{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04206098843322818,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008412197686645636,
      "eval_loss": 1.4323474168777466,
      "eval_runtime": 36.258,
      "eval_samples_per_second": 13.818,
      "eval_steps_per_second": 6.923,
      "step": 1
    },
    {
      "epoch": 0.004206098843322818,
      "grad_norm": 7.3401288986206055,
      "learning_rate": 5e-05,
      "loss": 4.5106,
      "step": 5
    },
    {
      "epoch": 0.008412197686645636,
      "grad_norm": 9.793989181518555,
      "learning_rate": 0.0001,
      "loss": 5.069,
      "step": 10
    },
    {
      "epoch": 0.008412197686645636,
      "eval_loss": 0.8625037670135498,
      "eval_runtime": 36.3466,
      "eval_samples_per_second": 13.784,
      "eval_steps_per_second": 6.906,
      "step": 10
    },
    {
      "epoch": 0.012618296529968454,
      "grad_norm": 4.714380264282227,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.2335,
      "step": 15
    },
    {
      "epoch": 0.016824395373291272,
      "grad_norm": 7.459444999694824,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9715,
      "step": 20
    },
    {
      "epoch": 0.016824395373291272,
      "eval_loss": 0.15596088767051697,
      "eval_runtime": 36.6136,
      "eval_samples_per_second": 13.683,
      "eval_steps_per_second": 6.855,
      "step": 20
    },
    {
      "epoch": 0.02103049421661409,
      "grad_norm": 3.0734777450561523,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6043,
      "step": 25
    },
    {
      "epoch": 0.025236593059936908,
      "grad_norm": 6.375624179840088,
      "learning_rate": 5e-05,
      "loss": 0.4428,
      "step": 30
    },
    {
      "epoch": 0.025236593059936908,
      "eval_loss": 0.10436299443244934,
      "eval_runtime": 36.4351,
      "eval_samples_per_second": 13.75,
      "eval_steps_per_second": 6.889,
      "step": 30
    },
    {
      "epoch": 0.029442691903259727,
      "grad_norm": 12.669096946716309,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.4152,
      "step": 35
    },
    {
      "epoch": 0.033648790746582544,
      "grad_norm": 2.661290168762207,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2648,
      "step": 40
    },
    {
      "epoch": 0.033648790746582544,
      "eval_loss": 0.09836208075284958,
      "eval_runtime": 36.4696,
      "eval_samples_per_second": 13.737,
      "eval_steps_per_second": 6.882,
      "step": 40
    },
    {
      "epoch": 0.03785488958990536,
      "grad_norm": 5.006651401519775,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3965,
      "step": 45
    },
    {
      "epoch": 0.04206098843322818,
      "grad_norm": 2.766874313354492,
      "learning_rate": 0.0,
      "loss": 0.3826,
      "step": 50
    },
    {
      "epoch": 0.04206098843322818,
      "eval_loss": 0.09258513897657394,
      "eval_runtime": 36.1781,
      "eval_samples_per_second": 13.848,
      "eval_steps_per_second": 6.938,
      "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": 4589766888652800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}