{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01255739120197779,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006278695600988894,
      "grad_norm": 1.6499921083450317,
      "learning_rate": 1e-05,
      "loss": 27.2109,
      "step": 1
    },
    {
      "epoch": 0.0006278695600988894,
      "eval_loss": 1.5100669860839844,
      "eval_runtime": 233.4391,
      "eval_samples_per_second": 11.493,
      "eval_steps_per_second": 5.749,
      "step": 1
    },
    {
      "epoch": 0.0012557391201977789,
      "grad_norm": 1.3669140338897705,
      "learning_rate": 2e-05,
      "loss": 22.2695,
      "step": 2
    },
    {
      "epoch": 0.0018836086802966683,
      "grad_norm": 1.511452078819275,
      "learning_rate": 3e-05,
      "loss": 24.6953,
      "step": 3
    },
    {
      "epoch": 0.0025114782403955578,
      "grad_norm": 1.1043322086334229,
      "learning_rate": 4e-05,
      "loss": 23.2188,
      "step": 4
    },
    {
      "epoch": 0.0031393478004944474,
      "grad_norm": 1.18587327003479,
      "learning_rate": 5e-05,
      "loss": 22.7891,
      "step": 5
    },
    {
      "epoch": 0.0031393478004944474,
      "eval_loss": 1.508397102355957,
      "eval_runtime": 85.0417,
      "eval_samples_per_second": 31.549,
      "eval_steps_per_second": 15.781,
      "step": 5
    },
    {
      "epoch": 0.0037672173605933367,
      "grad_norm": 2.3235645294189453,
      "learning_rate": 6e-05,
      "loss": 25.4453,
      "step": 6
    },
    {
      "epoch": 0.004395086920692226,
      "grad_norm": 1.4490516185760498,
      "learning_rate": 7e-05,
      "loss": 22.5156,
      "step": 7
    },
    {
      "epoch": 0.0050229564807911155,
      "grad_norm": 1.4218536615371704,
      "learning_rate": 8e-05,
      "loss": 25.3516,
      "step": 8
    },
    {
      "epoch": 0.005650826040890005,
      "grad_norm": 1.5750902891159058,
      "learning_rate": 9e-05,
      "loss": 23.1602,
      "step": 9
    },
    {
      "epoch": 0.006278695600988895,
      "grad_norm": 1.523149847984314,
      "learning_rate": 0.0001,
      "loss": 25.4883,
      "step": 10
    },
    {
      "epoch": 0.006278695600988895,
      "eval_loss": 1.4983664751052856,
      "eval_runtime": 84.6571,
      "eval_samples_per_second": 31.693,
      "eval_steps_per_second": 15.852,
      "step": 10
    },
    {
      "epoch": 0.006906565161087784,
      "grad_norm": 1.5122368335723877,
      "learning_rate": 9.755282581475769e-05,
      "loss": 23.3281,
      "step": 11
    },
    {
      "epoch": 0.007534434721186673,
      "grad_norm": 1.6233738660812378,
      "learning_rate": 9.045084971874738e-05,
      "loss": 23.0508,
      "step": 12
    },
    {
      "epoch": 0.008162304281285563,
      "grad_norm": 1.552497386932373,
      "learning_rate": 7.938926261462366e-05,
      "loss": 24.582,
      "step": 13
    },
    {
      "epoch": 0.008790173841384452,
      "grad_norm": 2.016003370285034,
      "learning_rate": 6.545084971874738e-05,
      "loss": 22.6602,
      "step": 14
    },
    {
      "epoch": 0.009418043401483342,
      "grad_norm": 1.8063987493515015,
      "learning_rate": 5e-05,
      "loss": 25.3066,
      "step": 15
    },
    {
      "epoch": 0.009418043401483342,
      "eval_loss": 1.4756321907043457,
      "eval_runtime": 83.3991,
      "eval_samples_per_second": 32.171,
      "eval_steps_per_second": 16.091,
      "step": 15
    },
    {
      "epoch": 0.010045912961582231,
      "grad_norm": 1.5516988039016724,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 22.9258,
      "step": 16
    },
    {
      "epoch": 0.01067378252168112,
      "grad_norm": 3.2057738304138184,
      "learning_rate": 2.061073738537635e-05,
      "loss": 23.6406,
      "step": 17
    },
    {
      "epoch": 0.01130165208178001,
      "grad_norm": 3.0766243934631348,
      "learning_rate": 9.549150281252633e-06,
      "loss": 24.7305,
      "step": 18
    },
    {
      "epoch": 0.0119295216418789,
      "grad_norm": 1.9255625009536743,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 21.9883,
      "step": 19
    },
    {
      "epoch": 0.01255739120197779,
      "grad_norm": 1.7242449522018433,
      "learning_rate": 0.0,
      "loss": 21.7461,
      "step": 20
    },
    {
      "epoch": 0.01255739120197779,
      "eval_loss": 1.4681618213653564,
      "eval_runtime": 84.5809,
      "eval_samples_per_second": 31.721,
      "eval_steps_per_second": 15.866,
      "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": 3756522253320192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}