{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 9295,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.8041,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.1898,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.1768,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.1508,
      "step": 200
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.1386,
      "step": 250
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.1382,
      "step": 300
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.138,
      "step": 350
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.102,
      "step": 400
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.1048,
      "step": 450
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.1056,
      "step": 500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.1124,
      "step": 550
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.1568,
      "step": 600
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.1067,
      "step": 650
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.0975,
      "step": 700
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.0954,
      "step": 750
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.091,
      "step": 800
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.0766,
      "step": 850
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.0811,
      "step": 900
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.1071,
      "step": 950
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.1041,
      "step": 1000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.0875,
      "step": 1050
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.0904,
      "step": 1100
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.0761,
      "step": 1150
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.0765,
      "step": 1200
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.0603,
      "step": 1250
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.0679,
      "step": 1300
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.0685,
      "step": 1350
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.0546,
      "step": 1400
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.0753,
      "step": 1450
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.051,
      "step": 1500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.0811,
      "step": 1550
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.073,
      "step": 1600
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.066,
      "step": 1650
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.058,
      "step": 1700
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.0501,
      "step": 1750
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.0828,
      "step": 1800
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.0514,
      "step": 1850
    },
    {
      "epoch": 1.0,
      "eval_f1": 25.2962,
      "eval_gen_len": 31.19437742578412,
      "eval_loss": 0.04159419238567352,
      "eval_runtime": 39.3318,
      "eval_samples_per_second": 242.374,
      "eval_steps_per_second": 7.577,
      "step": 1859
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0003,
      "loss": 0.0484,
      "step": 1900
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0003,
      "loss": 0.0293,
      "step": 1950
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0003,
      "loss": 0.0356,
      "step": 2000
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003,
      "loss": 0.0421,
      "step": 2050
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003,
      "loss": 0.0364,
      "step": 2100
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003,
      "loss": 0.0324,
      "step": 2150
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003,
      "loss": 0.0366,
      "step": 2200
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003,
      "loss": 0.0259,
      "step": 2250
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003,
      "loss": 0.0296,
      "step": 2300
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003,
      "loss": 0.0309,
      "step": 2350
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003,
      "loss": 0.0155,
      "step": 2400
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003,
      "loss": 0.0427,
      "step": 2450
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003,
      "loss": 0.0301,
      "step": 2500
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003,
      "loss": 0.0299,
      "step": 2550
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003,
      "loss": 0.0322,
      "step": 2600
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003,
      "loss": 0.0294,
      "step": 2650
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0003,
      "loss": 0.05,
      "step": 2700
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003,
      "loss": 0.0315,
      "step": 2750
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0003,
      "loss": 0.034,
      "step": 2800
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0003,
      "loss": 0.0229,
      "step": 2850
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0003,
      "loss": 0.0239,
      "step": 2900
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0003,
      "loss": 0.0195,
      "step": 2950
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0003,
      "loss": 0.0388,
      "step": 3000
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0003,
      "loss": 0.031,
      "step": 3050
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0003,
      "loss": 0.0188,
      "step": 3100
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0003,
      "loss": 0.0211,
      "step": 3150
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0003,
      "loss": 0.0177,
      "step": 3200
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0003,
      "loss": 0.0267,
      "step": 3250
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0003,
      "loss": 0.0426,
      "step": 3300
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0003,
      "loss": 0.0216,
      "step": 3350
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0003,
      "loss": 0.0239,
      "step": 3400
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0003,
      "loss": 0.0313,
      "step": 3450
