{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.997624703087886,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "global_step": 10,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.5879,
      "step": 10
    },
    {
      "epoch": 0.1,
      "global_step": 20,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.506,
      "step": 20
    },
    {
      "epoch": 0.14,
      "global_step": 30,
      "learning_rate": 0.0001,
      "loss": 0.5252,
      "step": 30
    },
    {
      "epoch": 0.19,
      "global_step": 40,
      "learning_rate": 0.0001,
      "loss": 0.5572,
      "step": 40
    },
    {
      "epoch": 0.24,
      "global_step": 50,
      "learning_rate": 0.0001,
      "loss": 0.4937,
      "step": 50
    },
    {
      "epoch": 0.29,
      "global_step": 60,
      "learning_rate": 0.0001,
      "loss": 0.4925,
      "step": 60
    },
    {
      "epoch": 0.33,
      "global_step": 70,
      "learning_rate": 0.0001,
      "loss": 0.4309,
      "step": 70
    },
    {
      "epoch": 0.38,
      "global_step": 80,
      "learning_rate": 0.0001,
      "loss": 0.4831,
      "step": 80
    },
    {
      "epoch": 0.43,
      "global_step": 90,
      "learning_rate": 0.0001,
      "loss": 0.4896,
      "step": 90
    },
    {
      "epoch": 0.48,
      "global_step": 100,
      "learning_rate": 0.0001,
      "loss": 0.4257,
      "step": 100
    },
    {
      "epoch": 0.52,
      "global_step": 110,
      "learning_rate": 0.0001,
      "loss": 0.5,
      "step": 110
    },
    {
      "epoch": 0.57,
      "global_step": 120,
      "learning_rate": 0.0001,
      "loss": 0.4954,
      "step": 120
    },
    {
      "epoch": 0.62,
      "global_step": 130,
      "learning_rate": 0.0001,
      "loss": 0.4691,
      "step": 130
    },
    {
      "epoch": 0.67,
      "global_step": 140,
      "learning_rate": 0.0001,
      "loss": 0.4373,
      "step": 140
    },
    {
      "epoch": 0.71,
      "global_step": 150,
      "learning_rate": 0.0001,
      "loss": 0.526,
      "step": 150
    },
    {
      "epoch": 0.76,
      "global_step": 160,
      "learning_rate": 0.0001,
      "loss": 0.4297,
      "step": 160
    },
    {
      "epoch": 0.81,
      "global_step": 170,
      "learning_rate": 0.0001,
      "loss": 0.4708,
      "step": 170
    },
    {
      "epoch": 0.86,
      "global_step": 180,
      "learning_rate": 0.0001,
      "loss": 0.4872,
      "step": 180
    },
    {
      "epoch": 0.9,
      "global_step": 190,
      "learning_rate": 0.0001,
      "loss": 0.4888,
      "step": 190
    },
    {
      "epoch": 0.95,
      "global_step": 200,
      "learning_rate": 0.0001,
      "loss": 0.4754,
      "step": 200
    },
    {
      "epoch": 1.0,
      "global_step": 210,
      "learning_rate": 0.0001,
      "loss": 0.4733,
      "step": 210
    },
    {
      "epoch": 1.0,
      "step": 210,
      "total_flos": 1.1368810483705446e+17,
      "train_loss": 0.4878490357171921,
      "train_runtime": 6234.3462,
      "train_samples_per_second": 0.405,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 10,
  "max_steps": 210,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1.1368810483705446e+17,
  "trial_name": null,
  "trial_params": null
}