{
  "best_metric": 0.11449769884347916,
  "best_model_checkpoint": "./results/checkpoint-7500",
  "epoch": 1.8518518518518519,
  "eval_steps": 500,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.9998765432098766e-05,
      "loss": 1.0193,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.997530864197531e-05,
      "loss": 0.4949,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.995061728395062e-05,
      "loss": 0.2844,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9925925925925927e-05,
      "loss": 0.1986,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.9901234567901236e-05,
      "loss": 0.1997,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.9876543209876545e-05,
      "loss": 0.2144,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.985185185185185e-05,
      "loss": 0.1782,
      "step": 120
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.9827160493827163e-05,
      "loss": 0.1901,
      "step": 140
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.980246913580247e-05,
      "loss": 0.1662,
      "step": 160
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.9777777777777777e-05,
      "loss": 0.2065,
      "step": 180
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.975308641975309e-05,
      "loss": 0.2146,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.9728395061728395e-05,
      "loss": 0.1374,
      "step": 220
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.9703703703703707e-05,
      "loss": 0.1214,
      "step": 240
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.9679012345679012e-05,
      "loss": 0.1994,
      "step": 260
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.965432098765432e-05,
      "loss": 0.1688,
      "step": 280
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.1858,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.960493827160494e-05,
      "loss": 0.1487,
      "step": 320
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.9580246913580248e-05,
      "loss": 0.1741,
      "step": 340
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.9555555555555556e-05,
      "loss": 0.1603,
      "step": 360
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.9530864197530865e-05,
      "loss": 0.1642,
      "step": 380
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.9506172839506174e-05,
      "loss": 0.1494,
      "step": 400
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.9481481481481483e-05,
      "loss": 0.1675,
      "step": 420
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.945679012345679e-05,
      "loss": 0.1467,
      "step": 440
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.94320987654321e-05,
      "loss": 0.1805,
      "step": 460
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.940740740740741e-05,
      "loss": 0.1565,
      "step": 480
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.9382716049382715e-05,
      "loss": 0.1608,
      "step": 500
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.9453855140186916,
      "eval_f1": 0.9649089885531995,
      "eval_loss": 0.1606026589870453,
      "eval_precision": 0.9685700446692859,
      "eval_recall": 0.9612755047537657,
      "eval_runtime": 119.1297,
      "eval_samples_per_second": 201.595,
      "eval_steps_per_second": 3.601,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.9358024691358027e-05,
      "loss": 0.1649,
      "step": 520
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 0.1528,
      "step": 540
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.9308641975308645e-05,
      "loss": 0.1851,
      "step": 560
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.928395061728395e-05,
      "loss": 0.1595,
      "step": 580
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.925925925925926e-05,
      "loss": 0.1417,
      "step": 600
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.923456790123457e-05,
      "loss": 0.1526,
      "step": 620
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.9209876543209877e-05,
      "loss": 0.1366,
      "step": 640
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.9185185185185186e-05,
      "loss": 0.1587,
      "step": 660
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.9160493827160494e-05,
      "loss": 0.1462,
      "step": 680
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.9135802469135803e-05,
      "loss": 0.1384,
      "step": 700
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.9111111111111112e-05,
      "loss": 0.1491,
      "step": 720
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.908641975308642e-05,
      "loss": 0.1626,
      "step": 740
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.906172839506173e-05,
      "loss": 0.1422,
      "step": 760
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.903703703703704e-05,
      "loss": 0.1658,
      "step": 780
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.9012345679012347e-05,
      "loss": 0.1427,
      "step": 800
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.8987654320987653e-05,
      "loss": 0.1422,
      "step": 820
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.8962962962962965e-05,
      "loss": 0.166,
      "step": 840
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.893827160493827e-05,
      "loss": 0.158,
      "step": 860
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.8913580246913583e-05,
      "loss": 0.1493,
      "step": 880
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.1661,
      "step": 900
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.8864197530864197e-05,
      "loss": 0.1911,
      "step": 920
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.883950617283951e-05,
      "loss": 0.1494,
      "step": 940
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.8814814814814815e-05,
      "loss": 0.1662,
      "step": 960
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.8790123456790124e-05,
      "loss": 0.1752,
      "step": 980
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.8765432098765432e-05,
      "loss": 0.1417,
      "step": 1000
    },
    {
      "epoch": 0.21,
      "eval_accuracy": 0.9548147530040053,
      "eval_f1": 0.9712220657401749,
      "eval_loss": 0.14220671355724335,
      "eval_precision": 0.9663687800750885,
      "eval_recall": 0.9761243456895631,
      "eval_runtime": 118.2799,
      "eval_samples_per_second": 203.044,
      "eval_steps_per_second": 3.627,
      "step": 1000
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.874074074074074e-05,
      "loss": 0.1381,
      "step": 1020
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.871604938271605e-05,
      "loss": 0.1386,
      "step": 1040
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.869135802469136e-05,
      "loss": 0.1465,
      "step": 1060
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.8666666666666668e-05,
      "loss": 0.1406,
      "step": 1080
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.8641975308641977e-05,
      "loss": 0.1484,
      "step": 1100
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.8617283950617285e-05,
      "loss": 0.1258,
      "step": 1120
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.859259259259259e-05,
      "loss": 0.1454,
      "step": 1140
