{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.975609756097562,
  "eval_steps": 100,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.0471,
      "step": 100
    },
    {
      "epoch": 0.61,
      "eval_runtime": 37.2354,
      "eval_samples_per_second": 1.853,
      "eval_steps_per_second": 0.242,
      "step": 100
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.1366,
      "step": 200
    },
    {
      "epoch": 1.22,
      "eval_runtime": 37.1405,
      "eval_samples_per_second": 1.858,
      "eval_steps_per_second": 0.242,
      "step": 200
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 0.1129,
      "step": 300
    },
    {
      "epoch": 1.83,
      "eval_runtime": 37.2493,
      "eval_samples_per_second": 1.852,
      "eval_steps_per_second": 0.242,
      "step": 300
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.0864,
      "step": 400
    },
    {
      "epoch": 2.44,
      "eval_runtime": 37.2723,
      "eval_samples_per_second": 1.851,
      "eval_steps_per_second": 0.241,
      "step": 400
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0002,
      "loss": 0.0735,
      "step": 500
    },
    {
      "epoch": 3.05,
      "eval_runtime": 37.2901,
      "eval_samples_per_second": 1.85,
      "eval_steps_per_second": 0.241,
      "step": 500
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0002,
      "loss": 0.0514,
      "step": 600
    },
    {
      "epoch": 3.66,
      "eval_runtime": 37.1296,
      "eval_samples_per_second": 1.858,
      "eval_steps_per_second": 0.242,
      "step": 600
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0002,
      "loss": 0.0453,
      "step": 700
    },
    {
      "epoch": 4.27,
      "eval_runtime": 37.1901,
      "eval_samples_per_second": 1.855,
      "eval_steps_per_second": 0.242,
      "step": 700
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0002,
      "loss": 0.0385,
      "step": 800
    },
    {
      "epoch": 4.88,
      "eval_runtime": 37.1702,
      "eval_samples_per_second": 1.856,
      "eval_steps_per_second": 0.242,
      "step": 800
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0002,
      "loss": 0.0315,
      "step": 900
    },
    {
      "epoch": 5.49,
      "eval_runtime": 37.193,
      "eval_samples_per_second": 1.855,
      "eval_steps_per_second": 0.242,
      "step": 900
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.0002,
      "loss": 0.0299,
      "step": 1000
    },
    {
      "epoch": 6.1,
      "eval_runtime": 37.2,
      "eval_samples_per_second": 1.855,
      "eval_steps_per_second": 0.242,
      "step": 1000
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.0002,
      "loss": 0.0254,
      "step": 1100
    },
    {
      "epoch": 6.71,
      "eval_runtime": 37.2367,
      "eval_samples_per_second": 1.853,
      "eval_steps_per_second": 0.242,
      "step": 1100
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.0002,
      "loss": 0.0245,
      "step": 1200
    },
    {
      "epoch": 7.32,
      "eval_runtime": 37.181,
      "eval_samples_per_second": 1.856,
      "eval_steps_per_second": 0.242,
      "step": 1200
    },
    {
      "epoch": 7.93,
      "learning_rate": 0.0002,
      "loss": 0.0237,
      "step": 1300
    },
    {
      "epoch": 7.93,
      "eval_runtime": 37.2913,
      "eval_samples_per_second": 1.85,
      "eval_steps_per_second": 0.241,
      "step": 1300
    },
    {
      "epoch": 8.54,
      "learning_rate": 0.0002,
      "loss": 0.0213,
      "step": 1400
    },
    {
      "epoch": 8.54,
      "eval_runtime": 36.2175,
      "eval_samples_per_second": 1.905,
      "eval_steps_per_second": 0.248,
      "step": 1400
    },
    {
      "epoch": 9.15,
      "learning_rate": 0.0002,
      "loss": 0.0218,
      "step": 1500
    },
    {
      "epoch": 9.15,
      "eval_runtime": 37.2434,
      "eval_samples_per_second": 1.853,
      "eval_steps_per_second": 0.242,
      "step": 1500
    },
    {
      "epoch": 9.76,
      "learning_rate": 0.0002,
      "loss": 0.0206,
      "step": 1600
    },
    {
      "epoch": 9.76,
      "eval_runtime": 36.6837,
      "eval_samples_per_second": 1.881,
      "eval_steps_per_second": 0.245,
      "step": 1600
    },
    {
      "epoch": 10.37,
      "learning_rate": 0.0002,
      "loss": 0.0195,
      "step": 1700
    },
    {
      "epoch": 10.37,
      "eval_runtime": 37.1791,
      "eval_samples_per_second": 1.856,
      "eval_steps_per_second": 0.242,
      "step": 1700
    },
    {
      "epoch": 10.98,
      "learning_rate": 0.0002,
      "loss": 0.0201,
      "step": 1800
    },
    {
      "epoch": 10.98,
      "eval_runtime": 36.3321,
      "eval_samples_per_second": 1.899,
      "eval_steps_per_second": 0.248,
      "step": 1800
    }
  ],
  "logging_steps": 100,
  "max_steps": 1804,
  "num_train_epochs": 11,
  "save_steps": 100,
  "total_flos": 1.5050311081132032e+17,
  "trial_name": null,
  "trial_params": null
}