{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.999775432292836,
  "global_step": 27830,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 0.9801,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 0.9375,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 0.8924,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 0.8901,
      "step": 200
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 0.8608,
      "step": 250
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 0.8033,
      "step": 300
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 0.826,
      "step": 350
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 0.8897,
      "step": 400
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 0.8379,
      "step": 450
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 0.8547,
      "step": 500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 0.8092,
      "step": 550
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 0.8155,
      "step": 600
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 0.7923,
      "step": 650
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 0.8267,
      "step": 700
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 0.8055,
      "step": 750
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 0.8084,
      "step": 800
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 0.8232,
      "step": 850
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 0.7805,
      "step": 900
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 0.8009,
      "step": 950
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 0.7566,
      "step": 1000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 0.7745,
      "step": 1050
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 0.7858,
      "step": 1100
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 0.7508,
      "step": 1150
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 0.8148,
      "step": 1200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 0.8054,
      "step": 1250
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 0.8149,
      "step": 1300
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 0.7903,
      "step": 1350
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 0.7937,
      "step": 1400
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 0.7489,
      "step": 1450
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 0.7783,
      "step": 1500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 0.7757,
      "step": 1550
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 0.7746,
      "step": 1600
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 0.778,
      "step": 1650
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 0.7951,
      "step": 1700
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 0.7764,
      "step": 1750
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 0.7385,
      "step": 1800
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 0.7503,
      "step": 1850
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 0.7673,
      "step": 1900
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 0.7718,
      "step": 1950
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 0.7988,
      "step": 2000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 0.7394,
      "step": 2050
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 0.7757,
      "step": 2100
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 0.7381,
      "step": 2150
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 0.7857,
      "step": 2200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 0.798,
      "step": 2250
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 0.7987,
      "step": 2300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 0.74,
      "step": 2350
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 0.7832,
      "step": 2400
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 0.7566,
      "step": 2450
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 0.7863,
      "step": 2500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 0.7419,
      "step": 2550
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 0.7553,
      "step": 2600
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 0.7749,
      "step": 2650
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 0.8235,
      "step": 2700
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 0.7366,
      "step": 2750
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 0.802,
      "step": 2800
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 0.7669,
      "step": 2850
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 0.7899,
      "step": 2900
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 0.7651,
      "step": 2950
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 0.7202,
      "step": 3000
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 0.7423,
      "step": 3050
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 0.7732,
      "step": 3100
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 0.7635,
      "step": 3150
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 0.7664,
      "step": 3200
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 0.7623,
      "step": 3250
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 0.7787,
      "step": 3300
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 0.7563,
      "step": 3350
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 0.7318,
      "step": 3400
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 0.762,
      "step": 3450
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 0.782,
      "step": 3500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 0.8114,
      "step": 3550
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 0.7182,
      "step": 3600
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 0.7546,
      "step": 3650
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 0.7953,
      "step": 3700
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 0.7772,
      "step": 3750
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 0.7737,
      "step": 3800
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 0.7334,
      "step": 3850
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 0.7713,
      "step": 3900
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 0.772,
      "step": 3950
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 0.7964,
      "step": 4000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 0.7997,
      "step": 4050
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 0.7341,
      "step": 4100
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 0.7837,
      "step": 4150
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 0.7973,
      "step": 4200
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 0.775,