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.8567901234567903e-05,
      "loss": 0.1564,
      "step": 1160
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.854320987654321e-05,
      "loss": 0.126,
      "step": 1180
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.851851851851852e-05,
      "loss": 0.1434,
      "step": 1200
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.849382716049383e-05,
      "loss": 0.1781,
      "step": 1220
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.8469135802469135e-05,
      "loss": 0.1571,
      "step": 1240
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.8444444444444447e-05,
      "loss": 0.1393,
      "step": 1260
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.8419753086419753e-05,
      "loss": 0.1343,
      "step": 1280
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.141,
      "step": 1300
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.837037037037037e-05,
      "loss": 0.1704,
      "step": 1320
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.834567901234568e-05,
      "loss": 0.143,
      "step": 1340
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.832098765432099e-05,
      "loss": 0.149,
      "step": 1360
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.8296296296296297e-05,
      "loss": 0.1451,
      "step": 1380
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.8271604938271606e-05,
      "loss": 0.1565,
      "step": 1400
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.8246913580246915e-05,
      "loss": 0.1257,
      "step": 1420
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.8222222222222223e-05,
      "loss": 0.1452,
      "step": 1440
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.819753086419753e-05,
      "loss": 0.1592,
      "step": 1460
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.817283950617284e-05,
      "loss": 0.1242,
      "step": 1480
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.8148148148148147e-05,
      "loss": 0.1508,
      "step": 1500
    },
    {
      "epoch": 0.31,
      "eval_accuracy": 0.954314085447263,
      "eval_f1": 0.9711058922869884,
      "eval_loss": 0.14577177166938782,
      "eval_precision": 0.9596349413298566,
      "eval_recall": 0.9828543958978742,
      "eval_runtime": 118.4509,
      "eval_samples_per_second": 202.751,
      "eval_steps_per_second": 3.622,
      "step": 1500
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.812345679012346e-05,
      "loss": 0.1491,
      "step": 1520
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.8098765432098768e-05,
      "loss": 0.1561,
      "step": 1540
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.8074074074074073e-05,
      "loss": 0.153,
      "step": 1560
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.8049382716049385e-05,
      "loss": 0.1359,
      "step": 1580
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.802469135802469e-05,
      "loss": 0.1502,
      "step": 1600
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.8e-05,
      "loss": 0.1367,
      "step": 1620
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.797530864197531e-05,
      "loss": 0.1195,
      "step": 1640
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.7950617283950617e-05,
      "loss": 0.1578,
      "step": 1660
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.792592592592593e-05,
      "loss": 0.1412,
      "step": 1680
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.7901234567901235e-05,
      "loss": 0.1489,
      "step": 1700
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.7876543209876544e-05,
      "loss": 0.1235,
      "step": 1720
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.7851851851851853e-05,
      "loss": 0.1064,
      "step": 1740
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.782716049382716e-05,
      "loss": 0.1226,
      "step": 1760
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.7802469135802467e-05,
      "loss": 0.1647,
      "step": 1780
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.1346,
      "step": 1800
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.7753086419753088e-05,
      "loss": 0.1582,
      "step": 1820
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.7728395061728397e-05,
      "loss": 0.1255,
      "step": 1840
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.7703703703703706e-05,
      "loss": 0.1412,
      "step": 1860
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.767901234567901e-05,
      "loss": 0.148,
      "step": 1880
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.7654320987654323e-05,
      "loss": 0.1356,
      "step": 1900
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.762962962962963e-05,
      "loss": 0.1349,
      "step": 1920
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.7604938271604938e-05,
      "loss": 0.158,
      "step": 1940
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.7580246913580246e-05,
      "loss": 0.144,
      "step": 1960
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.7555555555555555e-05,
      "loss": 0.1145,
      "step": 1980
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.7530864197530867e-05,
      "loss": 0.1617,
      "step": 2000
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.9513100801068091,
      "eval_f1": 0.9689321939142241,
      "eval_loss": 0.14288319647312164,
      "eval_precision": 0.9658722997717744,
      "eval_recall": 0.9720115372289285,
      "eval_runtime": 118.478,
      "eval_samples_per_second": 202.704,
      "eval_steps_per_second": 3.621,
      "step": 2000
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.7506172839506173e-05,
      "loss": 0.1565,
      "step": 2020
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.7481481481481482e-05,
      "loss": 0.1316,
      "step": 2040
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.745679012345679e-05,
      "loss": 0.09,
      "step": 2060
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.74320987654321e-05,
      "loss": 0.1537,
      "step": 2080
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.7407407407407408e-05,
      "loss": 0.1473,
      "step": 2100
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.7382716049382717e-05,
      "loss": 0.1646,
      "step": 2120
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.7358024691358026e-05,
      "loss": 0.1399,
      "step": 2140
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.7333333333333335e-05,
      "loss": 0.1369,
      "step": 2160
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.7308641975308644e-05,
      "loss": 0.1343,
      "step": 2180
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.728395061728395e-05,
      "loss": 0.1336,
      "step": 2200
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.725925925925926e-05,
      "loss": 0.1249,
      "step": 2220
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7234567901234567e-05,
      "loss": 0.1152,
      "step": 2240
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.720987654320988e-05,
      "loss": 0.1494,
      "step": 2260
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7185185185185188e-05,
      "loss": 0.1354,
      "step": 2280
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 0.1337,
