{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 1700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 9.941176470588236e-05,
      "loss": 0.1482,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.0992,
      "step": 20
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.823529411764706e-05,
      "loss": 0.0313,
      "step": 30
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.764705882352942e-05,
      "loss": 0.0365,
      "step": 40
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.705882352941177e-05,
      "loss": 0.0326,
      "step": 50
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.0122,
      "step": 60
    },
    {
      "epoch": 0.41,
      "learning_rate": 9.588235294117648e-05,
      "loss": 0.0045,
      "step": 70
    },
    {
      "epoch": 0.47,
      "learning_rate": 9.529411764705883e-05,
      "loss": 0.0044,
      "step": 80
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.470588235294118e-05,
      "loss": 0.0016,
      "step": 90
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.0036,
      "step": 100
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.352941176470589e-05,
      "loss": 0.0158,
      "step": 110
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.294117647058824e-05,
      "loss": 0.0019,
      "step": 120
    },
    {
      "epoch": 0.76,
      "learning_rate": 9.23529411764706e-05,
      "loss": 0.0132,
      "step": 130
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.0025,
      "step": 140
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.11764705882353e-05,
      "loss": 0.0049,
      "step": 150
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.058823529411765e-05,
      "loss": 0.0181,
      "step": 160
    },
    {
      "epoch": 1.0,
      "learning_rate": 9e-05,
      "loss": 0.0153,
      "step": 170
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.005996049847453833,
      "eval_mse": 0.005996049847453833,
      "eval_runtime": 15.3139,
      "eval_samples_per_second": 4.702,
      "eval_steps_per_second": 0.588,
      "step": 170
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.0079,
      "step": 180
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.882352941176471e-05,
      "loss": 0.0238,
      "step": 190
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.823529411764706e-05,
      "loss": 0.0274,
      "step": 200
    },
    {
      "epoch": 1.24,
      "learning_rate": 8.764705882352942e-05,
      "loss": 0.0078,
      "step": 210
    },
    {
      "epoch": 1.29,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.0144,
      "step": 220
    },
    {
      "epoch": 1.35,
      "learning_rate": 8.647058823529412e-05,
      "loss": 0.0046,
      "step": 230
    },
    {
      "epoch": 1.41,
      "learning_rate": 8.588235294117646e-05,
      "loss": 0.0078,
      "step": 240
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.529411764705883e-05,
      "loss": 0.0012,
      "step": 250
    },
    {
      "epoch": 1.53,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.0124,
      "step": 260
    },
    {
      "epoch": 1.59,
      "learning_rate": 8.411764705882354e-05,
      "loss": 0.0105,
      "step": 270
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.352941176470589e-05,
      "loss": 0.0089,
      "step": 280
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.294117647058824e-05,
      "loss": 0.0017,
      "step": 290
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.0095,
      "step": 300
    },
    {
      "epoch": 1.82,
      "learning_rate": 8.176470588235295e-05,
      "loss": 0.0016,
      "step": 310
    },
    {
      "epoch": 1.88,
      "learning_rate": 8.11764705882353e-05,
      "loss": 0.0128,
      "step": 320
    },
    {
      "epoch": 1.94,
      "learning_rate": 8.058823529411765e-05,
      "loss": 0.008,
      "step": 330
    },
    {
      "epoch": 2.0,
      "learning_rate": 8e-05,
      "loss": 0.001,
      "step": 340
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0011689820094034076,
      "eval_mse": 0.0011689820094034076,
      "eval_runtime": 15.7171,
      "eval_samples_per_second": 4.581,
      "eval_steps_per_second": 0.573,
      "step": 340
    },
    {
      "epoch": 2.06,
      "learning_rate": 7.941176470588235e-05,
      "loss": 0.0005,
      "step": 350
    },
    {
      "epoch": 2.12,