      "step": 4250
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 0.7599,
      "step": 4300
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 0.7406,
      "step": 4350
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 0.7875,
      "step": 4400
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 0.7264,
      "step": 4450
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001,
      "loss": 0.7318,
      "step": 4500
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001,
      "loss": 0.7532,
      "step": 4550
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001,
      "loss": 0.7386,
      "step": 4600
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 0.7729,
      "step": 4650
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 0.7428,
      "step": 4700
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 0.7561,
      "step": 4750
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001,
      "loss": 0.7798,
      "step": 4800
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001,
      "loss": 0.7675,
      "step": 4850
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001,
      "loss": 0.7443,
      "step": 4900
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 0.7992,
      "step": 4950
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 0.7841,
      "step": 5000
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 0.7626,
      "step": 5050
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001,
      "loss": 0.7272,
      "step": 5100
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001,
      "loss": 0.7563,
      "step": 5150
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001,
      "loss": 0.732,
      "step": 5200
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 0.7397,
      "step": 5250
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001,
      "loss": 0.723,
      "step": 5300
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001,
      "loss": 0.7764,
      "step": 5350
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001,
      "loss": 0.7605,
      "step": 5400
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001,
      "loss": 0.7118,
      "step": 5450
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001,
      "loss": 0.7386,
      "step": 5500
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 0.7196,
      "step": 5550
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7622227668762207,
      "eval_runtime": 209.9187,
      "eval_samples_per_second": 15.306,
      "eval_steps_per_second": 0.958,
      "step": 5566
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 0.6938,
      "step": 5600
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001,
      "loss": 0.6087,
      "step": 5650
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001,
      "loss": 0.6136,
      "step": 5700
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001,
      "loss": 0.6061,
      "step": 5750
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 0.6124,
      "step": 5800
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001,
      "loss": 0.5955,
      "step": 5850
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001,
      "loss": 0.6269,
      "step": 5900
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001,
      "loss": 0.6517,
      "step": 5950
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001,
      "loss": 0.6251,
      "step": 6000
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001,
      "loss": 0.6702,
      "step": 6050
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 0.6072,
      "step": 6100
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 0.6186,
      "step": 6150
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001,
      "loss": 0.6037,
      "step": 6200
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001,
      "loss": 0.5849,
      "step": 6250
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001,
      "loss": 0.5903,
      "step": 6300
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001,
      "loss": 0.6206,
      "step": 6350
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001,
      "loss": 0.6017,
      "step": 6400
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 0.5683,
      "step": 6450
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 0.6193,
      "step": 6500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001,
      "loss": 0.619,
      "step": 6550
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001,
      "loss": 0.5784,
      "step": 6600
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001,
      "loss": 0.6097,
      "step": 6650
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001,
      "loss": 0.598,
      "step": 6700
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001,
      "loss": 0.5999,
      "step": 6750
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001,
      "loss": 0.6172,
      "step": 6800
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001,
      "loss": 0.677,
      "step": 6850
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001,
      "loss": 0.6057,
      "step": 6900
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 0.6055,
      "step": 6950
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001,
      "loss": 0.6023,
      "step": 7000
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001,
      "loss": 0.6063,
      "step": 7050
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 0.6092,
      "step": 7100
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 0.622,
      "step": 7150
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001,
      "loss": 0.5788,
      "step": 7200
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001,
      "loss": 0.6234,
      "step": 7250
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001,
      "loss": 0.566,
      "step": 7300
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001,
      "loss": 0.6285,
      "step": 7350
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001,
      "loss": 0.5961,
      "step": 7400
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 0.5837,
      "step": 7450
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001,
      "loss": 0.6118,
      "step": 7500
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001,
      "loss": 0.6089,
      "step": 7550
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001,
      "loss": 0.6041,
      "step": 7600
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001,
      "loss": 0.607,
      "step": 7650
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001,
      "loss": 0.6613,
      "step": 7700
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001,
      "loss": 0.6176,
      "step": 7750
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001,
      "loss": 0.5791,
