{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010854816824966078,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001085481682496608,
      "grad_norm": 6.323154449462891,
      "learning_rate": 2e-05,
      "loss": 5.258,
      "step": 1
    },
    {
      "epoch": 0.001085481682496608,
      "eval_loss": NaN,
      "eval_runtime": 7.0378,
      "eval_samples_per_second": 55.131,
      "eval_steps_per_second": 27.565,
      "step": 1
    },
    {
      "epoch": 0.002170963364993216,
      "grad_norm": 5.363320827484131,
      "learning_rate": 4e-05,
      "loss": 5.2337,
      "step": 2
    },
    {
      "epoch": 0.0032564450474898234,
      "grad_norm": 7.305302619934082,
      "learning_rate": 6e-05,
      "loss": 5.9059,
      "step": 3
    },
    {
      "epoch": 0.0032564450474898234,
      "eval_loss": NaN,
      "eval_runtime": 6.0855,
      "eval_samples_per_second": 63.758,
      "eval_steps_per_second": 31.879,
      "step": 3
    },
    {
      "epoch": 0.004341926729986432,
      "grad_norm": 8.807498931884766,
      "learning_rate": 8e-05,
      "loss": 5.8812,
      "step": 4
    },
    {
      "epoch": 0.005427408412483039,
      "grad_norm": 5.269725322723389,
      "learning_rate": 0.0001,
      "loss": 5.4477,
      "step": 5
    },
    {
      "epoch": 0.006512890094979647,
      "grad_norm": 4.527466773986816,
      "learning_rate": 0.00012,
      "loss": 4.1991,
      "step": 6
    },
    {
      "epoch": 0.006512890094979647,
      "eval_loss": NaN,
      "eval_runtime": 6.1931,
      "eval_samples_per_second": 62.65,
      "eval_steps_per_second": 31.325,
      "step": 6
    },
    {
      "epoch": 0.007598371777476255,
      "grad_norm": 6.295800685882568,
      "learning_rate": 0.00014,
      "loss": 4.5805,
      "step": 7
    },
    {
      "epoch": 0.008683853459972864,
      "grad_norm": 5.254021167755127,
      "learning_rate": 0.00016,
      "loss": 4.2825,
      "step": 8
    },
    {
      "epoch": 0.00976933514246947,
      "grad_norm": 4.467378616333008,
      "learning_rate": 0.00018,
      "loss": 3.9673,
      "step": 9
    },
    {
      "epoch": 0.00976933514246947,
      "eval_loss": NaN,
      "eval_runtime": 6.1397,
      "eval_samples_per_second": 63.195,
      "eval_steps_per_second": 31.598,
      "step": 9
    },
    {
      "epoch": 0.010854816824966078,
      "grad_norm": 9.76582145690918,
      "learning_rate": 0.0002,
      "loss": 3.9622,
      "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": 312709170069504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}