      "step": 2300
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.7135802469135805e-05,
      "loss": 0.1545,
      "step": 2320
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.711111111111111e-05,
      "loss": 0.1325,
      "step": 2340
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.708641975308642e-05,
      "loss": 0.1268,
      "step": 2360
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.706172839506173e-05,
      "loss": 0.1289,
      "step": 2380
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.7037037037037037e-05,
      "loss": 0.1429,
      "step": 2400
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.701234567901235e-05,
      "loss": 0.1361,
      "step": 2420
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.6987654320987655e-05,
      "loss": 0.1181,
      "step": 2440
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.6962962962962964e-05,
      "loss": 0.1371,
      "step": 2460
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.6938271604938273e-05,
      "loss": 0.1475,
      "step": 2480
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.691358024691358e-05,
      "loss": 0.1424,
      "step": 2500
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.9566505340453939,
      "eval_f1": 0.9724410493090369,
      "eval_loss": 0.12953436374664307,
      "eval_precision": 0.9658569998419305,
      "eval_recall": 0.9791154791154791,
      "eval_runtime": 118.1592,
      "eval_samples_per_second": 203.251,
      "eval_steps_per_second": 3.631,
      "step": 2500
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.6888888888888887e-05,
      "loss": 0.1309,
      "step": 2520
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.68641975308642e-05,
      "loss": 0.1308,
      "step": 2540
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.6839506172839505e-05,
      "loss": 0.1229,
      "step": 2560
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.6814814814814817e-05,
      "loss": 0.1421,
      "step": 2580
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.6790123456790126e-05,
      "loss": 0.1407,
      "step": 2600
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.676543209876543e-05,
      "loss": 0.1494,
      "step": 2620
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.6740740740740743e-05,
      "loss": 0.126,
      "step": 2640
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.671604938271605e-05,
      "loss": 0.1101,
      "step": 2660
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.6691358024691358e-05,
      "loss": 0.1453,
      "step": 2680
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1439,
      "step": 2700
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.6641975308641975e-05,
      "loss": 0.1262,
      "step": 2720
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.6617283950617288e-05,
      "loss": 0.1342,
      "step": 2740
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.6592592592592593e-05,
      "loss": 0.1504,
      "step": 2760
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.6567901234567902e-05,
      "loss": 0.138,
      "step": 2780
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.654320987654321e-05,
      "loss": 0.1355,
      "step": 2800
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.651851851851852e-05,
      "loss": 0.1539,
      "step": 2820
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.6493827160493825e-05,
      "loss": 0.1354,
      "step": 2840
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6469135802469137e-05,
      "loss": 0.1349,
      "step": 2860
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6444444444444446e-05,
      "loss": 0.1464,
      "step": 2880
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.6419753086419755e-05,
      "loss": 0.1165,
      "step": 2900
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.6395061728395064e-05,
      "loss": 0.1331,
      "step": 2920
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.637037037037037e-05,
      "loss": 0.1494,
      "step": 2940
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.634567901234568e-05,
      "loss": 0.1248,
      "step": 2960
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.6320987654320987e-05,
      "loss": 0.126,
      "step": 2980
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.6296296296296296e-05,
      "loss": 0.1335,
      "step": 3000
    },
    {
      "epoch": 0.62,
      "eval_accuracy": 0.958194259012016,
      "eval_f1": 0.9733751395015146,
      "eval_loss": 0.1272495985031128,
      "eval_precision": 0.9684856175972927,
      "eval_recall": 0.9783142826621087,
      "eval_runtime": 118.461,
      "eval_samples_per_second": 202.733,
      "eval_steps_per_second": 3.621,
      "step": 3000
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.6271604938271608e-05,
      "loss": 0.1406,
      "step": 3020
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.6246913580246913e-05,
      "loss": 0.1196,
      "step": 3040
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.6222222222222226e-05,
      "loss": 0.138,
      "step": 3060
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.619753086419753e-05,
      "loss": 0.1346,
      "step": 3080
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.617283950617284e-05,
      "loss": 0.1261,
      "step": 3100
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.614814814814815e-05,
      "loss": 0.144,
      "step": 3120
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.6123456790123458e-05,
      "loss": 0.1276,
      "step": 3140
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.6098765432098763e-05,
      "loss": 0.1433,
      "step": 3160
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.6074074074074075e-05,
      "loss": 0.1231,
      "step": 3180
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.6049382716049384e-05,
      "loss": 0.1538,
      "step": 3200
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.6024691358024693e-05,
      "loss": 0.163,
      "step": 3220
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.1063,
      "step": 3240
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.5975308641975307e-05,
      "loss": 0.1063,
      "step": 3260
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.595061728395062e-05,
      "loss": 0.1199,
      "step": 3280
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.1225,
      "step": 3300
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.5901234567901234e-05,
      "loss": 0.1462,
      "step": 3320
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.5876543209876546e-05,
      "loss": 0.129,
      "step": 3340
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.585185185185185e-05,
      "loss": 0.1249,
      "step": 3360
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.5827160493827164e-05,
      "loss": 0.1167,
      "step": 3380
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.580246913580247e-05,
      "loss": 0.1356,
      "step": 3400
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.5777777777777778e-05,
      "loss": 0.1152,
      "step": 3420
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.5753086419753087e-05,
      "loss": 0.1356,
      "step": 3440