      "step": 7800
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001,
      "loss": 0.6092,
      "step": 7850
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001,
      "loss": 0.6262,
      "step": 7900
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001,
      "loss": 0.6086,
      "step": 7950
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001,
      "loss": 0.5735,
      "step": 8000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001,
      "loss": 0.6109,
      "step": 8050
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001,
      "loss": 0.6125,
      "step": 8100
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001,
      "loss": 0.6218,
      "step": 8150
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 0.6117,
      "step": 8200
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001,
      "loss": 0.5824,
      "step": 8250
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001,
      "loss": 0.6448,
      "step": 8300
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001,
      "loss": 0.6563,
      "step": 8350
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001,
      "loss": 0.6707,
      "step": 8400
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001,
      "loss": 0.6097,
      "step": 8450
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 0.5972,
      "step": 8500
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001,
      "loss": 0.6104,
      "step": 8550
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001,
      "loss": 0.601,
      "step": 8600
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001,
      "loss": 0.581,
      "step": 8650
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001,
      "loss": 0.6065,
      "step": 8700
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001,
      "loss": 0.5787,
      "step": 8750
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001,
      "loss": 0.6347,
      "step": 8800
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001,
      "loss": 0.6461,
      "step": 8850
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001,
      "loss": 0.6046,
      "step": 8900
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001,
      "loss": 0.6498,
      "step": 8950
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001,
      "loss": 0.6283,
      "step": 9000
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001,
      "loss": 0.6221,
      "step": 9050
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001,
      "loss": 0.6324,
      "step": 9100
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001,
      "loss": 0.6142,
      "step": 9150
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001,
      "loss": 0.5834,
      "step": 9200
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001,
      "loss": 0.6326,
      "step": 9250
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001,
      "loss": 0.5982,
      "step": 9300
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001,
      "loss": 0.5965,
      "step": 9350
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001,
      "loss": 0.6052,
      "step": 9400
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001,
      "loss": 0.6658,
      "step": 9450
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001,
      "loss": 0.6163,
      "step": 9500
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001,
      "loss": 0.6627,
      "step": 9550
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001,
      "loss": 0.6203,
      "step": 9600
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001,
      "loss": 0.633,
      "step": 9650
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001,
      "loss": 0.651,
      "step": 9700
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001,
      "loss": 0.5837,
      "step": 9750
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001,
      "loss": 0.6166,
      "step": 9800
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001,
      "loss": 0.5995,
      "step": 9850
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001,
      "loss": 0.5883,
      "step": 9900
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001,
      "loss": 0.5918,
      "step": 9950
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001,
      "loss": 0.5785,
      "step": 10000
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001,
      "loss": 0.6557,
      "step": 10050
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001,
      "loss": 0.5912,
      "step": 10100
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001,
      "loss": 0.6109,
      "step": 10150
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001,
      "loss": 0.599,
      "step": 10200
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001,
      "loss": 0.6325,
      "step": 10250
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001,
      "loss": 0.6339,
      "step": 10300
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001,
      "loss": 0.6074,
      "step": 10350
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001,
      "loss": 0.5943,
      "step": 10400
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001,
      "loss": 0.6133,
      "step": 10450
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 0.5984,
      "step": 10500
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001,
      "loss": 0.6695,
      "step": 10550
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001,
      "loss": 0.591,
      "step": 10600
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001,
      "loss": 0.6208,
      "step": 10650
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001,
      "loss": 0.5744,
      "step": 10700
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001,
      "loss": 0.5873,
      "step": 10750
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001,
      "loss": 0.6261,
      "step": 10800
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 0.617,
      "step": 10850
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001,
      "loss": 0.6151,
      "step": 10900
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001,
      "loss": 0.5936,
      "step": 10950
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001,
      "loss": 0.6366,
      "step": 11000
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001,
      "loss": 0.644,
      "step": 11050
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001,
      "loss": 0.6302,
      "step": 11100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7252166271209717,
      "eval_runtime": 201.6817,
      "eval_samples_per_second": 15.931,
      "eval_steps_per_second": 0.997,
      "step": 11132
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001,
      "loss": 0.5489,
      "step": 11150
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001,
