": 1.57,
      "learning_rate": 6.470588235294118e-06,
      "loss": 0.6084,
      "step": 400
    },
    {
      "epoch": 1.61,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.7258,
      "step": 410
    },
    {
      "epoch": 1.65,
      "learning_rate": 5.294117647058824e-06,
      "loss": 1.0022,
      "step": 420
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.7453,
      "step": 430
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.11764705882353e-06,
      "loss": 2.1497,
      "step": 440
    },
    {
      "epoch": 1.76,
      "learning_rate": 3.5294117647058825e-06,
      "loss": 1.6716,
      "step": 450
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.6858,
      "step": 460
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.6145,
      "step": 470
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.7647058823529412e-06,
      "loss": 2.4272,
      "step": 480
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.1166,
      "step": 490
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.882352941176471e-07,
      "loss": 1.4319,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 510,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}