{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014330753797649757,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028661507595299513,
      "eval_loss": 11.943561553955078,
      "eval_runtime": 23.888,
      "eval_samples_per_second": 61.537,
      "eval_steps_per_second": 30.769,
      "step": 1
    },
    {
      "epoch": 0.0014330753797649756,
      "grad_norm": 0.016951726749539375,
      "learning_rate": 5e-05,
      "loss": 11.9421,
      "step": 5
    },
    {
      "epoch": 0.002866150759529951,
      "grad_norm": 0.022354425862431526,
      "learning_rate": 0.0001,
      "loss": 11.9455,
      "step": 10
    },
    {
      "epoch": 0.002866150759529951,
      "eval_loss": 11.94344711303711,
      "eval_runtime": 24.2322,
      "eval_samples_per_second": 60.663,
      "eval_steps_per_second": 30.332,
      "step": 10
    },
    {
      "epoch": 0.004299226139294927,
      "grad_norm": 0.014445611275732517,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9419,
      "step": 15
    },
    {
      "epoch": 0.005732301519059902,
      "grad_norm": 0.02055429480969906,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9424,
      "step": 20
    },
    {
      "epoch": 0.005732301519059902,
      "eval_loss": 11.943193435668945,
      "eval_runtime": 23.8966,
      "eval_samples_per_second": 61.515,
      "eval_steps_per_second": 30.758,
      "step": 20
    },
    {
      "epoch": 0.0071653768988248785,
      "grad_norm": 0.021375872194767,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9438,
      "step": 25
    },
    {
      "epoch": 0.008598452278589854,
      "grad_norm": 0.02149290218949318,
      "learning_rate": 5e-05,
      "loss": 11.941,
      "step": 30
    },
    {
      "epoch": 0.008598452278589854,
      "eval_loss": 11.942995071411133,
      "eval_runtime": 24.2861,
      "eval_samples_per_second": 60.528,
      "eval_steps_per_second": 30.264,
      "step": 30
    },
    {
      "epoch": 0.01003152765835483,
      "grad_norm": 0.021839598193764687,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9437,
      "step": 35
    },
    {
      "epoch": 0.011464603038119804,
      "grad_norm": 0.024526268243789673,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9457,
      "step": 40
    },
    {
      "epoch": 0.011464603038119804,
      "eval_loss": 11.942913055419922,
      "eval_runtime": 24.2726,
      "eval_samples_per_second": 60.562,
      "eval_steps_per_second": 30.281,
      "step": 40
    },
    {
      "epoch": 0.012897678417884782,
      "grad_norm": 0.018200471997261047,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9401,
      "step": 45
    },
    {
      "epoch": 0.014330753797649757,
      "grad_norm": 0.030765095725655556,
      "learning_rate": 0.0,
      "loss": 11.9439,
      "step": 50
    },
    {
      "epoch": 0.014330753797649757,
      "eval_loss": 11.942886352539062,
      "eval_runtime": 23.8007,
      "eval_samples_per_second": 61.763,
      "eval_steps_per_second": 30.881,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5908070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}