      "learning_rate": 7.882352941176471e-05,
      "loss": 0.0007,
      "step": 360
    },
    {
      "epoch": 2.18,
      "learning_rate": 7.823529411764707e-05,
      "loss": 0.0183,
      "step": 370
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.0021,
      "step": 380
    },
    {
      "epoch": 2.29,
      "learning_rate": 7.705882352941177e-05,
      "loss": 0.008,
      "step": 390
    },
    {
      "epoch": 2.35,
      "learning_rate": 7.647058823529411e-05,
      "loss": 0.0047,
      "step": 400
    },
    {
      "epoch": 2.41,
      "learning_rate": 7.588235294117648e-05,
      "loss": 0.011,
      "step": 410
    },
    {
      "epoch": 2.47,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.0024,
      "step": 420
    },
    {
      "epoch": 2.53,
      "learning_rate": 7.470588235294118e-05,
      "loss": 0.0019,
      "step": 430
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.411764705882354e-05,
      "loss": 0.0074,
      "step": 440
    },
    {
      "epoch": 2.65,
      "learning_rate": 7.352941176470589e-05,
      "loss": 0.0017,
      "step": 450
    },
    {
      "epoch": 2.71,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.0081,
      "step": 460
    },
    {
      "epoch": 2.76,
      "learning_rate": 7.23529411764706e-05,
      "loss": 0.0195,
      "step": 470
    },
    {
      "epoch": 2.82,
      "learning_rate": 7.176470588235295e-05,
      "loss": 0.0072,
      "step": 480
    },
    {
      "epoch": 2.88,
      "learning_rate": 7.11764705882353e-05,
      "loss": 0.0048,
      "step": 490
    },
    {
      "epoch": 2.94,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.0012,
      "step": 500
    },
    {
      "epoch": 3.0,
      "learning_rate": 7e-05,
      "loss": 0.0036,
      "step": 510
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0050306557677686214,
      "eval_mse": 0.0050306557677686214,
      "eval_runtime": 16.8544,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 0.534,
      "step": 510
    },
    {
      "epoch": 3.06,
      "learning_rate": 6.941176470588236e-05,
      "loss": 0.0055,
      "step": 520
    },
    {
      "epoch": 3.12,
      "learning_rate": 6.882352941176471e-05,
      "loss": 0.0112,
      "step": 530
    },
    {
      "epoch": 3.18,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.0038,
      "step": 540
    },
    {
      "epoch": 3.24,
      "learning_rate": 6.764705882352942e-05,
      "loss": 0.0017,
      "step": 550
    },
    {
      "epoch": 3.29,
      "learning_rate": 6.705882352941176e-05,
      "loss": 0.0015,
      "step": 560
    },
    {
      "epoch": 3.35,
      "learning_rate": 6.647058823529411e-05,
      "loss": 0.001,
      "step": 570
    },
    {
      "epoch": 3.41,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.0115,
      "step": 580
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.529411764705883e-05,
      "loss": 0.0024,
      "step": 590
    },
    {
      "epoch": 3.53,
      "learning_rate": 6.470588235294118e-05,
      "loss": 0.0021,
      "step": 600
    },
    {
      "epoch": 3.59,
      "learning_rate": 6.411764705882354e-05,
      "loss": 0.0015,
      "step": 610
    },
    {
      "epoch": 3.65,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.0016,
      "step": 620
    },
    {
      "epoch": 3.71,
      "learning_rate": 6.294117647058824e-05,
      "loss": 0.0103,
      "step": 630
    },
    {
      "epoch": 3.76,
      "learning_rate": 6.23529411764706e-05,
      "loss": 0.0108,
      "step": 640
    },
    {
      "epoch": 3.82,
      "learning_rate": 6.176470588235295e-05,
      "loss": 0.0071,
      "step": 650
    },
    {
      "epoch": 3.88,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.0078,
      "step": 660
    },
    {
      "epoch": 3.94,
      "learning_rate": 6.058823529411765e-05,
      "loss": 0.0043,
      "step": 670
    },
    {
      "epoch": 4.0,
      "learning_rate": 6e-05,
      "loss": 0.0017,
      "step": 680
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.0019855075515806675,
      "eval_mse": 0.001985507318750024,
      "eval_runtime": 15.5377,
      "eval_samples_per_second": 4.634,
      "eval_steps_per_second": 0.579,
      "step": 680
    },
    {
      "epoch": 4.06,
      "learning_rate": 5.9411764705882355e-05,
      "loss": 0.0022,
      "step": 690
    },
    {