      "loss": 0.5112,
      "step": 11200
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001,
      "loss": 0.4868,
      "step": 11250
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001,
      "loss": 0.483,
      "step": 11300
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001,
      "loss": 0.4569,
      "step": 11350
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001,
      "loss": 0.4638,
      "step": 11400
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0001,
      "loss": 0.4764,
      "step": 11450
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001,
      "loss": 0.4984,
      "step": 11500
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001,
      "loss": 0.4797,
      "step": 11550
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001,
      "loss": 0.4924,
      "step": 11600
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001,
      "loss": 0.4921,
      "step": 11650
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001,
      "loss": 0.4652,
      "step": 11700
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001,
      "loss": 0.4842,
      "step": 11750
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001,
      "loss": 0.4982,
      "step": 11800
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001,
      "loss": 0.4682,
      "step": 11850
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001,
      "loss": 0.4642,
      "step": 11900
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001,
      "loss": 0.4982,
      "step": 11950
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001,
      "loss": 0.5336,
      "step": 12000
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001,
      "loss": 0.4739,
      "step": 12050
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001,
      "loss": 0.4938,
      "step": 12100
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001,
      "loss": 0.5114,
      "step": 12150
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001,
      "loss": 0.4893,
      "step": 12200
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001,
      "loss": 0.4924,
      "step": 12250
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001,
      "loss": 0.4826,
      "step": 12300
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001,
      "loss": 0.4651,
      "step": 12350
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001,
      "loss": 0.5192,
      "step": 12400
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001,
      "loss": 0.5012,
      "step": 12450
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001,
      "loss": 0.4913,
      "step": 12500
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001,
      "loss": 0.4999,
      "step": 12550
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001,
      "loss": 0.5245,
      "step": 12600
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001,
      "loss": 0.5264,
      "step": 12650
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001,
      "loss": 0.5132,
      "step": 12700
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0001,
      "loss": 0.4598,
      "step": 12750
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001,
      "loss": 0.4883,
      "step": 12800
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001,
      "loss": 0.5397,
      "step": 12850
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001,
      "loss": 0.5253,
      "step": 12900
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001,
      "loss": 0.5067,
      "step": 12950
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 0.4831,
      "step": 13000
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 0.482,
      "step": 13050
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001,
      "loss": 0.5039,
      "step": 13100
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001,
      "loss": 0.473,
      "step": 13150
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001,
      "loss": 0.5094,
      "step": 13200
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001,
      "loss": 0.4866,
      "step": 13250
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0001,
      "loss": 0.4881,
      "step": 13300
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001,
      "loss": 0.5268,
      "step": 13350
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001,
      "loss": 0.5188,
      "step": 13400
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001,
      "loss": 0.501,
      "step": 13450
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0001,
      "loss": 0.5135,
      "step": 13500
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0001,
      "loss": 0.5056,
      "step": 13550
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001,
      "loss": 0.5062,
      "step": 13600
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001,
      "loss": 0.4823,
      "step": 13650
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0001,
      "loss": 0.4636,
      "step": 13700
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001,
      "loss": 0.507,
      "step": 13750
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001,
      "loss": 0.4648,
      "step": 13800
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001,
      "loss": 0.5061,
      "step": 13850
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001,
      "loss": 0.4872,
      "step": 13900
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001,
      "loss": 0.4897,
      "step": 13950
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001,
      "loss": 0.5166,
      "step": 14000
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001,
      "loss": 0.4764,
      "step": 14050
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001,
      "loss": 0.5094,
      "step": 14100
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001,
      "loss": 0.4821,
      "step": 14150
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0001,
      "loss": 0.5222,
      "step": 14200
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001,
      "loss": 0.4904,
      "step": 14250
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0001,
      "loss": 0.5085,
      "step": 14300
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0001,
      "loss": 0.4719,
      "step": 14350
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0001,
      "loss": 0.5112,
      "step": 14400
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001,
      "loss": 0.5052,
      "step": 14450
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001,
      "loss": 0.5457,
      "step": 14500
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0001,
      "loss": 0.5034,
      "step": 14550
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001,
      "loss": 0.5023,
      "step": 14600
