{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021278859453133313,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010639429726566656,
      "eval_loss": NaN,
      "eval_runtime": 60.3888,
      "eval_samples_per_second": 32.771,
      "eval_steps_per_second": 16.394,
      "step": 1
    },
    {
      "epoch": 0.0010639429726566655,
      "grad_norm": NaN,
      "learning_rate": 0.00019967573081342103,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.002127885945313331,
      "grad_norm": NaN,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0031918289179699967,
      "grad_norm": NaN,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.004255771890626662,
      "grad_norm": NaN,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.005319714863283328,
      "grad_norm": NaN,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.005319714863283328,
      "eval_loss": NaN,
      "eval_runtime": 58.7596,
      "eval_samples_per_second": 33.68,
      "eval_steps_per_second": 16.848,
      "step": 50
    },
    {
      "epoch": 0.0063836578359399935,
      "grad_norm": NaN,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.00744760080859666,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.008511543781253324,
      "grad_norm": NaN,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.009575486753909991,
      "grad_norm": NaN,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.010639429726566656,
      "grad_norm": NaN,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.010639429726566656,
      "eval_loss": NaN,
      "eval_runtime": 59.2065,
      "eval_samples_per_second": 33.425,
      "eval_steps_per_second": 16.721,
      "step": 100
    },
    {
      "epoch": 0.011703372699223322,
      "grad_norm": NaN,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.012767315671879987,
      "grad_norm": NaN,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.013831258644536652,
      "grad_norm": NaN,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.01489520161719332,
      "grad_norm": NaN,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.015959144589849983,
      "grad_norm": NaN,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.015959144589849983,
      "eval_loss": NaN,
      "eval_runtime": 59.0531,
      "eval_samples_per_second": 33.512,
      "eval_steps_per_second": 16.765,
      "step": 150
    },
    {
      "epoch": 0.017023087562506648,
      "grad_norm": NaN,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.018087030535163317,
      "grad_norm": NaN,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.019150973507819982,
      "grad_norm": NaN,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.020214916480476647,
      "grad_norm": NaN,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.021278859453133313,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.021278859453133313,
      "eval_loss": NaN,
      "eval_runtime": 59.0967,
      "eval_samples_per_second": 33.487,
      "eval_steps_per_second": 16.752,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6475799272030208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}