{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01511144692104269,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007555723460521345,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.4814,
      "step": 1
    },
    {
      "epoch": 0.0007555723460521345,
      "eval_loss": NaN,
      "eval_runtime": 332.2255,
      "eval_samples_per_second": 6.712,
      "eval_steps_per_second": 3.356,
      "step": 1
    },
    {
      "epoch": 0.001511144692104269,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 355.716,
      "step": 2
    },
    {
      "epoch": 0.0022667170381564035,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.003022289384208538,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0037778617302606727,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 888.046,
      "step": 5
    },
    {
      "epoch": 0.0037778617302606727,
      "eval_loss": NaN,
      "eval_runtime": 249.8579,
      "eval_samples_per_second": 8.925,
      "eval_steps_per_second": 4.463,
      "step": 5
    },
    {
      "epoch": 0.004533434076312807,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.005289006422364941,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 152.26,
      "step": 7
    },
    {
      "epoch": 0.006044578768417076,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 2.0486,
      "step": 8
    },
    {
      "epoch": 0.00680015111446921,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0262,
      "step": 9
    },
    {
      "epoch": 0.007555723460521345,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.285,
      "step": 10
    },
    {
      "epoch": 0.007555723460521345,
      "eval_loss": NaN,
      "eval_runtime": 193.3818,
      "eval_samples_per_second": 11.532,
      "eval_steps_per_second": 5.766,
      "step": 10
    },
    {
      "epoch": 0.00831129580657348,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 85.5864,
      "step": 11
    },
    {
      "epoch": 0.009066868152625614,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.009822440498677748,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0735,
      "step": 13
    },
    {
      "epoch": 0.010578012844729883,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 6.7404,
      "step": 14
    },
    {
      "epoch": 0.011333585190782017,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 171.2843,
      "step": 15
    },
    {
      "epoch": 0.011333585190782017,
      "eval_loss": NaN,
      "eval_runtime": 173.033,
      "eval_samples_per_second": 12.888,
      "eval_steps_per_second": 6.444,
      "step": 15
    },
    {
      "epoch": 0.012089157536834151,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.012844729882886286,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 460.4789,
      "step": 17
    },
    {
      "epoch": 0.01360030222893842,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 8.2432,
      "step": 18
    },
    {
      "epoch": 0.014355874574990555,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 580.8181,
      "step": 19
    },
    {
      "epoch": 0.01511144692104269,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 988.7248,
      "step": 20
    },
    {
      "epoch": 0.01511144692104269,
      "eval_loss": NaN,
      "eval_runtime": 172.6591,
      "eval_samples_per_second": 12.916,
      "eval_steps_per_second": 6.458,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4309082437451776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}