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0003,
      "loss": 0.0306,
      "step": 3500
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0003,
      "loss": 0.0374,
      "step": 3550
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0003,
      "loss": 0.0262,
      "step": 3600
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0003,
      "loss": 0.0372,
      "step": 3650
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0003,
      "loss": 0.0239,
      "step": 3700
    },
    {
      "epoch": 2.0,
      "eval_f1": 25.2962,
      "eval_gen_len": 31.19437742578412,
      "eval_loss": 0.04727494344115257,
      "eval_runtime": 39.1502,
      "eval_samples_per_second": 243.498,
      "eval_steps_per_second": 7.612,
      "step": 3718
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0003,
      "loss": 0.0235,
      "step": 3750
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0003,
      "loss": 0.0167,
      "step": 3800
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0003,
      "loss": 0.0211,
      "step": 3850
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0003,
      "loss": 0.0197,
      "step": 3900
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0003,
      "loss": 0.0312,
      "step": 3950
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0003,
      "loss": 0.0154,
      "step": 4000
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0003,
      "loss": 0.0106,
      "step": 4050
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0003,
      "loss": 0.0252,
      "step": 4100
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0003,
      "loss": 0.0098,
      "step": 4150
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0003,
      "loss": 0.0145,
      "step": 4200
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0003,
      "loss": 0.0093,
      "step": 4250
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0003,
      "loss": 0.0086,
      "step": 4300
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0003,
      "loss": 0.0114,
      "step": 4350
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0003,
      "loss": 0.0128,
      "step": 4400
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0003,
      "loss": 0.0198,
      "step": 4450
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0003,
      "loss": 0.0204,
      "step": 4500
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0003,
      "loss": 0.0083,
      "step": 4550
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0003,
      "loss": 0.01,
      "step": 4600
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0003,
      "loss": 0.0182,
      "step": 4650
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0003,
      "loss": 0.0212,
      "step": 4700
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0003,
      "loss": 0.0203,
      "step": 4750
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0003,
      "loss": 0.0124,
      "step": 4800
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0003,
      "loss": 0.0123,
      "step": 4850
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0003,
      "loss": 0.0079,
      "step": 4900
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0003,
      "loss": 0.0135,
      "step": 4950
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0003,
      "loss": 0.0119,
      "step": 5000
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0003,
      "loss": 0.007,
      "step": 5050
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0003,
      "loss": 0.0117,
      "step": 5100
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0003,
      "loss": 0.0084,
      "step": 5150
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0003,
      "loss": 0.0126,
      "step": 5200
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0003,
      "loss": 0.031,
      "step": 5250
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0003,
      "loss": 0.0114,
      "step": 5300
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0003,
      "loss": 0.0115,
      "step": 5350
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0003,
      "loss": 0.0106,
      "step": 5400
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0003,
      "loss": 0.0154,
      "step": 5450
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0003,
      "loss": 0.0238,
      "step": 5500
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0003,
      "loss": 0.0086,
      "step": 5550
    },
    {
      "epoch": 3.0,
      "eval_f1": 25.2962,
      "eval_gen_len": 31.19437742578412,
      "eval_loss": 0.046078164130449295,
      "eval_runtime": 39.2413,
      "eval_samples_per_second": 242.933,
      "eval_steps_per_second": 7.594,
      "step": 5577
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0003,
      "loss": 0.0062,
      "step": 5600
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0003,
      "loss": 0.0075,
      "step": 5650
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0003,
      "loss": 0.0071,
      "step": 5700
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0003,
      "loss": 0.0089,
      "step": 5750
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0003,
      "loss": 0.0055,
      "step": 5800
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0003,
      "loss": 0.0071,
      "step": 5850
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0003,
      "loss": 0.0029,
      "step": 5900
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0003,
      "loss": 0.0032,
      "step": 5950
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0003,
      "loss": 0.006,
      "step": 6000
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0003,
      "loss": 0.0052,
      "step": 6050
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0003,
      "loss": 0.013,
      "step": 6100
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0003,
      "loss": 0.0052,
      "step": 6150
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0003,
      "loss": 0.0091,
      "step": 6200
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0003,
      "loss": 0.0032,
      "step": 6250
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.0003,
      "loss": 0.0059,
      "step": 6300
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0003,
      "loss": 0.0129,
      "step": 6350