      "epoch": 4.12,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.0092,
      "step": 700
    },
    {
      "epoch": 4.18,
      "learning_rate": 5.823529411764707e-05,
      "loss": 0.0024,
      "step": 710
    },
    {
      "epoch": 4.24,
      "learning_rate": 5.764705882352941e-05,
      "loss": 0.002,
      "step": 720
    },
    {
      "epoch": 4.29,
      "learning_rate": 5.7058823529411766e-05,
      "loss": 0.0042,
      "step": 730
    },
    {
      "epoch": 4.35,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.0602,
      "step": 740
    },
    {
      "epoch": 4.41,
      "learning_rate": 5.588235294117647e-05,
      "loss": 0.0062,
      "step": 750
    },
    {
      "epoch": 4.47,
      "learning_rate": 5.529411764705883e-05,
      "loss": 0.003,
      "step": 760
    },
    {
      "epoch": 4.53,
      "learning_rate": 5.4705882352941185e-05,
      "loss": 0.0088,
      "step": 770
    },
    {
      "epoch": 4.59,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.0025,
      "step": 780
    },
    {
      "epoch": 4.65,
      "learning_rate": 5.3529411764705884e-05,
      "loss": 0.0109,
      "step": 790
    },
    {
      "epoch": 4.71,
      "learning_rate": 5.294117647058824e-05,
      "loss": 0.0015,
      "step": 800
    },
    {
      "epoch": 4.76,
      "learning_rate": 5.235294117647059e-05,
      "loss": 0.0011,
      "step": 810
    },
    {
      "epoch": 4.82,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.0101,
      "step": 820
    },
    {
      "epoch": 4.88,
      "learning_rate": 5.117647058823529e-05,
      "loss": 0.0011,
      "step": 830
    },
    {
      "epoch": 4.94,
      "learning_rate": 5.058823529411765e-05,
      "loss": 0.0017,
      "step": 840
    },
    {
      "epoch": 5.0,
      "learning_rate": 5e-05,
      "loss": 0.0014,
      "step": 850
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.001027416903525591,
      "eval_mse": 0.001027416903525591,
      "eval_runtime": 17.3556,
      "eval_samples_per_second": 4.149,
      "eval_steps_per_second": 0.519,
      "step": 850
    },
    {
      "epoch": 5.06,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.0023,
      "step": 860
    },
    {
      "epoch": 5.12,
      "learning_rate": 4.882352941176471e-05,
      "loss": 0.0005,
      "step": 870
    },
    {
      "epoch": 5.18,
      "learning_rate": 4.823529411764706e-05,
      "loss": 0.0053,
      "step": 880
    },
    {
      "epoch": 5.24,
      "learning_rate": 4.7647058823529414e-05,
      "loss": 0.0026,
      "step": 890
    },
    {
      "epoch": 5.29,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.0045,
      "step": 900
    },
    {
      "epoch": 5.35,
      "learning_rate": 4.647058823529412e-05,
      "loss": 0.0017,
      "step": 910
    },
    {
      "epoch": 5.41,
      "learning_rate": 4.588235294117647e-05,
      "loss": 0.0012,
      "step": 920
    },
    {
      "epoch": 5.47,
      "learning_rate": 4.5294117647058826e-05,
      "loss": 0.0098,
      "step": 930
    },
    {
      "epoch": 5.53,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.0016,
      "step": 940
    },
    {
      "epoch": 5.59,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.0011,
      "step": 950
    },
    {
      "epoch": 5.65,
      "learning_rate": 4.3529411764705885e-05,
      "loss": 0.001,
      "step": 960
    },
    {
      "epoch": 5.71,
      "learning_rate": 4.294117647058823e-05,
      "loss": 0.0005,
      "step": 970
    },
    {
      "epoch": 5.76,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.0021,
      "step": 980
    },
    {
      "epoch": 5.82,
      "learning_rate": 4.1764705882352944e-05,
      "loss": 0.0107,
      "step": 990
    },
    {
      "epoch": 5.88,
      "learning_rate": 4.11764705882353e-05,
      "loss": 0.0086,
      "step": 1000
    },
    {
      "epoch": 5.94,
      "learning_rate": 4.058823529411765e-05,
      "loss": 0.0014,
      "step": 1010
    },
    {
      "epoch": 6.0,
      "learning_rate": 4e-05,
      "loss": 0.0008,
      "step": 1020
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.001083881827071309,
      "eval_mse": 0.001083881827071309,
      "eval_runtime": 15.3262,
      "eval_samples_per_second": 4.698,
      "eval_steps_per_second": 0.587,
      "step": 1020
    },
    {
      "epoch": 6.06,
