{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015203344735841885,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015203344735841885,
      "grad_norm": 1.1856921911239624,
      "learning_rate": 2e-05,
      "loss": 2.0886,
      "step": 1
    },
    {
      "epoch": 0.0015203344735841885,
      "eval_loss": 2.2539732456207275,
      "eval_runtime": 54.3619,
      "eval_samples_per_second": 5.095,
      "eval_steps_per_second": 2.557,
      "step": 1
    },
    {
      "epoch": 0.003040668947168377,
      "grad_norm": 1.251565933227539,
      "learning_rate": 4e-05,
      "loss": 2.1271,
      "step": 2
    },
    {
      "epoch": 0.004561003420752566,
      "grad_norm": 1.1893006563186646,
      "learning_rate": 6e-05,
      "loss": 2.3036,
      "step": 3
    },
    {
      "epoch": 0.004561003420752566,
      "eval_loss": 2.247591972351074,
      "eval_runtime": 51.7739,
      "eval_samples_per_second": 5.35,
      "eval_steps_per_second": 2.685,
      "step": 3
    },
    {
      "epoch": 0.006081337894336754,
      "grad_norm": 1.1530547142028809,
      "learning_rate": 8e-05,
      "loss": 2.0354,
      "step": 4
    },
    {
      "epoch": 0.007601672367920942,
      "grad_norm": 1.4242063760757446,
      "learning_rate": 0.0001,
      "loss": 2.6578,
      "step": 5
    },
    {
      "epoch": 0.009122006841505131,
      "grad_norm": 1.3272254467010498,
      "learning_rate": 0.00012,
      "loss": 1.9634,
      "step": 6
    },
    {
      "epoch": 0.009122006841505131,
      "eval_loss": 2.148479700088501,
      "eval_runtime": 52.6585,
      "eval_samples_per_second": 5.26,
      "eval_steps_per_second": 2.64,
      "step": 6
    },
    {
      "epoch": 0.010642341315089319,
      "grad_norm": 1.2682982683181763,
      "learning_rate": 0.00014,
      "loss": 2.0671,
      "step": 7
    },
    {
      "epoch": 0.012162675788673508,
      "grad_norm": 1.5430965423583984,
      "learning_rate": 0.00016,
      "loss": 2.2311,
      "step": 8
    },
    {
      "epoch": 0.013683010262257697,
      "grad_norm": 1.4492532014846802,
      "learning_rate": 0.00018,
      "loss": 1.928,
      "step": 9
    },
    {
      "epoch": 0.013683010262257697,
      "eval_loss": 1.9016118049621582,
      "eval_runtime": 49.9717,
      "eval_samples_per_second": 5.543,
      "eval_steps_per_second": 2.782,
      "step": 9
    },
    {
      "epoch": 0.015203344735841885,
      "grad_norm": 1.5801235437393188,
      "learning_rate": 0.0002,
      "loss": 1.6542,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}