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.5728395061728396e-05,
      "loss": 0.1306,
      "step": 3460
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.5703703703703704e-05,
      "loss": 0.1351,
      "step": 3480
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.5679012345679013e-05,
      "loss": 0.1033,
      "step": 3500
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9573180907877169,
      "eval_f1": 0.9728625620075868,
      "eval_loss": 0.13398964703083038,
      "eval_precision": 0.9663768115942029,
      "eval_recall": 0.9794359576968272,
      "eval_runtime": 118.1747,
      "eval_samples_per_second": 203.225,
      "eval_steps_per_second": 3.63,
      "step": 3500
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.5654320987654322e-05,
      "loss": 0.1352,
      "step": 3520
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.562962962962963e-05,
      "loss": 0.1552,
      "step": 3540
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.560493827160494e-05,
      "loss": 0.1197,
      "step": 3560
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.5580246913580245e-05,
      "loss": 0.1188,
      "step": 3580
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.5555555555555557e-05,
      "loss": 0.1266,
      "step": 3600
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.5530864197530863e-05,
      "loss": 0.1155,
      "step": 3620
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.5506172839506172e-05,
      "loss": 0.1416,
      "step": 3640
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.5481481481481484e-05,
      "loss": 0.1213,
      "step": 3660
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.545679012345679e-05,
      "loss": 0.1072,
      "step": 3680
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.54320987654321e-05,
      "loss": 0.1483,
      "step": 3700
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5407407407407407e-05,
      "loss": 0.1286,
      "step": 3720
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5382716049382716e-05,
      "loss": 0.1324,
      "step": 3740
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5358024691358025e-05,
      "loss": 0.1076,
      "step": 3760
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5333333333333334e-05,
      "loss": 0.141,
      "step": 3780
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5308641975308642e-05,
      "loss": 0.1554,
      "step": 3800
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.528395061728395e-05,
      "loss": 0.1328,
      "step": 3820
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.525925925925926e-05,
      "loss": 0.1227,
      "step": 3840
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.523456790123457e-05,
      "loss": 0.0846,
      "step": 3860
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.5209876543209878e-05,
      "loss": 0.1244,
      "step": 3880
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.5185185185185183e-05,
      "loss": 0.1444,
      "step": 3900
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.5160493827160495e-05,
      "loss": 0.1512,
      "step": 3920
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.5135802469135804e-05,
      "loss": 0.1179,
      "step": 3940
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.511111111111111e-05,
      "loss": 0.107,
      "step": 3960
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.5086419753086422e-05,
      "loss": 0.1402,
      "step": 3980
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.5061728395061727e-05,
      "loss": 0.1498,
      "step": 4000
    },
    {
      "epoch": 0.82,
      "eval_accuracy": 0.9575684245660881,
      "eval_f1": 0.9728503163458715,
      "eval_loss": 0.12487499415874481,
      "eval_precision": 0.9724609062283183,
      "eval_recall": 0.9732400384574298,
      "eval_runtime": 117.9936,
      "eval_samples_per_second": 203.536,
      "eval_steps_per_second": 3.636,
      "step": 4000
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.503703703703704e-05,
      "loss": 0.1367,
      "step": 4020
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.5012345679012345e-05,
      "loss": 0.1371,
      "step": 4040
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.4987654320987654e-05,
      "loss": 0.1326,
      "step": 4060
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.4962962962962966e-05,
      "loss": 0.1375,
      "step": 4080
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.493827160493827e-05,
      "loss": 0.1402,
      "step": 4100
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.491358024691358e-05,
      "loss": 0.1133,
      "step": 4120
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.488888888888889e-05,
      "loss": 0.1122,
      "step": 4140
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.4864197530864198e-05,
      "loss": 0.1286,
      "step": 4160
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.4839506172839507e-05,
      "loss": 0.1354,
      "step": 4180
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.4814814814814816e-05,
      "loss": 0.1122,
      "step": 4200
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.479012345679012e-05,
      "loss": 0.1037,
      "step": 4220
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.4765432098765433e-05,
      "loss": 0.133,
      "step": 4240
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.4740740740740742e-05,
      "loss": 0.1256,
      "step": 4260
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.4716049382716048e-05,
      "loss": 0.1263,
      "step": 4280
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.469135802469136e-05,
      "loss": 0.1101,
      "step": 4300
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.4666666666666665e-05,
      "loss": 0.1286,
      "step": 4320
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.4641975308641978e-05,
      "loss": 0.1219,
      "step": 4340
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.4617283950617283e-05,
      "loss": 0.1246,
      "step": 4360
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.4592592592592592e-05,
      "loss": 0.1136,
      "step": 4380
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.4567901234567904e-05,
      "loss": 0.1224,
      "step": 4400
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.454320987654321e-05,
      "loss": 0.1169,
      "step": 4420
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.451851851851852e-05,
      "loss": 0.1206,
      "step": 4440
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.4493827160493827e-05,
      "loss": 0.1277,
      "step": 4460
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.4469135802469136e-05,
      "loss": 0.1414,
      "step": 4480
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.1241,
      "step": 4500
    },
    {
      "epoch": 0.93,
      "eval_accuracy": 0.95798564753004,
      "eval_f1": 0.9734293780838544,
      "eval_loss": 0.13109906017780304,
      "eval_precision": 0.9618814204515826,
      "eval_recall": 0.9852579852579852,
      "eval_runtime": 117.9222,
      "eval_samples_per_second": 203.66,
      "eval_steps_per_second": 3.638,
      "step": 4500
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4419753086419754e-05,
      "loss": 0.1164,
      "step": 4520
