{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00211999152003392,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021199915200339198,
      "grad_norm": 0.3678000867366791,
      "learning_rate": 2e-05,
      "loss": 8.1981,
      "step": 1
    },
    {
      "epoch": 0.00021199915200339198,
      "eval_loss": 2.003500461578369,
      "eval_runtime": 182.355,
      "eval_samples_per_second": 10.896,
      "eval_steps_per_second": 5.451,
      "step": 1
    },
    {
      "epoch": 0.00042399830400678397,
      "grad_norm": 0.4345238208770752,
      "learning_rate": 4e-05,
      "loss": 9.0302,
      "step": 2
    },
    {
      "epoch": 0.0006359974560101759,
      "grad_norm": 0.3662622272968292,
      "learning_rate": 6e-05,
      "loss": 8.0094,
      "step": 3
    },
    {
      "epoch": 0.0006359974560101759,
      "eval_loss": 2.0033600330352783,
      "eval_runtime": 182.5116,
      "eval_samples_per_second": 10.887,
      "eval_steps_per_second": 5.446,
      "step": 3
    },
    {
      "epoch": 0.0008479966080135679,
      "grad_norm": 0.5354431867599487,
      "learning_rate": 8e-05,
      "loss": 7.7939,
      "step": 4
    },
    {
      "epoch": 0.00105999576001696,
      "grad_norm": 0.38323837518692017,
      "learning_rate": 0.0001,
      "loss": 7.8888,
      "step": 5
    },
    {
      "epoch": 0.0012719949120203519,
      "grad_norm": 0.3331907391548157,
      "learning_rate": 0.00012,
      "loss": 7.7627,
      "step": 6
    },
    {
      "epoch": 0.0012719949120203519,
      "eval_loss": 2.0003929138183594,
      "eval_runtime": 182.423,
      "eval_samples_per_second": 10.892,
      "eval_steps_per_second": 5.449,
      "step": 6
    },
    {
      "epoch": 0.001483994064023744,
      "grad_norm": 0.36112990975379944,
      "learning_rate": 0.00014,
      "loss": 7.6414,
      "step": 7
    },
    {
      "epoch": 0.0016959932160271359,
      "grad_norm": 0.5424998998641968,
      "learning_rate": 0.00016,
      "loss": 7.2724,
      "step": 8
    },
    {
      "epoch": 0.0019079923680305278,
      "grad_norm": 0.45831239223480225,
      "learning_rate": 0.00018,
      "loss": 8.5277,
      "step": 9
    },
    {
      "epoch": 0.0019079923680305278,
      "eval_loss": 1.982421636581421,
      "eval_runtime": 181.1433,
      "eval_samples_per_second": 10.969,
      "eval_steps_per_second": 5.487,
      "step": 9
    },
    {
      "epoch": 0.00211999152003392,
      "grad_norm": 0.4713221788406372,
      "learning_rate": 0.0002,
      "loss": 7.6253,
      "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": 597458807685120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}