{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002924831822170225,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.9248318221702253e-05,
      "grad_norm": 0.12183666229248047,
      "learning_rate": 2e-05,
      "loss": 10.378,
      "step": 1
    },
    {
      "epoch": 2.9248318221702253e-05,
      "eval_loss": 10.375866889953613,
      "eval_runtime": 37.2361,
      "eval_samples_per_second": 386.614,
      "eval_steps_per_second": 193.307,
      "step": 1
    },
    {
      "epoch": 5.8496636443404506e-05,
      "grad_norm": 0.15408086776733398,
      "learning_rate": 4e-05,
      "loss": 10.3599,
      "step": 2
    },
    {
      "epoch": 8.774495466510675e-05,
      "grad_norm": 0.07234669476747513,
      "learning_rate": 6e-05,
      "loss": 10.3726,
      "step": 3
    },
    {
      "epoch": 8.774495466510675e-05,
      "eval_loss": 10.375816345214844,
      "eval_runtime": 36.6402,
      "eval_samples_per_second": 392.902,
      "eval_steps_per_second": 196.451,
      "step": 3
    },
    {
      "epoch": 0.00011699327288680901,
      "grad_norm": 0.0598064549267292,
      "learning_rate": 8e-05,
      "loss": 10.3709,
      "step": 4
    },
    {
      "epoch": 0.00014624159110851126,
      "grad_norm": 0.038922108709812164,
      "learning_rate": 0.0001,
      "loss": 10.3798,
      "step": 5
    },
    {
      "epoch": 0.0001754899093302135,
      "grad_norm": 0.18488682806491852,
      "learning_rate": 0.00012,
      "loss": 10.3835,
      "step": 6
    },
    {
      "epoch": 0.0001754899093302135,
      "eval_loss": 10.375616073608398,
      "eval_runtime": 37.1039,
      "eval_samples_per_second": 387.992,
      "eval_steps_per_second": 193.996,
      "step": 6
    },
    {
      "epoch": 0.00020473822755191578,
      "grad_norm": 0.11034737527370453,
      "learning_rate": 0.00014,
      "loss": 10.3855,
      "step": 7
    },
    {
      "epoch": 0.00023398654577361802,
      "grad_norm": 0.12399976700544357,
      "learning_rate": 0.00016,
      "loss": 10.3921,
      "step": 8
    },
    {
      "epoch": 0.00026323486399532027,
      "grad_norm": 0.0644148513674736,
      "learning_rate": 0.00018,
      "loss": 10.3695,
      "step": 9
    },
    {
      "epoch": 0.00026323486399532027,
      "eval_loss": 10.375258445739746,
      "eval_runtime": 37.1911,
      "eval_samples_per_second": 387.082,
      "eval_steps_per_second": 193.541,
      "step": 9
    },
    {
      "epoch": 0.0002924831822170225,
      "grad_norm": 0.1216086596250534,
      "learning_rate": 0.0002,
      "loss": 10.3682,
      "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": 129309081600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}