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0001,
      "loss": 0.4967,
      "step": 14650
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001,
      "loss": 0.5124,
      "step": 14700
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001,
      "loss": 0.4987,
      "step": 14750
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0001,
      "loss": 0.5234,
      "step": 14800
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001,
      "loss": 0.4957,
      "step": 14850
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0001,
      "loss": 0.516,
      "step": 14900
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0001,
      "loss": 0.479,
      "step": 14950
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0001,
      "loss": 0.5057,
      "step": 15000
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0001,
      "loss": 0.5224,
      "step": 15050
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0001,
      "loss": 0.5428,
      "step": 15100
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0001,
      "loss": 0.4645,
      "step": 15150
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0001,
      "loss": 0.5114,
      "step": 15200
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001,
      "loss": 0.5074,
      "step": 15250
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0001,
      "loss": 0.5103,
      "step": 15300
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001,
      "loss": 0.5326,
      "step": 15350
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0001,
      "loss": 0.5023,
      "step": 15400
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001,
      "loss": 0.467,
      "step": 15450
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001,
      "loss": 0.4833,
      "step": 15500
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001,
      "loss": 0.5119,
      "step": 15550
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001,
      "loss": 0.5181,
      "step": 15600
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0001,
      "loss": 0.4917,
      "step": 15650
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0001,
      "loss": 0.5281,
      "step": 15700
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001,
      "loss": 0.4971,
      "step": 15750
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001,
      "loss": 0.483,
      "step": 15800
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0001,
      "loss": 0.5254,
      "step": 15850
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001,
      "loss": 0.5838,
      "step": 15900
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0001,
      "loss": 0.5201,
      "step": 15950
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0001,
      "loss": 0.5232,
      "step": 16000
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001,
      "loss": 0.5249,
      "step": 16050
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0001,
      "loss": 0.4707,
      "step": 16100
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001,
      "loss": 0.5058,
      "step": 16150
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0001,
      "loss": 0.4838,
      "step": 16200
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0001,
      "loss": 0.5012,
      "step": 16250
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001,
      "loss": 0.5369,
      "step": 16300
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0001,
      "loss": 0.5372,
      "step": 16350
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0001,
      "loss": 0.5441,
      "step": 16400
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0001,
      "loss": 0.5506,
      "step": 16450
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0001,
      "loss": 0.5412,
      "step": 16500
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0001,
      "loss": 0.4903,
      "step": 16550
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0001,
      "loss": 0.5145,
      "step": 16600
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0001,
      "loss": 0.5237,
      "step": 16650
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7354088425636292,
      "eval_runtime": 207.8886,
      "eval_samples_per_second": 15.455,
      "eval_steps_per_second": 0.967,
      "step": 16698
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0001,
      "loss": 0.5086,
      "step": 16700
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0001,
      "loss": 0.4071,
      "step": 16750
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0001,
      "loss": 0.4299,
      "step": 16800
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0001,
      "loss": 0.3996,
      "step": 16850
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001,
      "loss": 0.412,
      "step": 16900
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001,
      "loss": 0.4214,
      "step": 16950
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001,
      "loss": 0.3986,
      "step": 17000
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0001,
      "loss": 0.4177,
      "step": 17050
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0001,
      "loss": 0.3833,
      "step": 17100
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001,
      "loss": 0.4054,
      "step": 17150
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0001,
      "loss": 0.3802,
      "step": 17200
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0001,
      "loss": 0.4142,
      "step": 17250
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0001,
      "loss": 0.3996,
      "step": 17300
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001,
      "loss": 0.4025,
      "step": 17350
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0001,
      "loss": 0.3554,
      "step": 17400
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0001,
      "loss": 0.3842,
      "step": 17450
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0001,
      "loss": 0.3796,
      "step": 17500
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0001,
      "loss": 0.3765,
      "step": 17550
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0001,
      "loss": 0.4065,
      "step": 17600
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0001,
      "loss": 0.3981,
      "step": 17650
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0001,
      "loss": 0.4013,
      "step": 17700
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001,
      "loss": 0.4043,
      "step": 17750
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0001,
      "loss": 0.422,
      "step": 17800
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.0001,
      "loss": 0.4058,
      "step": 17850
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0001,
      "loss": 0.3772,
      "step": 17900
