{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009643201542912247,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003214400514304082,
      "eval_loss": 2.9586496353149414,
      "eval_runtime": 97.8177,
      "eval_samples_per_second": 13.392,
      "eval_steps_per_second": 6.696,
      "step": 1
    },
    {
      "epoch": 0.0009643201542912247,
      "grad_norm": 3.8007397651672363,
      "learning_rate": 3e-05,
      "loss": 11.2314,
      "step": 3
    },
    {
      "epoch": 0.0019286403085824494,
      "grad_norm": 4.28609561920166,
      "learning_rate": 6e-05,
      "loss": 12.17,
      "step": 6
    },
    {
      "epoch": 0.0025715204114432656,
      "eval_loss": 2.790358543395996,
      "eval_runtime": 97.7559,
      "eval_samples_per_second": 13.401,
      "eval_steps_per_second": 6.7,
      "step": 8
    },
    {
      "epoch": 0.0028929604628736743,
      "grad_norm": 4.557946681976318,
      "learning_rate": 9e-05,
      "loss": 11.5635,
      "step": 9
    },
    {
      "epoch": 0.003857280617164899,
      "grad_norm": 3.8071141242980957,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.8458,
      "step": 12
    },
    {
      "epoch": 0.0048216007714561235,
      "grad_norm": 4.1461181640625,
      "learning_rate": 8.535533905932738e-05,
      "loss": 9.5473,
      "step": 15
    },
    {
      "epoch": 0.005143040822886531,
      "eval_loss": 2.2719030380249023,
      "eval_runtime": 97.8904,
      "eval_samples_per_second": 13.382,
      "eval_steps_per_second": 6.691,
      "step": 16
    },
    {
      "epoch": 0.0057859209257473485,
      "grad_norm": 4.0003509521484375,
      "learning_rate": 6.545084971874738e-05,
      "loss": 9.4062,
      "step": 18
    },
    {
      "epoch": 0.006750241080038573,
      "grad_norm": 3.088686466217041,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 8.6215,
      "step": 21
    },
    {
      "epoch": 0.007714561234329798,
      "grad_norm": 3.382463216781616,
      "learning_rate": 2.061073738537635e-05,
      "loss": 8.265,
      "step": 24
    },
    {
      "epoch": 0.007714561234329798,
      "eval_loss": 2.131692886352539,
      "eval_runtime": 97.8953,
      "eval_samples_per_second": 13.382,
      "eval_steps_per_second": 6.691,
      "step": 24
    },
    {
      "epoch": 0.008678881388621022,
      "grad_norm": 3.0111000537872314,
      "learning_rate": 5.449673790581611e-06,
      "loss": 8.3954,
      "step": 27
    },
    {
      "epoch": 0.009643201542912247,
      "grad_norm": 2.815706253051758,
      "learning_rate": 0.0,
      "loss": 8.3801,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0183366485504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}