{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.9705882352941178e-05,
      "loss": 1.0836,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 1.0019,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8788,
      "step": 30
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 0.8091,
      "step": 40
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.8529411764705884e-05,
      "loss": 0.7834,
      "step": 50
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.823529411764706e-05,
      "loss": 0.7014,
      "step": 60
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.7941176470588237e-05,
      "loss": 0.6923,
      "step": 70
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.7349,
      "step": 80
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.735294117647059e-05,
      "loss": 0.6577,
      "step": 90
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7058823529411767e-05,
      "loss": 0.5255,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.6764705882352943e-05,
      "loss": 0.4952,
      "step": 110
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.647058823529412e-05,
      "loss": 0.4352,
      "step": 120
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.5161,
      "step": 130
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 0.4864,
      "step": 140
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.558823529411765e-05,
      "loss": 0.3699,
      "step": 150
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.5294117647058822e-05,
      "loss": 0.4127,
      "step": 160
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.3442,
      "step": 170
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.3352,
      "step": 180
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.4411764705882353e-05,
      "loss": 0.2948,
      "step": 190
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.4117647058823532e-05,
      "loss": 0.2847,
      "step": 200
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.3823529411764706e-05,
      "loss": 0.4593,
      "step": 210
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.3529411764705885e-05,
      "loss": 0.3336,
      "step": 220
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.2393,
      "step": 230
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.2941176470588238e-05,
      "loss": 0.2694,
      "step": 240
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.2647058823529412e-05,
      "loss": 0.2853,
      "step": 250
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.235294117647059e-05,
      "loss": 0.465,
      "step": 260
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.2058823529411765e-05,
      "loss": 0.2817,
      "step": 270
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.2782,
      "step": 280
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.1470588235294118e-05,
      "loss": 0.2407,
      "step": 290
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.1176470588235295e-05,
      "loss": 0.1703,
      "step": 300
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.0882352941176471e-05,
      "loss": 0.2805,
      "step": 310
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 0.201,
      "step": 320
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.2091,
      "step": 330
    },
    {
      "epoch": 2.5,
      "learning_rate": 1e-05,
      "loss": 0.2248,
      "step": 340
    },
    {
      "epoch": 2.57,
      "learning_rate": 9.705882352941177e-06,
      "loss": 0.1915,
      "step": 350
    },
    {
      "epoch": 2.65,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.2132,
      "step": 360
    },
    {
      "epoch": 2.72,
      "learning_rate": 9.11764705882353e-06,
      "loss": 0.1448,
      "step": 370
    },
    {
      "epoch": 2.79,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.1909,
      "step": 380
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.529411764705883e-06,
      "loss": 0.1651,
      "step": 390
    },
    {
      "epoch": 2.94,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.1619,
      "step": 400
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.941176470588236e-06,
      "loss": 0.2061,
      "step": 410
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.647058823529411e-06,
      "loss": 0.1458,
      "step": 420
    },
    {
      "epoch": 3.16,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.166,
      "step": 430
    },
    {
      "epoch": 3.24,
      "learning_rate": 7.058823529411766e-06,
      "loss": 0.1641,
      "step": 440
    },
    {
      "epoch": 3.31,
      "learning_rate": 6.764705882352942e-06,
      "loss": 0.1657,
      "step": 450
    },
    {
      "epoch": 3.38,
      "learning_rate": 6.470588235294119e-06,
      "loss": 0.1467,
      "step": 460
    },
    {
      "epoch": 3.46,
      "learning_rate": 6.176470588235295e-06,
      "loss": 0.1654,
      "step": 470
    },
    {
      "epoch": 3.53,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.1557,
      "step": 480
    },
    {
      "epoch": 3.6,
      "learning_rate": 5.588235294117647e-06,
      "loss": 0.1344,
      "step": 490
    },
    {
      "epoch": 3.68,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.1183,
      "step": 500
    },
    {
      "epoch": 3.75,
      "learning_rate": 5e-06,
      "loss": 0.1637,
      "step": 510
    },
    {
      "epoch": 3.82,
      "learning_rate": 4.705882352941177e-06,
      "loss": 0.0994,
      "step": 520
    },
    {
      "epoch": 3.9,
      "learning_rate": 4.411764705882353e-06,
      "loss": 0.13,
      "step": 530
    },
    {
      "epoch": 3.97,
      "learning_rate": 4.11764705882353e-06,
      "loss": 0.1547,
      "step": 540
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.8235294117647055e-06,
      "loss": 0.0713,
      "step": 550
    },
    {
      "epoch": 4.12,
      "learning_rate": 3.529411764705883e-06,
      "loss": 0.1357,
      "step": 560
    },
    {
      "epoch": 4.19,
      "learning_rate": 3.2352941176470594e-06,
      "loss": 0.1262,
      "step": 570
    },
    {
      "epoch": 4.26,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.162,
      "step": 580
    },
    {
      "epoch": 4.34,
      "learning_rate": 2.647058823529412e-06,
      "loss": 0.0756,
      "step": 590
    },
    {
      "epoch": 4.41,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.0953,
      "step": 600
    },
    {
      "epoch": 4.49,
      "learning_rate": 2.058823529411765e-06,
      "loss": 0.1475,
      "step": 610
    },
    {
      "epoch": 4.56,
      "learning_rate": 1.7647058823529414e-06,
      "loss": 0.0962,
      "step": 620
    },
    {
      "epoch": 4.63,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 0.1273,
      "step": 630
    },
    {
      "epoch": 4.71,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 0.0762,
      "step": 640
    },
    {
      "epoch": 4.78,
      "learning_rate": 8.823529411764707e-07,
      "loss": 0.1287,
      "step": 650
    },
    {
      "epoch": 4.85,
      "learning_rate": 5.882352941176471e-07,
      "loss": 0.114,
      "step": 660
    },
    {
      "epoch": 4.93,
      "learning_rate": 2.9411764705882356e-07,
      "loss": 0.0847,
      "step": 670
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0581,
      "step": 680
    },
    {
      "epoch": 5.0,
      "step": 680,
      "total_flos": 1434252424400640.0,
      "train_loss": 0.30093149113304474,
      "train_runtime": 237.668,
      "train_samples_per_second": 91.114,
      "train_steps_per_second": 2.861
    }
  ],
  "max_steps": 680,
  "num_train_epochs": 5,
  "total_flos": 1434252424400640.0,
  "trial_name": null,
  "trial_params": null
}