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0001,
      "loss": 0.3926,
      "step": 17950
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0001,
      "loss": 0.3846,
      "step": 18000
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0001,
      "loss": 0.4259,
      "step": 18050
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001,
      "loss": 0.3775,
      "step": 18100
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0001,
      "loss": 0.4124,
      "step": 18150
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0001,
      "loss": 0.404,
      "step": 18200
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0001,
      "loss": 0.4017,
      "step": 18250
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0001,
      "loss": 0.4419,
      "step": 18300
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0001,
      "loss": 0.4284,
      "step": 18350
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0001,
      "loss": 0.4295,
      "step": 18400
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0001,
      "loss": 0.4021,
      "step": 18450
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0001,
      "loss": 0.4314,
      "step": 18500
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0001,
      "loss": 0.4332,
      "step": 18550
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0001,
      "loss": 0.3919,
      "step": 18600
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0001,
      "loss": 0.4467,
      "step": 18650
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0001,
      "loss": 0.3978,
      "step": 18700
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0001,
      "loss": 0.4264,
      "step": 18750
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0001,
      "loss": 0.421,
      "step": 18800
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.0001,
      "loss": 0.4217,
      "step": 18850
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0001,
      "loss": 0.4244,
      "step": 18900
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0001,
      "loss": 0.3918,
      "step": 18950
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0001,
      "loss": 0.4048,
      "step": 19000
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001,
      "loss": 0.4142,
      "step": 19050
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0001,
      "loss": 0.4071,
      "step": 19100
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0001,
      "loss": 0.39,
      "step": 19150
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0001,
      "loss": 0.3983,
      "step": 19200
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001,
      "loss": 0.4342,
      "step": 19250
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0001,
      "loss": 0.4071,
      "step": 19300
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0001,
      "loss": 0.4294,
      "step": 19350
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0001,
      "loss": 0.3989,
      "step": 19400
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0001,
      "loss": 0.4115,
      "step": 19450
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0001,
      "loss": 0.4238,
      "step": 19500
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0001,
      "loss": 0.3964,
      "step": 19550
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0001,
      "loss": 0.4103,
      "step": 19600
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0001,
      "loss": 0.416,
      "step": 19650
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0001,
      "loss": 0.4362,
      "step": 19700
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0001,
      "loss": 0.4094,
      "step": 19750
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0001,
      "loss": 0.4167,
      "step": 19800
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0001,
      "loss": 0.4025,
      "step": 19850
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0001,
      "loss": 0.3804,
      "step": 19900
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0001,
      "loss": 0.4188,
      "step": 19950
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0001,
      "loss": 0.4333,
      "step": 20000
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0001,
      "loss": 0.4001,
      "step": 20050
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0001,
      "loss": 0.3774,
      "step": 20100
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0001,
      "loss": 0.4332,
      "step": 20150
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001,
      "loss": 0.4342,
      "step": 20200
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0001,
      "loss": 0.4147,
      "step": 20250
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0001,
      "loss": 0.4372,
      "step": 20300
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0001,
      "loss": 0.3962,
      "step": 20350
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0001,
      "loss": 0.4262,
      "step": 20400
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0001,
      "loss": 0.4362,
      "step": 20450
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0001,
      "loss": 0.4112,
      "step": 20500
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0001,
      "loss": 0.4011,
      "step": 20550
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0001,
      "loss": 0.3906,
      "step": 20600
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0001,
      "loss": 0.4094,
      "step": 20650
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0001,
      "loss": 0.4302,
      "step": 20700
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0001,
      "loss": 0.4143,
      "step": 20750
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0001,
      "loss": 0.398,
      "step": 20800
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.0001,
      "loss": 0.43,
      "step": 20850
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.0001,
      "loss": 0.4124,
      "step": 20900
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0001,
      "loss": 0.4167,
      "step": 20950
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0001,
      "loss": 0.4219,
      "step": 21000
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0001,
      "loss": 0.4264,
      "step": 21050
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0001,
      "loss": 0.435,
      "step": 21100
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0001,
      "loss": 0.4449,
      "step": 21150
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0001,
      "loss": 0.4595,
      "step": 21200
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0001,
      "loss": 0.4202,
      "step": 21250
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0001,
      "loss": 0.3981,
