{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001365607183093783,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001365607183093783,
      "grad_norm": 7.427431228279602e-06,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0001365607183093783,
      "eval_loss": 11.5,
      "eval_runtime": 20.1964,
      "eval_samples_per_second": 152.701,
      "eval_steps_per_second": 76.35,
      "step": 1
    },
    {
      "epoch": 0.0002731214366187566,
      "grad_norm": 1.0944732821371872e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0004096821549281349,
      "grad_norm": 1.7248999938601628e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0004096821549281349,
      "eval_loss": 11.5,
      "eval_runtime": 20.2614,
      "eval_samples_per_second": 152.21,
      "eval_steps_per_second": 76.105,
      "step": 3
    },
    {
      "epoch": 0.0005462428732375132,
      "grad_norm": 1.1958129107370041e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0006828035915468915,
      "grad_norm": 1.750692717905622e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0008193643098562698,
      "grad_norm": 1.0798053153848741e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0008193643098562698,
      "eval_loss": 11.5,
      "eval_runtime": 20.6863,
      "eval_samples_per_second": 149.084,
      "eval_steps_per_second": 74.542,
      "step": 6
    },
    {
      "epoch": 0.0009559250281656481,
      "grad_norm": 2.4527542336727493e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0010924857464750264,
      "grad_norm": 8.6453201220138e-06,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0012290464647844047,
      "grad_norm": 5.170768872631015e-06,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0012290464647844047,
      "eval_loss": 11.5,
      "eval_runtime": 20.5844,
      "eval_samples_per_second": 149.822,
      "eval_steps_per_second": 74.911,
      "step": 9
    },
    {
      "epoch": 0.001365607183093783,
      "grad_norm": 1.0133277100976557e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 393476849664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}