{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002824459822059031,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028244598220590313,
      "grad_norm": 0.5669630765914917,
      "learning_rate": 2e-05,
      "loss": 1.694,
      "step": 1
    },
    {
      "epoch": 0.00028244598220590313,
      "eval_loss": 1.4107834100723267,
      "eval_runtime": 85.5831,
      "eval_samples_per_second": 17.422,
      "eval_steps_per_second": 8.717,
      "step": 1
    },
    {
      "epoch": 0.0005648919644118063,
      "grad_norm": 0.4896361827850342,
      "learning_rate": 4e-05,
      "loss": 1.2039,
      "step": 2
    },
    {
      "epoch": 0.0008473379466177093,
      "grad_norm": 0.49284276366233826,
      "learning_rate": 6e-05,
      "loss": 1.4376,
      "step": 3
    },
    {
      "epoch": 0.0008473379466177093,
      "eval_loss": 1.408732533454895,
      "eval_runtime": 83.5396,
      "eval_samples_per_second": 17.848,
      "eval_steps_per_second": 8.93,
      "step": 3
    },
    {
      "epoch": 0.0011297839288236125,
      "grad_norm": 0.6072423458099365,
      "learning_rate": 8e-05,
      "loss": 1.5728,
      "step": 4
    },
    {
      "epoch": 0.0014122299110295156,
      "grad_norm": 0.5226939916610718,
      "learning_rate": 0.0001,
      "loss": 1.28,
      "step": 5
    },
    {
      "epoch": 0.0016946758932354187,
      "grad_norm": 0.6130642294883728,
      "learning_rate": 0.00012,
      "loss": 1.4993,
      "step": 6
    },
    {
      "epoch": 0.0016946758932354187,
      "eval_loss": 1.3740650415420532,
      "eval_runtime": 83.8221,
      "eval_samples_per_second": 17.788,
      "eval_steps_per_second": 8.9,
      "step": 6
    },
    {
      "epoch": 0.001977121875441322,
      "grad_norm": 0.5710554718971252,
      "learning_rate": 0.00014,
      "loss": 1.2506,
      "step": 7
    },
    {
      "epoch": 0.002259567857647225,
      "grad_norm": 0.6765641570091248,
      "learning_rate": 0.00016,
      "loss": 1.581,
      "step": 8
    },
    {
      "epoch": 0.002542013839853128,
      "grad_norm": 0.4887714982032776,
      "learning_rate": 0.00018,
      "loss": 1.0725,
      "step": 9
    },
    {
      "epoch": 0.002542013839853128,
      "eval_loss": 1.3453608751296997,
      "eval_runtime": 83.7345,
      "eval_samples_per_second": 17.806,
      "eval_steps_per_second": 8.909,
      "step": 9
    },
    {
      "epoch": 0.002824459822059031,
      "grad_norm": 0.8616594076156616,
      "learning_rate": 0.0002,
      "loss": 1.3613,
      "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": 3652889390088192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}