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4395061728395063e-05,
      "loss": 0.1182,
      "step": 4540
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.437037037037037e-05,
      "loss": 0.1272,
      "step": 4560
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.434567901234568e-05,
      "loss": 0.1372,
      "step": 4580
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.432098765432099e-05,
      "loss": 0.1051,
      "step": 4600
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.4296296296296298e-05,
      "loss": 0.1237,
      "step": 4620
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.4271604938271603e-05,
      "loss": 0.134,
      "step": 4640
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.4246913580246916e-05,
      "loss": 0.0968,
      "step": 4660
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.4222222222222224e-05,
      "loss": 0.1444,
      "step": 4680
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.419753086419753e-05,
      "loss": 0.1229,
      "step": 4700
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.4172839506172842e-05,
      "loss": 0.1147,
      "step": 4720
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.4148148148148148e-05,
      "loss": 0.1271,
      "step": 4740
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.412345679012346e-05,
      "loss": 0.1312,
      "step": 4760
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.4098765432098765e-05,
      "loss": 0.1253,
      "step": 4780
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.1191,
      "step": 4800
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4049382716049383e-05,
      "loss": 0.12,
      "step": 4820
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.4024691358024692e-05,
      "loss": 0.1191,
      "step": 4840
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.4e-05,
      "loss": 0.1113,
      "step": 4860
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.397530864197531e-05,
      "loss": 0.118,
      "step": 4880
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.3950617283950618e-05,
      "loss": 0.1009,
      "step": 4900
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.3925925925925927e-05,
      "loss": 0.0994,
      "step": 4920
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.3901234567901236e-05,
      "loss": 0.1258,
      "step": 4940
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.387654320987654e-05,
      "loss": 0.1148,
      "step": 4960
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.3851851851851854e-05,
      "loss": 0.1353,
      "step": 4980
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.3827160493827162e-05,
      "loss": 0.0948,
      "step": 5000
    },
    {
      "epoch": 1.03,
      "eval_accuracy": 0.9608227636849133,
      "eval_f1": 0.9750816017832975,
      "eval_loss": 0.13325688242912292,
      "eval_precision": 0.9689362375402141,
      "eval_recall": 0.9813054160880248,
      "eval_runtime": 117.992,
      "eval_samples_per_second": 203.539,
      "eval_steps_per_second": 3.636,
      "step": 5000
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.3802469135802468e-05,
      "loss": 0.1017,
      "step": 5020
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.377777777777778e-05,
      "loss": 0.1222,
      "step": 5040
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.3753086419753086e-05,
      "loss": 0.1274,
      "step": 5060
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3728395061728398e-05,
      "loss": 0.0985,
      "step": 5080
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3703703703703703e-05,
      "loss": 0.1219,
      "step": 5100
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3679012345679012e-05,
      "loss": 0.1291,
      "step": 5120
    },
    {
      "epoch": 1.06,
      "learning_rate": 2.3654320987654324e-05,
      "loss": 0.111,
      "step": 5140
    },
    {
      "epoch": 1.06,
      "learning_rate": 2.362962962962963e-05,
      "loss": 0.122,
      "step": 5160
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.360493827160494e-05,
      "loss": 0.1155,
      "step": 5180
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.3580246913580247e-05,
      "loss": 0.1143,
      "step": 5200
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.3555555555555556e-05,
      "loss": 0.1138,
      "step": 5220
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.3530864197530865e-05,
      "loss": 0.0986,
      "step": 5240
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.3506172839506174e-05,
      "loss": 0.1188,
      "step": 5260
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.348148148148148e-05,
      "loss": 0.1039,
      "step": 5280
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.345679012345679e-05,
      "loss": 0.117,
      "step": 5300
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.34320987654321e-05,
      "loss": 0.1051,
      "step": 5320
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.3407407407407406e-05,
      "loss": 0.1184,
      "step": 5340
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.3382716049382718e-05,
      "loss": 0.1118,
      "step": 5360
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.3358024691358024e-05,
      "loss": 0.1039,
      "step": 5380
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.1224,
      "step": 5400
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.330864197530864e-05,
      "loss": 0.1001,
      "step": 5420
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.328395061728395e-05,
      "loss": 0.0947,
      "step": 5440
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.3259259259259262e-05,
      "loss": 0.0956,
      "step": 5460
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.3234567901234568e-05,
      "loss": 0.1144,
      "step": 5480
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.3209876543209877e-05,
      "loss": 0.0724,
      "step": 5500
    },
    {
      "epoch": 1.13,
      "eval_accuracy": 0.9604472630173565,
      "eval_f1": 0.9749033726902102,
      "eval_loss": 0.13315214216709137,
      "eval_precision": 0.9664602141507453,
      "eval_recall": 0.9834953530605705,
      "eval_runtime": 117.9099,
      "eval_samples_per_second": 203.681,
      "eval_steps_per_second": 3.638,
      "step": 5500
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.3185185185185185e-05,
      "loss": 0.1323,
      "step": 5520
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.3160493827160494e-05,
      "loss": 0.1146,
      "step": 5540
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.3135802469135803e-05,
      "loss": 0.0911,
      "step": 5560
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.3111111111111112e-05,
      "loss": 0.0801,
      "step": 5580
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.308641975308642e-05,
      "loss": 0.1175,
      "step": 5600
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.306172839506173e-05,
      "loss": 0.0949,
      "step": 5620
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.303703703703704e-05,
      "loss": 0.1318,
      "step": 5640
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.3012345679012344e-05,
      "loss": 0.1205,
      "step": 5660