      "learning_rate": 3.9411764705882356e-05,
      "loss": 0.0012,
      "step": 1030
    },
    {
      "epoch": 6.12,
      "learning_rate": 3.882352941176471e-05,
      "loss": 0.002,
      "step": 1040
    },
    {
      "epoch": 6.18,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.0062,
      "step": 1050
    },
    {
      "epoch": 6.24,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.0017,
      "step": 1060
    },
    {
      "epoch": 6.29,
      "learning_rate": 3.705882352941177e-05,
      "loss": 0.0008,
      "step": 1070
    },
    {
      "epoch": 6.35,
      "learning_rate": 3.6470588235294114e-05,
      "loss": 0.0013,
      "step": 1080
    },
    {
      "epoch": 6.41,
      "learning_rate": 3.5882352941176474e-05,
      "loss": 0.0078,
      "step": 1090
    },
    {
      "epoch": 6.47,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.0026,
      "step": 1100
    },
    {
      "epoch": 6.53,
      "learning_rate": 3.470588235294118e-05,
      "loss": 0.0084,
      "step": 1110
    },
    {
      "epoch": 6.59,
      "learning_rate": 3.411764705882353e-05,
      "loss": 0.0016,
      "step": 1120
    },
    {
      "epoch": 6.65,
      "learning_rate": 3.352941176470588e-05,
      "loss": 0.0026,
      "step": 1130
    },
    {
      "epoch": 6.71,
      "learning_rate": 3.294117647058824e-05,
      "loss": 0.0053,
      "step": 1140
    },
    {
      "epoch": 6.76,
      "learning_rate": 3.235294117647059e-05,
      "loss": 0.0058,
      "step": 1150
    },
    {
      "epoch": 6.82,
      "learning_rate": 3.176470588235294e-05,
      "loss": 0.001,
      "step": 1160
    },
    {
      "epoch": 6.88,
      "learning_rate": 3.11764705882353e-05,
      "loss": 0.0011,
      "step": 1170
    },
    {
      "epoch": 6.94,
      "learning_rate": 3.058823529411765e-05,
      "loss": 0.001,
      "step": 1180
    },
    {
      "epoch": 7.0,
      "learning_rate": 3e-05,
      "loss": 0.0008,
      "step": 1190
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.000933311355765909,
      "eval_mse": 0.000933311355765909,
      "eval_runtime": 15.2402,
      "eval_samples_per_second": 4.724,
      "eval_steps_per_second": 0.591,
      "step": 1190
    },
    {
      "epoch": 7.06,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.0152,
      "step": 1200
    },
    {
      "epoch": 7.12,
      "learning_rate": 2.8823529411764703e-05,
      "loss": 0.0025,
      "step": 1210
    },
    {
      "epoch": 7.18,
      "learning_rate": 2.823529411764706e-05,
      "loss": 0.0018,
      "step": 1220
    },
    {
      "epoch": 7.24,
      "learning_rate": 2.7647058823529416e-05,
      "loss": 0.0011,
      "step": 1230
    },
    {
      "epoch": 7.29,
      "learning_rate": 2.7058823529411766e-05,
      "loss": 0.0076,
      "step": 1240
    },
    {
      "epoch": 7.35,
      "learning_rate": 2.647058823529412e-05,
      "loss": 0.0009,
      "step": 1250
    },
    {
      "epoch": 7.41,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 0.0054,
      "step": 1260
    },
    {
      "epoch": 7.47,
      "learning_rate": 2.5294117647058825e-05,
      "loss": 0.0012,
      "step": 1270
    },
    {
      "epoch": 7.53,
      "learning_rate": 2.4705882352941178e-05,
      "loss": 0.0012,
      "step": 1280
    },
    {
      "epoch": 7.59,
      "learning_rate": 2.411764705882353e-05,
      "loss": 0.0005,
      "step": 1290
    },
    {
      "epoch": 7.65,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.0011,
      "step": 1300
    },
    {
      "epoch": 7.71,
      "learning_rate": 2.2941176470588237e-05,
      "loss": 0.0022,
      "step": 1310
    },
    {
      "epoch": 7.76,
      "learning_rate": 2.235294117647059e-05,
      "loss": 0.0009,
      "step": 1320
    },
    {
      "epoch": 7.82,
      "learning_rate": 2.1764705882352943e-05,
      "loss": 0.0007,
      "step": 1330
    },
    {
      "epoch": 7.88,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 0.0007,
      "step": 1340
    },
    {
      "epoch": 7.94,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.0007,
      "step": 1350
    },
    {
      "epoch": 8.0,
      "learning_rate": 2e-05,
      "loss": 0.0008,
      "step": 1360
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.001160233630798757,
      "eval_mse": 0.001160233747214079,
      "eval_runtime": 18.2978,