      "step": 21300
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.0001,
      "loss": 0.4261,
      "step": 21350
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.0001,
      "loss": 0.4412,
      "step": 21400
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0001,
      "loss": 0.3918,
      "step": 21450
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0001,
      "loss": 0.4354,
      "step": 21500
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0001,
      "loss": 0.4373,
      "step": 21550
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0001,
      "loss": 0.4302,
      "step": 21600
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0001,
      "loss": 0.4113,
      "step": 21650
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0001,
      "loss": 0.392,
      "step": 21700
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0001,
      "loss": 0.4335,
      "step": 21750
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0001,
      "loss": 0.4211,
      "step": 21800
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001,
      "loss": 0.4178,
      "step": 21850
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001,
      "loss": 0.4333,
      "step": 21900
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0001,
      "loss": 0.4438,
      "step": 21950
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0001,
      "loss": 0.4118,
      "step": 22000
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0001,
      "loss": 0.4256,
      "step": 22050
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0001,
      "loss": 0.4394,
      "step": 22100
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0001,
      "loss": 0.4329,
      "step": 22150
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.0001,
      "loss": 0.4481,
      "step": 22200
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0001,
      "loss": 0.4215,
      "step": 22250
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.7574929594993591,
      "eval_runtime": 207.1872,
      "eval_samples_per_second": 15.508,
      "eval_steps_per_second": 0.97,
      "step": 22265
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0001,
      "loss": 0.3323,
      "step": 22300
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001,
      "loss": 0.3289,
      "step": 22350
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001,
      "loss": 0.3332,
      "step": 22400
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0001,
      "loss": 0.3404,
      "step": 22450
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.0001,
      "loss": 0.3108,
      "step": 22500
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0001,
      "loss": 0.3362,
      "step": 22550
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0001,
      "loss": 0.3105,
      "step": 22600
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0001,
      "loss": 0.3056,
      "step": 22650
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0001,
      "loss": 0.3253,
      "step": 22700
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0001,
      "loss": 0.3151,
      "step": 22750
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0001,
      "loss": 0.3482,
      "step": 22800
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0001,
      "loss": 0.3216,
      "step": 22850
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0001,
      "loss": 0.3492,
      "step": 22900
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0001,
      "loss": 0.3172,
      "step": 22950
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0001,
      "loss": 0.3397,
      "step": 23000
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0001,
      "loss": 0.3569,
      "step": 23050
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.0001,
      "loss": 0.3143,
      "step": 23100
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0001,
      "loss": 0.313,
      "step": 23150
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0001,
      "loss": 0.3394,
      "step": 23200
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.0001,
      "loss": 0.3434,
      "step": 23250
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001,
      "loss": 0.3217,
      "step": 23300
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001,
      "loss": 0.3066,
      "step": 23350
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0001,
      "loss": 0.3317,
      "step": 23400
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0001,
      "loss": 0.3496,
      "step": 23450
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0001,
      "loss": 0.3313,
      "step": 23500
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0001,
      "loss": 0.3496,
      "step": 23550
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0001,
      "loss": 0.3218,
      "step": 23600
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001,
      "loss": 0.3474,
      "step": 23650
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0001,
      "loss": 0.3447,
      "step": 23700
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0001,
      "loss": 0.3166,
      "step": 23750
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.0001,
      "loss": 0.3571,
      "step": 23800
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.0001,
      "loss": 0.3497,
      "step": 23850
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001,
      "loss": 0.3384,
      "step": 23900
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0001,
      "loss": 0.3305,
      "step": 23950
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0001,
      "loss": 0.3372,
      "step": 24000
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.0001,
      "loss": 0.3429,
      "step": 24050
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0001,
      "loss": 0.3241,
      "step": 24100
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001,
      "loss": 0.3267,
      "step": 24150
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0001,
      "loss": 0.3426,
      "step": 24200
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0001,
      "loss": 0.3445,
      "step": 24250
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001,
      "loss": 0.3387,
      "step": 24300
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001,
      "loss": 0.3388,
      "step": 24350
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.0001,
      "loss": 0.343,
      "step": 24400
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001,
      "loss": 0.3596,
      "step": 24450
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0001,
      "loss": 0.3675,
      "step": 24500
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001,
      "loss": 0.3494,
      "step": 24550
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0001,
