{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.556420233463035,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1556420233463035,
      "grad_norm": 5.363790512084961,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.5426,
      "step": 10
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 5.297606468200684,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4551,
      "step": 20
    },
    {
      "epoch": 0.4669260700389105,
      "grad_norm": 1.6734049320220947,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.5765,
      "step": 30
    },
    {
      "epoch": 0.622568093385214,
      "grad_norm": 0.5996205806732178,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.9482,
      "step": 40
    },
    {
      "epoch": 0.7782101167315175,
      "grad_norm": 0.5326632857322693,
      "learning_rate": 1.4994303528285384e-05,
      "loss": 0.7767,
      "step": 50
    },
    {
      "epoch": 0.7782101167315175,
      "eval_loss": 0.7420370578765869,
      "eval_runtime": 75.0351,
      "eval_samples_per_second": 3.052,
      "eval_steps_per_second": 1.533,
      "step": 50
    },
    {
      "epoch": 0.933852140077821,
      "grad_norm": 0.47296807169914246,
      "learning_rate": 1.4948783661087592e-05,
      "loss": 0.6917,
      "step": 60
    },
    {
      "epoch": 1.0894941634241244,
      "grad_norm": 0.5496929883956909,
      "learning_rate": 1.485802041113141e-05,
      "loss": 0.5968,
      "step": 70
    },
    {
      "epoch": 1.245136186770428,
      "grad_norm": 0.5656551122665405,
      "learning_rate": 1.4722565067948796e-05,
      "loss": 0.5096,
      "step": 80
    },
    {
      "epoch": 1.4007782101167314,
      "grad_norm": 0.7151289582252502,
      "learning_rate": 1.454324037767081e-05,
      "loss": 0.5053,
      "step": 90
    },
    {
      "epoch": 1.556420233463035,
      "grad_norm": 0.7926196455955505,
      "learning_rate": 1.4321135545726069e-05,
      "loss": 0.4193,
      "step": 100
    },
    {
      "epoch": 1.556420233463035,
      "eval_loss": 0.4160374701023102,
      "eval_runtime": 75.0144,
      "eval_samples_per_second": 3.053,
      "eval_steps_per_second": 1.533,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 448,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.696156762578616e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}