{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007521200383581219,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.52120038358122e-05,
      "grad_norm": 0.38321930170059204,
      "learning_rate": 2e-05,
      "loss": 44.3463,
      "step": 1
    },
    {
      "epoch": 7.52120038358122e-05,
      "eval_loss": 11.091534614562988,
      "eval_runtime": 13.9971,
      "eval_samples_per_second": 400.012,
      "eval_steps_per_second": 200.042,
      "step": 1
    },
    {
      "epoch": 0.0001504240076716244,
      "grad_norm": 0.47467467188835144,
      "learning_rate": 4e-05,
      "loss": 44.378,
      "step": 2
    },
    {
      "epoch": 0.00022563601150743658,
      "grad_norm": 0.4313117563724518,
      "learning_rate": 6e-05,
      "loss": 44.3639,
      "step": 3
    },
    {
      "epoch": 0.00022563601150743658,
      "eval_loss": 11.091465950012207,
      "eval_runtime": 12.849,
      "eval_samples_per_second": 435.755,
      "eval_steps_per_second": 217.916,
      "step": 3
    },
    {
      "epoch": 0.0003008480153432488,
      "grad_norm": 0.48261135816574097,
      "learning_rate": 8e-05,
      "loss": 44.3863,
      "step": 4
    },
    {
      "epoch": 0.00037606001917906096,
      "grad_norm": 0.3973361551761627,
      "learning_rate": 0.0001,
      "loss": 44.339,
      "step": 5
    },
    {
      "epoch": 0.00045127202301487317,
      "grad_norm": 0.4755844473838806,
      "learning_rate": 0.00012,
      "loss": 44.3582,
      "step": 6
    },
    {
      "epoch": 0.00045127202301487317,
      "eval_loss": 11.09097957611084,
      "eval_runtime": 12.865,
      "eval_samples_per_second": 435.212,
      "eval_steps_per_second": 217.645,
      "step": 6
    },
    {
      "epoch": 0.0005264840268506853,
      "grad_norm": 0.4780758321285248,
      "learning_rate": 0.00014,
      "loss": 44.3746,
      "step": 7
    },
    {
      "epoch": 0.0006016960306864976,
      "grad_norm": 0.4785214364528656,
      "learning_rate": 0.00016,
      "loss": 44.3519,
      "step": 8
    },
    {
      "epoch": 0.0006769080345223098,
      "grad_norm": 0.5370668768882751,
      "learning_rate": 0.00018,
      "loss": 44.3743,
      "step": 9
    },
    {
      "epoch": 0.0006769080345223098,
      "eval_loss": 11.090177536010742,
      "eval_runtime": 12.8547,
      "eval_samples_per_second": 435.559,
      "eval_steps_per_second": 217.818,
      "step": 9
    },
    {
      "epoch": 0.0007521200383581219,
      "grad_norm": 0.43962928652763367,
      "learning_rate": 0.0002,
      "loss": 44.3987,
      "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": 7471104000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}