{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016333197223356473,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005444399074452157,
      "eval_loss": 7.361711502075195,
      "eval_runtime": 5.2901,
      "eval_samples_per_second": 146.311,
      "eval_steps_per_second": 73.155,
      "step": 1
    },
    {
      "epoch": 0.0016333197223356473,
      "grad_norm": 3018.555419921875,
      "learning_rate": 4e-05,
      "loss": 29.4527,
      "step": 3
    },
    {
      "epoch": 0.0027221995372260785,
      "eval_loss": 7.326521396636963,
      "eval_runtime": 4.8792,
      "eval_samples_per_second": 158.633,
      "eval_steps_per_second": 79.317,
      "step": 5
    },
    {
      "epoch": 0.0032666394446712946,
      "grad_norm": 2035.9393310546875,
      "learning_rate": 8e-05,
      "loss": 29.6231,
      "step": 6
    },
    {
      "epoch": 0.004899959167006942,
      "grad_norm": 2877.90185546875,
      "learning_rate": 0.00012,
      "loss": 29.1023,
      "step": 9
    },
    {
      "epoch": 0.005444399074452157,
      "eval_loss": 7.256721019744873,
      "eval_runtime": 4.8765,
      "eval_samples_per_second": 158.721,
      "eval_steps_per_second": 79.361,
      "step": 10
    },
    {
      "epoch": 0.006533278889342589,
      "grad_norm": 2655.123291015625,
      "learning_rate": 0.00016,
      "loss": 28.3913,
      "step": 12
    },
    {
      "epoch": 0.008166598611678236,
      "grad_norm": 2249.07373046875,
      "learning_rate": 0.0002,
      "loss": 28.355,
      "step": 15
    },
    {
      "epoch": 0.008166598611678236,
      "eval_loss": 7.156546592712402,
      "eval_runtime": 4.8891,
      "eval_samples_per_second": 158.31,
      "eval_steps_per_second": 79.155,
      "step": 15
    },
    {
      "epoch": 0.009799918334013884,
      "grad_norm": 2144.675048828125,
      "learning_rate": 0.00018090169943749476,
      "loss": 29.4269,
      "step": 18
    },
    {
      "epoch": 0.010888798148904314,
      "eval_loss": 7.053538799285889,
      "eval_runtime": 4.9311,
      "eval_samples_per_second": 156.964,
      "eval_steps_per_second": 78.482,
      "step": 20
    },
    {
      "epoch": 0.011433238056349531,
      "grad_norm": 2027.64697265625,
      "learning_rate": 0.00013090169943749476,
      "loss": 28.5078,
      "step": 21
    },
    {
      "epoch": 0.013066557778685178,
      "grad_norm": 1969.8271484375,
      "learning_rate": 6.909830056250527e-05,
      "loss": 27.8338,
      "step": 24
    },
    {
      "epoch": 0.013610997686130393,
      "eval_loss": 7.016091823577881,
      "eval_runtime": 4.8933,
      "eval_samples_per_second": 158.175,
      "eval_steps_per_second": 79.087,
      "step": 25
    },
    {
      "epoch": 0.014699877501020826,
      "grad_norm": 2088.4873046875,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 28.0861,
      "step": 27
    },
    {
      "epoch": 0.016333197223356473,
      "grad_norm": 2591.714599609375,
      "learning_rate": 0.0,
      "loss": 27.7559,
      "step": 30
    },
    {
      "epoch": 0.016333197223356473,
      "eval_loss": 7.001165866851807,
      "eval_runtime": 4.879,
      "eval_samples_per_second": 158.639,
      "eval_steps_per_second": 79.319,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 12533486321664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}