{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 12138,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 1.9154,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 1.43,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 0.9686,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 2e-05,
      "loss": 0.9181,
      "step": 400
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 0.9455,
      "step": 500
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.949,
      "step": 600
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.8024,
      "step": 700
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.6846,
      "step": 800
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.5948,
      "step": 900
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.5975,
      "step": 1000
    },
    {
      "epoch": 0.18,
      "learning_rate": 2e-05,
      "loss": 0.7143,
      "step": 1100
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.7405,
      "step": 1200
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 0.6561,
      "step": 1300
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 0.6427,
      "step": 1400
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 0.5293,
      "step": 1500
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.6634,
      "step": 1600
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 0.5758,
      "step": 1700
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.6344,
      "step": 1800
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 0.6298,
      "step": 1900
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.5303,
      "step": 2000
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.5188,
      "step": 2100
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 0.6227,
      "step": 2200
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 0.6051,
      "step": 2300
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.6769,
      "step": 2400
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.5749,
      "step": 2500
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.4436,
      "step": 2600
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.6846,
      "step": 2700
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.556,
      "step": 2800
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.5762,
      "step": 2900
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.5248,
      "step": 3000
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.5558,
      "step": 3100
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 0.5116,
      "step": 3200
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.5295,
      "step": 3300
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.5301,
      "step": 3400
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.5294,
      "step": 3500
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.515,
      "step": 3600
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.5794,
      "step": 3700
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.4725,
      "step": 3800
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.5957,
      "step": 3900
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.5277,
      "step": 4000
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.5457,
      "step": 4100
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.4994,
      "step": 4200
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.5515,
      "step": 4300
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.5008,
      "step": 4400
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.593,
      "step": 4500
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.585,
      "step": 4600
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.5274,
      "step": 4700
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.4437,
      "step": 4800
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.5143,
      "step": 4900
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.537,
      "step": 5000
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.4277,
      "step": 5100
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.4822,
      "step": 5200
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.5356,
      "step": 5300
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.5248,
      "step": 5400
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 0.5202,
      "step": 5500
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 0.599,
      "step": 5600
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.4688,
      "step": 5700
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.5126,
      "step": 5800
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 0.5361,
      "step": 5900
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 0.3963,
      "step": 6000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.314893901348114,
      "eval_macro_f1": 0.861683908045977,
      "eval_runtime": 1926.7043,
      "eval_samples_per_second": 1.828,
      "eval_steps_per_second": 1.828,
      "eval_w_f1": 0.9317006533644023,
      "step": 6069
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 0.3971,
      "step": 6100
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 0.5884,
      "step": 6200
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.4905,
      "step": 6300
    },
    {
      "epoch": 1.05,
      "learning_rate": 2e-05,
      "loss": 0.5088,
      "step": 6400
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.5391,
      "step": 6500
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 0.385,
      "step": 6600
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.5233,
      "step": 6700
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 0.3826,
      "step": 6800
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 0.401,
      "step": 6900
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 0.4315,
      "step": 7000
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 0.5173,
      "step": 7100
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.5372,
      "step": 7200
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.3717,
      "step": 7300
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.4668,
      "step": 7400
    },
    {
      "epoch": 1.24,
      "learning_rate": 2e-05,
      "loss": 0.431,
      "step": 7500
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.4545,
      "step": 7600
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 0.3506,
      "step": 7700
    },
    {
      "epoch": 1.29,
      "learning_rate": 2e-05,
      "loss": 0.5173,
      "step": 7800
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.3631,
      "step": 7900
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.4804,
      "step": 8000
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.4384,
      "step": 8100
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.5182,
      "step": 8200
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 0.4416,
      "step": 8300
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 0.4043,
      "step": 8400
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 0.4462,
      "step": 8500
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.5009,
      "step": 8600
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 0.5086,
      "step": 8700
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.4446,
      "step": 8800
    },
    {
      "epoch": 1.47,
      "learning_rate": 2e-05,
      "loss": 0.4701,
      "step": 8900
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.449,
      "step": 9000
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.4368,
      "step": 9100
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.5384,
      "step": 9200
    },
    {
      "epoch": 1.53,
      "learning_rate": 2e-05,
      "loss": 0.4209,
      "step": 9300
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 0.4485,
      "step": 9400
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.4414,
      "step": 9500
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.418,
      "step": 9600
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.2729,
      "step": 9700
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.4574,
      "step": 9800
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.4475,
      "step": 9900
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.5195,
      "step": 10000
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.4451,
      "step": 10100
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 0.3544,
      "step": 10200
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.5105,
      "step": 10300
    },
    {
      "epoch": 1.71,
      "learning_rate": 2e-05,
      "loss": 0.3476,
      "step": 10400
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-05,
      "loss": 0.5183,
      "step": 10500
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 0.4595,
      "step": 10600
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.488,
      "step": 10700
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.353,
      "step": 10800
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 0.4504,
      "step": 10900
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.4664,
      "step": 11000
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.4726,
      "step": 11100
    },
    {
      "epoch": 1.85,
      "learning_rate": 2e-05,
      "loss": 0.4457,
      "step": 11200
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 0.5226,
      "step": 11300
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 0.5333,
      "step": 11400
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 0.4751,
      "step": 11500
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.4763,
      "step": 11600
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 0.4873,
      "step": 11700
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.4186,
      "step": 11800
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 0.4183,
      "step": 11900
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.5434,
      "step": 12000
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 0.5285,
      "step": 12100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.1769913136959076,
      "eval_macro_f1": 0.9112129368062815,
      "eval_runtime": 1924.1679,
      "eval_samples_per_second": 1.83,
      "eval_steps_per_second": 1.83,
      "eval_w_f1": 0.9568650424835885,
      "step": 12138
    }
  ],
  "logging_steps": 100,
  "max_steps": 30345,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 7.842335249417011e+17,
  "trial_name": null,
  "trial_params": null
}