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.2987654320987656e-05,
      "loss": 0.1064,
      "step": 5680
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.296296296296296e-05,
      "loss": 0.1026,
      "step": 5700
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.2938271604938274e-05,
      "loss": 0.1171,
      "step": 5720
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.2913580246913583e-05,
      "loss": 0.0932,
      "step": 5740
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.2888888888888888e-05,
      "loss": 0.1065,
      "step": 5760
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.28641975308642e-05,
      "loss": 0.0845,
      "step": 5780
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.2839506172839506e-05,
      "loss": 0.1043,
      "step": 5800
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.2814814814814815e-05,
      "loss": 0.119,
      "step": 5820
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.2790123456790123e-05,
      "loss": 0.0996,
      "step": 5840
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.2765432098765432e-05,
      "loss": 0.0925,
      "step": 5860
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.274074074074074e-05,
      "loss": 0.1106,
      "step": 5880
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.271604938271605e-05,
      "loss": 0.1311,
      "step": 5900
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.269135802469136e-05,
      "loss": 0.0954,
      "step": 5920
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.2666666666666668e-05,
      "loss": 0.1134,
      "step": 5940
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.2641975308641976e-05,
      "loss": 0.0981,
      "step": 5960
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.2617283950617282e-05,
      "loss": 0.1243,
      "step": 5980
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.2592592592592594e-05,
      "loss": 0.119,
      "step": 6000
    },
    {
      "epoch": 1.23,
      "eval_accuracy": 0.9606975967957276,
      "eval_f1": 0.9748262960983431,
      "eval_loss": 0.11842501163482666,
      "eval_precision": 0.975451919991443,
      "eval_recall": 0.9742014742014742,
      "eval_runtime": 117.8591,
      "eval_samples_per_second": 203.769,
      "eval_steps_per_second": 3.64,
      "step": 6000
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.25679012345679e-05,
      "loss": 0.0755,
      "step": 6020
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.2543209876543212e-05,
      "loss": 0.1345,
      "step": 6040
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.251851851851852e-05,
      "loss": 0.1345,
      "step": 6060
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.2493827160493826e-05,
      "loss": 0.1098,
      "step": 6080
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.246913580246914e-05,
      "loss": 0.1108,
      "step": 6100
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.2444444444444444e-05,
      "loss": 0.1012,
      "step": 6120
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.2419753086419753e-05,
      "loss": 0.1102,
      "step": 6140
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.239506172839506e-05,
      "loss": 0.1118,
      "step": 6160
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.237037037037037e-05,
      "loss": 0.096,
      "step": 6180
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.2345679012345682e-05,
      "loss": 0.0819,
      "step": 6200
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.2320987654320988e-05,
      "loss": 0.1192,
      "step": 6220
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.2296296296296297e-05,
      "loss": 0.0985,
      "step": 6240
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.2271604938271606e-05,
      "loss": 0.1228,
      "step": 6260
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.2246913580246914e-05,
      "loss": 0.1563,
      "step": 6280
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.222222222222222e-05,
      "loss": 0.1124,
      "step": 6300
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.2197530864197532e-05,
      "loss": 0.113,
      "step": 6320
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.217283950617284e-05,
      "loss": 0.079,
      "step": 6340
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.214814814814815e-05,
      "loss": 0.1008,
      "step": 6360
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.212345679012346e-05,
      "loss": 0.1113,
      "step": 6380
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.2098765432098764e-05,
      "loss": 0.1208,
      "step": 6400
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.2074074074074076e-05,
      "loss": 0.1179,
      "step": 6420
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.2049382716049382e-05,
      "loss": 0.099,
      "step": 6440
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.202469135802469e-05,
      "loss": 0.1354,
      "step": 6460
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.2e-05,
      "loss": 0.1184,
      "step": 6480
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.1975308641975308e-05,
      "loss": 0.0951,
      "step": 6500
    },
    {
      "epoch": 1.34,
      "eval_accuracy": 0.9622413217623498,
      "eval_f1": 0.9759186823128708,
      "eval_loss": 0.12240301817655563,
      "eval_precision": 0.9723739328702476,
      "eval_recall": 0.9794893707937187,
      "eval_runtime": 118.068,
      "eval_samples_per_second": 203.408,
      "eval_steps_per_second": 3.633,
      "step": 6500
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.195061728395062e-05,
      "loss": 0.1098,
      "step": 6520
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.1925925925925926e-05,
      "loss": 0.1339,
      "step": 6540
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.1901234567901235e-05,
      "loss": 0.1085,
      "step": 6560
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.1876543209876544e-05,
      "loss": 0.0945,
      "step": 6580
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.1851851851851852e-05,
      "loss": 0.1293,
      "step": 6600
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.182716049382716e-05,
      "loss": 0.0976,
      "step": 6620
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.180246913580247e-05,
      "loss": 0.086,
      "step": 6640
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.177777777777778e-05,
      "loss": 0.1261,
      "step": 6660
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.1753086419753088e-05,
      "loss": 0.1047,
      "step": 6680
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.1728395061728397e-05,
      "loss": 0.1114,
      "step": 6700
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.1703703703703702e-05,
      "loss": 0.1019,
      "step": 6720
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.1679012345679014e-05,
      "loss": 0.1104,
      "step": 6740
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.165432098765432e-05,
      "loss": 0.1024,
      "step": 6760
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.1629629629629632e-05,
      "loss": 0.1065,
      "step": 6780
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.160493827160494e-05,
      "loss": 0.0815,