      "eval_samples_per_second": 3.935,
      "eval_steps_per_second": 0.492,
      "step": 1360
    },
    {
      "epoch": 8.06,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 0.0072,
      "step": 1370
    },
    {
      "epoch": 8.12,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 0.001,
      "step": 1380
    },
    {
      "epoch": 8.18,
      "learning_rate": 1.8235294117647057e-05,
      "loss": 0.0008,
      "step": 1390
    },
    {
      "epoch": 8.24,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.0025,
      "step": 1400
    },
    {
      "epoch": 8.29,
      "learning_rate": 1.7058823529411767e-05,
      "loss": 0.001,
      "step": 1410
    },
    {
      "epoch": 8.35,
      "learning_rate": 1.647058823529412e-05,
      "loss": 0.0014,
      "step": 1420
    },
    {
      "epoch": 8.41,
      "learning_rate": 1.588235294117647e-05,
      "loss": 0.0015,
      "step": 1430
    },
    {
      "epoch": 8.47,
      "learning_rate": 1.5294117647058826e-05,
      "loss": 0.0041,
      "step": 1440
    },
    {
      "epoch": 8.53,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.0012,
      "step": 1450
    },
    {
      "epoch": 8.59,
      "learning_rate": 1.411764705882353e-05,
      "loss": 0.0009,
      "step": 1460
    },
    {
      "epoch": 8.65,
      "learning_rate": 1.3529411764705883e-05,
      "loss": 0.0012,
      "step": 1470
    },
    {
      "epoch": 8.71,
      "learning_rate": 1.2941176470588238e-05,
      "loss": 0.0022,
      "step": 1480
    },
    {
      "epoch": 8.76,
      "learning_rate": 1.2352941176470589e-05,
      "loss": 0.0007,
      "step": 1490
    },
    {
      "epoch": 8.82,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.0064,
      "step": 1500
    },
    {
      "epoch": 8.88,
      "learning_rate": 1.1176470588235295e-05,
      "loss": 0.0014,
      "step": 1510
    },
    {
      "epoch": 8.94,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 0.0006,
      "step": 1520
    },
    {
      "epoch": 9.0,
      "learning_rate": 1e-05,
      "loss": 0.001,
      "step": 1530
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.0007979701040312648,
      "eval_mse": 0.0007979701040312648,
      "eval_runtime": 17.0378,
      "eval_samples_per_second": 4.226,
      "eval_steps_per_second": 0.528,
      "step": 1530
    },
    {
      "epoch": 9.06,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.0009,
      "step": 1540
    },
    {
      "epoch": 9.12,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.0008,
      "step": 1550
    },
    {
      "epoch": 9.18,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.0021,
      "step": 1560
    },
    {
      "epoch": 9.24,
      "learning_rate": 7.647058823529413e-06,
      "loss": 0.0009,
      "step": 1570
    },
    {
      "epoch": 9.29,
      "learning_rate": 7.058823529411765e-06,
      "loss": 0.0006,
      "step": 1580
    },
    {
      "epoch": 9.35,
      "learning_rate": 6.470588235294119e-06,
      "loss": 0.0005,
      "step": 1590
    },
    {
      "epoch": 9.41,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.0005,
      "step": 1600
    },
    {
      "epoch": 9.47,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.0007,
      "step": 1610
    },
    {
      "epoch": 9.53,
      "learning_rate": 4.705882352941177e-06,
      "loss": 0.0033,
      "step": 1620
    },
    {
      "epoch": 9.59,
      "learning_rate": 4.11764705882353e-06,
      "loss": 0.0009,
      "step": 1630
    },
    {
      "epoch": 9.65,
      "learning_rate": 3.5294117647058825e-06,
      "loss": 0.0008,
      "step": 1640
    },
    {
      "epoch": 9.71,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.0007,
      "step": 1650
    },
    {
      "epoch": 9.76,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.002,
      "step": 1660
    },
    {
      "epoch": 9.82,
      "learning_rate": 1.7647058823529412e-06,
      "loss": 0.0009,
      "step": 1670
    },
    {
      "epoch": 9.88,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 0.0008,
      "step": 1680
    },
    {
      "epoch": 9.94,
      "learning_rate": 5.882352941176471e-07,
      "loss": 0.0063,
      "step": 1690
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0004,
      "step": 1700
    }
  ],
  "max_steps": 1700,
  "num_train_epochs": 10,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}