{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008685833405715278,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.685833405715279e-05,
      "grad_norm": 19.607969284057617,
      "learning_rate": 2e-05,
      "loss": 21.7314,
      "step": 1
    },
    {
      "epoch": 8.685833405715279e-05,
      "eval_loss": 5.757102012634277,
      "eval_runtime": 55.117,
      "eval_samples_per_second": 87.958,
      "eval_steps_per_second": 43.979,
      "step": 1
    },
    {
      "epoch": 0.00017371666811430558,
      "grad_norm": 14.081522941589355,
      "learning_rate": 4e-05,
      "loss": 21.4816,
      "step": 2
    },
    {
      "epoch": 0.00026057500217145836,
      "grad_norm": 31.582218170166016,
      "learning_rate": 6e-05,
      "loss": 26.0581,
      "step": 3
    },
    {
      "epoch": 0.00026057500217145836,
      "eval_loss": 5.680545806884766,
      "eval_runtime": 55.2006,
      "eval_samples_per_second": 87.825,
      "eval_steps_per_second": 43.913,
      "step": 3
    },
    {
      "epoch": 0.00034743333622861116,
      "grad_norm": 18.147464752197266,
      "learning_rate": 8e-05,
      "loss": 20.2487,
      "step": 4
    },
    {
      "epoch": 0.0004342916702857639,
      "grad_norm": 21.6803035736084,
      "learning_rate": 0.0001,
      "loss": 23.0398,
      "step": 5
    },
    {
      "epoch": 0.0005211500043429167,
      "grad_norm": 21.650285720825195,
      "learning_rate": 0.00012,
      "loss": 22.4191,
      "step": 6
    },
    {
      "epoch": 0.0005211500043429167,
      "eval_loss": 5.138402938842773,
      "eval_runtime": 55.977,
      "eval_samples_per_second": 86.607,
      "eval_steps_per_second": 43.303,
      "step": 6
    },
    {
      "epoch": 0.0006080083384000695,
      "grad_norm": 16.647531509399414,
      "learning_rate": 0.00014,
      "loss": 22.1353,
      "step": 7
    },
    {
      "epoch": 0.0006948666724572223,
      "grad_norm": 11.165193557739258,
      "learning_rate": 0.00016,
      "loss": 19.1234,
      "step": 8
    },
    {
      "epoch": 0.000781725006514375,
      "grad_norm": 11.652397155761719,
      "learning_rate": 0.00018,
      "loss": 20.5037,
      "step": 9
    },
    {
      "epoch": 0.000781725006514375,
      "eval_loss": 4.6256794929504395,
      "eval_runtime": 55.5105,
      "eval_samples_per_second": 87.335,
      "eval_steps_per_second": 43.667,
      "step": 9
    },
    {
      "epoch": 0.0008685833405715278,
      "grad_norm": 8.353578567504883,
      "learning_rate": 0.0002,
      "loss": 18.8501,
      "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": 75069652992000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}