      "step": 6800
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.1580246913580246e-05,
      "loss": 0.0937,
      "step": 6820
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.155555555555556e-05,
      "loss": 0.0692,
      "step": 6840
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.1530864197530864e-05,
      "loss": 0.0806,
      "step": 6860
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.1506172839506173e-05,
      "loss": 0.107,
      "step": 6880
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.148148148148148e-05,
      "loss": 0.1163,
      "step": 6900
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.145679012345679e-05,
      "loss": 0.0935,
      "step": 6920
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.14320987654321e-05,
      "loss": 0.1367,
      "step": 6940
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.1407407407407408e-05,
      "loss": 0.1004,
      "step": 6960
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.1382716049382717e-05,
      "loss": 0.0886,
      "step": 6980
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.1358024691358026e-05,
      "loss": 0.0819,
      "step": 7000
    },
    {
      "epoch": 1.44,
      "eval_accuracy": 0.9604889853137517,
      "eval_f1": 0.9746567827227233,
      "eval_loss": 0.13311195373535156,
      "eval_precision": 0.9766693483507642,
      "eval_recall": 0.9726524943916248,
      "eval_runtime": 119.2139,
      "eval_samples_per_second": 201.453,
      "eval_steps_per_second": 3.599,
      "step": 7000
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1189,
      "step": 7020
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.130864197530864e-05,
      "loss": 0.1069,
      "step": 7040
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.1283950617283952e-05,
      "loss": 0.1283,
      "step": 7060
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.1259259259259258e-05,
      "loss": 0.1003,
      "step": 7080
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.123456790123457e-05,
      "loss": 0.1056,
      "step": 7100
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.120987654320988e-05,
      "loss": 0.1014,
      "step": 7120
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.1185185185185184e-05,
      "loss": 0.1168,
      "step": 7140
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.1160493827160496e-05,
      "loss": 0.0907,
      "step": 7160
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.1135802469135802e-05,
      "loss": 0.0923,
      "step": 7180
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.111111111111111e-05,
      "loss": 0.0988,
      "step": 7200
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.108641975308642e-05,
      "loss": 0.1175,
      "step": 7220
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.106172839506173e-05,
      "loss": 0.0972,
      "step": 7240
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.103703703703704e-05,
      "loss": 0.1246,
      "step": 7260
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.1012345679012346e-05,
      "loss": 0.1101,
      "step": 7280
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 0.1098,
      "step": 7300
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.0962962962962964e-05,
      "loss": 0.0871,
      "step": 7320
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.0938271604938273e-05,
      "loss": 0.084,
      "step": 7340
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.0913580246913578e-05,
      "loss": 0.104,
      "step": 7360
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.088888888888889e-05,
      "loss": 0.1303,
      "step": 7380
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.08641975308642e-05,
      "loss": 0.0962,
      "step": 7400
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.0839506172839508e-05,
      "loss": 0.1089,
      "step": 7420
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.0814814814814817e-05,
      "loss": 0.0981,
      "step": 7440
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.0790123456790122e-05,
      "loss": 0.0792,
      "step": 7460
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.0765432098765434e-05,
      "loss": 0.1249,
      "step": 7480
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.074074074074074e-05,
      "loss": 0.127,
      "step": 7500
    },
    {
      "epoch": 1.54,
      "eval_accuracy": 0.962700267022697,
      "eval_f1": 0.976176517614454,
      "eval_loss": 0.11449769884347916,
      "eval_precision": 0.9740480748776856,
      "eval_recall": 0.9783142826621087,
      "eval_runtime": 118.8781,
      "eval_samples_per_second": 202.022,
      "eval_steps_per_second": 3.609,
      "step": 7500
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.071604938271605e-05,
      "loss": 0.0836,
      "step": 7520
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.0691358024691358e-05,
      "loss": 0.0979,
      "step": 7540
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.0666666666666666e-05,
      "loss": 0.1134,
      "step": 7560
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.064197530864198e-05,
      "loss": 0.0892,
      "step": 7580
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.0617283950617284e-05,
      "loss": 0.1021,
      "step": 7600
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0592592592592593e-05,
      "loss": 0.1197,
      "step": 7620
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.0567901234567902e-05,
      "loss": 0.0848,
      "step": 7640
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.054320987654321e-05,
      "loss": 0.1178,
      "step": 7660
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.0518518518518516e-05,
      "loss": 0.0788,
      "step": 7680
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.0493827160493828e-05,
      "loss": 0.1155,
      "step": 7700
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.0469135802469137e-05,
      "loss": 0.1142,
      "step": 7720
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.0444444444444446e-05,
      "loss": 0.09,
      "step": 7740
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.0419753086419755e-05,
      "loss": 0.1027,
      "step": 7760
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.039506172839506e-05,
      "loss": 0.0836,
      "step": 7780
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.0370370370370372e-05,
      "loss": 0.0839,
      "step": 7800
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.0345679012345678e-05,
      "loss": 0.1156,
      "step": 7820
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.0320987654320987e-05,
      "loss": 0.0997,
      "step": 7840
    },
    {
      "epoch": 1.62,
      "learning_rate": 2.02962962962963e-05,
      "loss": 0.1058,
      "step": 7860
    },
    {
      "epoch": 1.62,
      "learning_rate": 2.0271604938271604e-05,
      "loss": 0.1151,
      "step": 7880
    },
    {
      "epoch": 1.63,
      "learning_rate": 2.0246913580246917e-05,
      "loss": 0.092,
      "step": 7900
    },
    {
      "epoch": 1.63,
      "learning_rate": 2.0222222222222222e-05,
      "loss": 0.0875,
      "step": 7920
    },
    {
      "epoch": 1.63,
      "learning_rate": 2.019753086419753e-05,
      "loss": 0.1045,