      "loss": 0.3435,
      "step": 24600
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0001,
      "loss": 0.3374,
      "step": 24650
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0001,
      "loss": 0.3486,
      "step": 24700
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0001,
      "loss": 0.3753,
      "step": 24750
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0001,
      "loss": 0.3417,
      "step": 24800
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0001,
      "loss": 0.3431,
      "step": 24850
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0001,
      "loss": 0.3354,
      "step": 24900
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001,
      "loss": 0.3351,
      "step": 24950
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0001,
      "loss": 0.3239,
      "step": 25000
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001,
      "loss": 0.3404,
      "step": 25050
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0001,
      "loss": 0.3418,
      "step": 25100
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0001,
      "loss": 0.3809,
      "step": 25150
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.0001,
      "loss": 0.3399,
      "step": 25200
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0001,
      "loss": 0.3327,
      "step": 25250
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0001,
      "loss": 0.3445,
      "step": 25300
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0001,
      "loss": 0.3208,
      "step": 25350
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0001,
      "loss": 0.3522,
      "step": 25400
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0001,
      "loss": 0.3467,
      "step": 25450
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.0001,
      "loss": 0.34,
      "step": 25500
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.0001,
      "loss": 0.3376,
      "step": 25550
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0001,
      "loss": 0.329,
      "step": 25600
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0001,
      "loss": 0.333,
      "step": 25650
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0001,
      "loss": 0.3547,
      "step": 25700
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0001,
      "loss": 0.345,
      "step": 25750
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001,
      "loss": 0.3507,
      "step": 25800
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001,
      "loss": 0.3705,
      "step": 25850
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0001,
      "loss": 0.3417,
      "step": 25900
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0001,
      "loss": 0.3667,
      "step": 25950
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0001,
      "loss": 0.3328,
      "step": 26000
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001,
      "loss": 0.3337,
      "step": 26050
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0001,
      "loss": 0.3462,
      "step": 26100
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0001,
      "loss": 0.3463,
      "step": 26150
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0001,
      "loss": 0.3293,
      "step": 26200
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0001,
      "loss": 0.3444,
      "step": 26250
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0001,
      "loss": 0.3554,
      "step": 26300
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0001,
      "loss": 0.3538,
      "step": 26350
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.0001,
      "loss": 0.3365,
      "step": 26400
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.0001,
      "loss": 0.3396,
      "step": 26450
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0001,
      "loss": 0.3481,
      "step": 26500
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.0001,
      "loss": 0.3623,
      "step": 26550
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0001,
      "loss": 0.3395,
      "step": 26600
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0001,
      "loss": 0.3763,
      "step": 26650
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0001,
      "loss": 0.3368,
      "step": 26700
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001,
      "loss": 0.3409,
      "step": 26750
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001,
      "loss": 0.3473,
      "step": 26800
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.0001,
      "loss": 0.3595,
      "step": 26850
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0001,
      "loss": 0.3463,
      "step": 26900
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0001,
      "loss": 0.3486,
      "step": 26950
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.0001,
      "loss": 0.3689,
      "step": 27000
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0001,
      "loss": 0.3721,
      "step": 27050
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0001,
      "loss": 0.377,
      "step": 27100
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0001,
      "loss": 0.3337,
      "step": 27150
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0001,
      "loss": 0.3574,
      "step": 27200
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0001,
      "loss": 0.3342,
      "step": 27250
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0001,
      "loss": 0.3368,
      "step": 27300
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.0001,
      "loss": 0.3494,
      "step": 27350
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0001,
      "loss": 0.3333,
      "step": 27400
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.0001,
      "loss": 0.3729,
      "step": 27450
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0001,
      "loss": 0.3522,
      "step": 27500
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.0001,
      "loss": 0.3498,
      "step": 27550
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.0001,
      "loss": 0.3494,
      "step": 27600
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0001,
      "loss": 0.336,
      "step": 27650
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.0001,
      "loss": 0.3659,
      "step": 27700
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0001,
      "loss": 0.3807,
      "step": 27750
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0001,
      "loss": 0.3693,
      "step": 27800
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7859576940536499,
      "eval_runtime": 205.7789,
      "eval_samples_per_second": 15.614,
      "eval_steps_per_second": 0.977,
      "step": 27830
    }
  ],
  "max_steps": 27830,
  "num_train_epochs": 5,
  "total_flos": 14931153948672.0,
  "trial_name": null,
  "trial_params": null
}