{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012810248198558846,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047445363698366103,
      "eval_loss": 1.2206629514694214,
      "eval_runtime": 2455.084,
      "eval_samples_per_second": 2.892,
      "eval_steps_per_second": 1.446,
      "step": 1
    },
    {
      "epoch": 0.001423360910950983,
      "grad_norm": 42.169185638427734,
      "learning_rate": 3e-05,
      "loss": 38.8115,
      "step": 3
    },
    {
      "epoch": 0.002846721821901966,
      "grad_norm": 30.064516067504883,
      "learning_rate": 6e-05,
      "loss": 36.5887,
      "step": 6
    },
    {
      "epoch": 0.004270082732852949,
      "grad_norm": 24.0466365814209,
      "learning_rate": 9e-05,
      "loss": 31.7486,
      "step": 9
    },
    {
      "epoch": 0.004270082732852949,
      "eval_loss": 0.872442364692688,
      "eval_runtime": 2457.1575,
      "eval_samples_per_second": 2.89,
      "eval_steps_per_second": 1.445,
      "step": 9
    },
    {
      "epoch": 0.005693443643803932,
      "grad_norm": 26.121597290039062,
      "learning_rate": 0.00012,
      "loss": 28.0893,
      "step": 12
    },
    {
      "epoch": 0.007116804554754915,
      "grad_norm": 22.931711196899414,
      "learning_rate": 0.00015000000000000001,
      "loss": 26.3657,
      "step": 15
    },
    {
      "epoch": 0.008540165465705898,
      "grad_norm": 15.313858032226562,
      "learning_rate": 0.00018,
      "loss": 22.876,
      "step": 18
    },
    {
      "epoch": 0.008540165465705898,
      "eval_loss": 0.7377527952194214,
      "eval_runtime": 730.2515,
      "eval_samples_per_second": 9.723,
      "eval_steps_per_second": 4.861,
      "step": 18
    },
    {
      "epoch": 0.009963526376656881,
      "grad_norm": 14.844147682189941,
      "learning_rate": 0.0001999229036240723,
      "loss": 23.8388,
      "step": 21
    },
    {
      "epoch": 0.011386887287607865,
      "grad_norm": 13.040925025939941,
      "learning_rate": 0.00019876883405951377,
      "loss": 23.2438,
      "step": 24
    },
    {
      "epoch": 0.012810248198558846,
      "grad_norm": 13.732440948486328,
      "learning_rate": 0.00019624552364536473,
      "loss": 23.504,
      "step": 27
    },
    {
      "epoch": 0.012810248198558846,
      "eval_loss": 0.708083987236023,
      "eval_runtime": 2490.0558,
      "eval_samples_per_second": 2.851,
      "eval_steps_per_second": 1.426,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4232452299594138e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}