{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00046185643192813515,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6185643192813516e-05,
      "grad_norm": 1.717484474182129,
      "learning_rate": 2e-05,
      "loss": 16.2714,
      "step": 1
    },
    {
      "epoch": 4.6185643192813516e-05,
      "eval_loss": 3.6097772121429443,
      "eval_runtime": 140.9907,
      "eval_samples_per_second": 64.664,
      "eval_steps_per_second": 32.335,
      "step": 1
    },
    {
      "epoch": 9.237128638562703e-05,
      "grad_norm": 0.7847801446914673,
      "learning_rate": 4e-05,
      "loss": 14.3018,
      "step": 2
    },
    {
      "epoch": 0.00013855692957844053,
      "grad_norm": 0.7307888865470886,
      "learning_rate": 6e-05,
      "loss": 14.5611,
      "step": 3
    },
    {
      "epoch": 0.00013855692957844053,
      "eval_loss": 3.6097519397735596,
      "eval_runtime": 139.9133,
      "eval_samples_per_second": 65.162,
      "eval_steps_per_second": 32.584,
      "step": 3
    },
    {
      "epoch": 0.00018474257277125407,
      "grad_norm": 0.6767831444740295,
      "learning_rate": 8e-05,
      "loss": 13.8588,
      "step": 4
    },
    {
      "epoch": 0.00023092821596406757,
      "grad_norm": 0.8352742195129395,
      "learning_rate": 0.0001,
      "loss": 14.6376,
      "step": 5
    },
    {
      "epoch": 0.00027711385915688106,
      "grad_norm": 0.8315963745117188,
      "learning_rate": 0.00012,
      "loss": 13.9297,
      "step": 6
    },
    {
      "epoch": 0.00027711385915688106,
      "eval_loss": 3.6088805198669434,
      "eval_runtime": 141.7907,
      "eval_samples_per_second": 64.299,
      "eval_steps_per_second": 32.153,
      "step": 6
    },
    {
      "epoch": 0.0003232995023496946,
      "grad_norm": 0.7119724750518799,
      "learning_rate": 0.00014,
      "loss": 13.9683,
      "step": 7
    },
    {
      "epoch": 0.00036948514554250813,
      "grad_norm": 0.6508973836898804,
      "learning_rate": 0.00016,
      "loss": 13.9883,
      "step": 8
    },
    {
      "epoch": 0.0004156707887353216,
      "grad_norm": 1.389617681503296,
      "learning_rate": 0.00018,
      "loss": 14.9808,
      "step": 9
    },
    {
      "epoch": 0.0004156707887353216,
      "eval_loss": 3.60542368888855,
      "eval_runtime": 143.2536,
      "eval_samples_per_second": 63.642,
      "eval_steps_per_second": 31.825,
      "step": 9
    },
    {
      "epoch": 0.00046185643192813515,
      "grad_norm": 0.7027760148048401,
      "learning_rate": 0.0002,
      "loss": 14.7874,
      "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": 21222716866560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}