      "step": 7940
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.017283950617284e-05,
      "loss": 0.1227,
      "step": 7960
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.014814814814815e-05,
      "loss": 0.1071,
      "step": 7980
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.0123456790123457e-05,
      "loss": 0.0941,
      "step": 8000
    },
    {
      "epoch": 1.65,
      "eval_accuracy": 0.9632843791722296,
      "eval_f1": 0.9765745621040303,
      "eval_loss": 0.1196218952536583,
      "eval_precision": 0.9734132880492464,
      "eval_recall": 0.9797564362781754,
      "eval_runtime": 119.025,
      "eval_samples_per_second": 201.773,
      "eval_steps_per_second": 3.604,
      "step": 8000
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.0098765432098766e-05,
      "loss": 0.1148,
      "step": 8020
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.0074074074074075e-05,
      "loss": 0.0743,
      "step": 8040
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.0049382716049384e-05,
      "loss": 0.1345,
      "step": 8060
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.0024691358024693e-05,
      "loss": 0.0996,
      "step": 8080
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.0957,
      "step": 8100
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.997530864197531e-05,
      "loss": 0.1243,
      "step": 8120
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.9950617283950616e-05,
      "loss": 0.1107,
      "step": 8140
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.9925925925925925e-05,
      "loss": 0.1135,
      "step": 8160
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.9901234567901237e-05,
      "loss": 0.1369,
      "step": 8180
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.9876543209876542e-05,
      "loss": 0.1048,
      "step": 8200
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.9851851851851855e-05,
      "loss": 0.0905,
      "step": 8220
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.982716049382716e-05,
      "loss": 0.0722,
      "step": 8240
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.980246913580247e-05,
      "loss": 0.0888,
      "step": 8260
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.9777777777777778e-05,
      "loss": 0.1043,
      "step": 8280
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 0.1128,
      "step": 8300
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.9728395061728395e-05,
      "loss": 0.0871,
      "step": 8320
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.9703703703703704e-05,
      "loss": 0.0937,
      "step": 8340
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.9679012345679013e-05,
      "loss": 0.1066,
      "step": 8360
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.9654320987654322e-05,
      "loss": 0.0968,
      "step": 8380
    },
    {
      "epoch": 1.73,
      "learning_rate": 1.962962962962963e-05,
      "loss": 0.0972,
      "step": 8400
    },
    {
      "epoch": 1.73,
      "learning_rate": 1.9604938271604936e-05,
      "loss": 0.0909,
      "step": 8420
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.958024691358025e-05,
      "loss": 0.1374,
      "step": 8440
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 0.1248,
      "step": 8460
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.9530864197530863e-05,
      "loss": 0.1214,
      "step": 8480
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.9506172839506175e-05,
      "loss": 0.1126,
      "step": 8500
    },
    {
      "epoch": 1.75,
      "eval_accuracy": 0.9621161548731643,
      "eval_f1": 0.9759240600307578,
      "eval_loss": 0.1229991540312767,
      "eval_precision": 0.9689869418702611,
      "eval_recall": 0.9829612220916569,
      "eval_runtime": 118.0869,
      "eval_samples_per_second": 203.376,
      "eval_steps_per_second": 3.633,
      "step": 8500
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.948148148148148e-05,
      "loss": 0.0955,
      "step": 8520
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.9456790123456793e-05,
      "loss": 0.1143,
      "step": 8540
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.9432098765432098e-05,
      "loss": 0.0861,
      "step": 8560
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.9407407407407407e-05,
      "loss": 0.1063,
      "step": 8580
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.9382716049382716e-05,
      "loss": 0.0943,
      "step": 8600
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.9358024691358025e-05,
      "loss": 0.0877,
      "step": 8620
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 0.1026,
      "step": 8640
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.9308641975308642e-05,
      "loss": 0.1131,
      "step": 8660
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.928395061728395e-05,
      "loss": 0.0792,
      "step": 8680
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.925925925925926e-05,
      "loss": 0.1341,
      "step": 8700
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.923456790123457e-05,
      "loss": 0.0976,
      "step": 8720
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.9209876543209874e-05,
      "loss": 0.1013,
      "step": 8740
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.9185185185185186e-05,
      "loss": 0.1113,
      "step": 8760
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.9160493827160495e-05,
      "loss": 0.0925,
      "step": 8780
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.9135802469135804e-05,
      "loss": 0.1121,
      "step": 8800
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 0.0796,
      "step": 8820
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.908641975308642e-05,
      "loss": 0.0917,
      "step": 8840
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.906172839506173e-05,
      "loss": 0.1036,
      "step": 8860
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.9037037037037036e-05,
      "loss": 0.1078,
      "step": 8880
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.9012345679012345e-05,
      "loss": 0.1065,
      "step": 8900
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.8987654320987657e-05,
      "loss": 0.07,
      "step": 8920
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.8962962962962963e-05,
      "loss": 0.0851,
      "step": 8940
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.8938271604938275e-05,
      "loss": 0.1354,
      "step": 8960
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.891358024691358e-05,
      "loss": 0.1199,
      "step": 8980
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.888888888888889e-05,
      "loss": 0.0819,
      "step": 9000
    },
    {
      "epoch": 1.85,
      "eval_accuracy": 0.9624499332443258,
      "eval_f1": 0.9760549140637471,
      "eval_loss": 0.12362895160913467,
      "eval_precision": 0.9723812553011026,
      "eval_recall": 0.9797564362781754,
      "eval_runtime": 118.6044,
      "eval_samples_per_second": 202.488,
      "eval_steps_per_second": 3.617,
      "step": 9000
    }
  ],
  "logging_steps": 20,
  "max_steps": 24300,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.69693407117312e+17,
  "trial_name": null,
  "trial_params": null
}