{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9998654648190501,
  "eval_steps": 500,
  "global_step": 3716,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.991071065046783e-05,
      "loss": 3.0435,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9643480408906496e-05,
      "loss": 0.0382,
      "step": 200
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.920021814047156e-05,
      "loss": 0.0227,
      "step": 300
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.858409013313266e-05,
      "loss": 0.0258,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7799497480410125e-05,
      "loss": 0.0256,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.685204464371269e-05,
      "loss": 0.0312,
      "step": 600
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.574849941884044e-05,
      "loss": 0.0212,
      "step": 700
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.449674459261804e-05,
      "loss": 0.0271,
      "step": 800
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.310572163498205e-05,
      "loss": 0.0203,
      "step": 900
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.158536682873821e-05,
      "loss": 0.0172,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.994654029322313e-05,
      "loss": 0.0241,
      "step": 1100
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.8200948408864986e-05,
      "loss": 0.0167,
      "step": 1200
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.636106019677602e-05,
      "loss": 0.0134,
      "step": 1300
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.4440018250689767e-05,
      "loss": 0.0145,
      "step": 1400
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.2451544857469436e-05,
      "loss": 0.0127,
      "step": 1500
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.040984397678245e-05,
      "loss": 0.0164,
      "step": 1600
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8329499780114865e-05,
      "loss": 0.0187,
      "step": 1700
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6225372473876565e-05,
      "loss": 0.0147,
      "step": 1800
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.41124921507481e-05,
      "loss": 0.0156,
      "step": 1900
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.2005951427504784e-05,
      "loss": 0.0184,
      "step": 2000
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.9920797636221933e-05,
      "loss": 0.0119,
      "step": 2100
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7871925338955412e-05,
      "loss": 0.0144,
      "step": 2200
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.5873969933681e-05,
      "loss": 0.0124,
      "step": 2300
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3941203111481194e-05,
      "loss": 0.0129,
      "step": 2400
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.2087430911744144e-05,
      "loss": 0.0067,
      "step": 2500
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.0325895103581462e-05,
      "loss": 0.0161,
      "step": 2600
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.669178597912217e-06,
      "loss": 0.0124,
      "step": 2700
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.129115565868463e-06,
      "loss": 0.0161,
      "step": 2800
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.716706905559768e-06,
      "loss": 0.0145,
      "step": 2900
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.4420416610303325e-06,
      "loss": 0.0088,
      "step": 3000
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.314224954724593e-06,
      "loss": 0.0124,
      "step": 3100
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.341312948250349e-06,
      "loss": 0.0154,
      "step": 3200
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.5302552960244022e-06,
      "loss": 0.0161,
      "step": 3300
    },
    {
      "epoch": 0.91,
      "learning_rate": 8.868455028627959e-07,
      "loss": 0.0118,
      "step": 3400
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.156795401186381e-07,
      "loss": 0.0067,
      "step": 3500
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.2012301597874863e-07,
      "loss": 0.0096,
      "step": 3600
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.2871344263597496e-09,
      "loss": 0.0113,
      "step": 3700
    },
    {
      "epoch": 1.0,
      "step": 3716,
      "total_flos": 3.0689685240938496e+17,
      "train_loss": 0.09819089700903973,
      "train_runtime": 7694.3429,
      "train_samples_per_second": 15.456,
      "train_steps_per_second": 0.483
    }
  ],
  "logging_steps": 100,
  "max_steps": 3716,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 3.0689685240938496e+17,
  "trial_name": null,
  "trial_params": null
}