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0003,
      "loss": 0.0044,
      "step": 6400
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0003,
      "loss": 0.0098,
      "step": 6450
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0003,
      "loss": 0.0133,
      "step": 6500
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0003,
      "loss": 0.0139,
      "step": 6550
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0003,
      "loss": 0.009,
      "step": 6600
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0003,
      "loss": 0.01,
      "step": 6650
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0003,
      "loss": 0.0054,
      "step": 6700
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0003,
      "loss": 0.0058,
      "step": 6750
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0003,
      "loss": 0.0064,
      "step": 6800
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0003,
      "loss": 0.0071,
      "step": 6850
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0003,
      "loss": 0.0109,
      "step": 6900
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0003,
      "loss": 0.0183,
      "step": 6950
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0003,
      "loss": 0.0029,
      "step": 7000
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0003,
      "loss": 0.0048,
      "step": 7050
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0003,
      "loss": 0.0059,
      "step": 7100
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0003,
      "loss": 0.0137,
      "step": 7150
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0003,
      "loss": 0.0072,
      "step": 7200
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0003,
      "loss": 0.0044,
      "step": 7250
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0003,
      "loss": 0.0057,
      "step": 7300
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0003,
      "loss": 0.0072,
      "step": 7350
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0003,
      "loss": 0.0032,
      "step": 7400
    },
    {
      "epoch": 4.0,
      "eval_f1": 25.2962,
      "eval_gen_len": 31.19437742578412,
      "eval_loss": 0.050509095191955566,
      "eval_runtime": 39.1959,
      "eval_samples_per_second": 243.214,
      "eval_steps_per_second": 7.603,
      "step": 7436
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0003,
      "loss": 0.0062,
      "step": 7450
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0003,
      "loss": 0.0035,
      "step": 7500
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0003,
      "loss": 0.0072,
      "step": 7550
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0003,
      "loss": 0.0105,
      "step": 7600
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 7650
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0003,
      "loss": 0.0035,
      "step": 7700
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0003,
      "loss": 0.003,
      "step": 7750
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0003,
      "loss": 0.0026,
      "step": 7800
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0003,
      "loss": 0.0086,
      "step": 7850
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0003,
      "loss": 0.009,
      "step": 7900
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.0003,
      "loss": 0.0042,
      "step": 7950
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0003,
      "loss": 0.0089,
      "step": 8000
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0003,
      "loss": 0.0026,
      "step": 8050
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0003,
      "loss": 0.0075,
      "step": 8100
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.0003,
      "loss": 0.0051,
      "step": 8150
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0003,
      "loss": 0.0031,
      "step": 8200
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0003,
      "loss": 0.0039,
      "step": 8250
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0003,
      "loss": 0.0076,
      "step": 8300
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0003,
      "loss": 0.0037,
      "step": 8350
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0003,
      "loss": 0.0061,
      "step": 8400
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0003,
      "loss": 0.0071,
      "step": 8450
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0003,
      "loss": 0.0023,
      "step": 8500
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0003,
      "loss": 0.0159,
      "step": 8550
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0003,
      "loss": 0.003,
      "step": 8600
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0003,
      "loss": 0.0034,
      "step": 8650
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0003,
      "loss": 0.0061,
      "step": 8700
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0003,
      "loss": 0.0055,
      "step": 8750
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 8800
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 8850
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0003,
      "loss": 0.0015,
      "step": 8900
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0003,
      "loss": 0.0133,
      "step": 8950
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0003,
      "loss": 0.0049,
      "step": 9000
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0003,
      "loss": 0.0031,
      "step": 9050
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0003,
      "loss": 0.0029,
      "step": 9100
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0003,
      "loss": 0.0012,
      "step": 9150
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.0003,
      "loss": 0.0031,
      "step": 9200
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 9250
    },
    {
      "epoch": 5.0,
      "eval_f1": 25.2962,
      "eval_gen_len": 31.19437742578412,
      "eval_loss": 0.06311735510826111,
      "eval_runtime": 39.2339,
      "eval_samples_per_second": 242.979,
      "eval_steps_per_second": 7.595,
      "step": 9295
    }
  ],
  "logging_steps": 50,
  "max_steps": 9295,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 250,
  "total_flos": 9.1382350098432e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}