{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006435643564356435,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004950495049504951,
      "grad_norm": 0.5099626779556274,
      "learning_rate": 5e-06,
      "loss": 2.5697,
      "step": 1
    },
    {
      "epoch": 0.0004950495049504951,
      "eval_loss": 2.622131824493408,
      "eval_runtime": 15.9426,
      "eval_samples_per_second": 53.379,
      "eval_steps_per_second": 26.721,
      "step": 1
    },
    {
      "epoch": 0.0009900990099009901,
      "grad_norm": 0.539216935634613,
      "learning_rate": 1e-05,
      "loss": 2.6019,
      "step": 2
    },
    {
      "epoch": 0.0014851485148514852,
      "grad_norm": 1.0987958908081055,
      "learning_rate": 1.5e-05,
      "loss": 2.5236,
      "step": 3
    },
    {
      "epoch": 0.0019801980198019802,
      "grad_norm": 0.9217115640640259,
      "learning_rate": 2e-05,
      "loss": 2.682,
      "step": 4
    },
    {
      "epoch": 0.0024752475247524753,
      "grad_norm": 0.7861433625221252,
      "learning_rate": 2.5e-05,
      "loss": 2.3686,
      "step": 5
    },
    {
      "epoch": 0.0029702970297029703,
      "grad_norm": 0.9432778358459473,
      "learning_rate": 3e-05,
      "loss": 2.3954,
      "step": 6
    },
    {
      "epoch": 0.0034653465346534654,
      "grad_norm": 0.6162946820259094,
      "learning_rate": 3.5e-05,
      "loss": 2.8127,
      "step": 7
    },
    {
      "epoch": 0.0039603960396039604,
      "grad_norm": 0.671248197555542,
      "learning_rate": 4e-05,
      "loss": 2.5454,
      "step": 8
    },
    {
      "epoch": 0.004455445544554455,
      "grad_norm": 0.7792280912399292,
      "learning_rate": 4.5e-05,
      "loss": 2.5155,
      "step": 9
    },
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": 0.5344467163085938,
      "learning_rate": 5e-05,
      "loss": 2.6138,
      "step": 10
    },
    {
      "epoch": 0.005445544554455445,
      "grad_norm": 0.8850129246711731,
      "learning_rate": 4.99229333433282e-05,
      "loss": 2.5492,
      "step": 11
    },
    {
      "epoch": 0.005940594059405941,
      "grad_norm": 0.8699153065681458,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 2.7188,
      "step": 12
    },
    {
      "epoch": 0.006435643564356435,
      "grad_norm": 0.7159351110458374,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 2.7603,
      "step": 13
    },
    {
      "epoch": 0.006435643564356435,
      "eval_loss": 2.6000754833221436,
      "eval_runtime": 14.7393,
      "eval_samples_per_second": 57.737,
      "eval_steps_per_second": 28.902,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 422056764112896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}