{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019000570017100513,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003800114003420103,
      "eval_loss": 23.27000617980957,
      "eval_runtime": 9.2402,
      "eval_samples_per_second": 119.911,
      "eval_steps_per_second": 59.956,
      "step": 1
    },
    {
      "epoch": 0.0019000570017100513,
      "grad_norm": 519.7586669921875,
      "learning_rate": 5e-05,
      "loss": 87.194,
      "step": 5
    },
    {
      "epoch": 0.0038001140034201026,
      "grad_norm": 664.9725952148438,
      "learning_rate": 0.0001,
      "loss": 92.1238,
      "step": 10
    },
    {
      "epoch": 0.0038001140034201026,
      "eval_loss": 23.24598503112793,
      "eval_runtime": 7.9253,
      "eval_samples_per_second": 139.805,
      "eval_steps_per_second": 69.903,
      "step": 10
    },
    {
      "epoch": 0.005700171005130154,
      "grad_norm": 529.2100830078125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 81.4961,
      "step": 15
    },
    {
      "epoch": 0.007600228006840205,
      "grad_norm": 598.62158203125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 82.2434,
      "step": 20
    },
    {
      "epoch": 0.007600228006840205,
      "eval_loss": 23.046268463134766,
      "eval_runtime": 7.9899,
      "eval_samples_per_second": 138.675,
      "eval_steps_per_second": 69.338,
      "step": 20
    },
    {
      "epoch": 0.009500285008550257,
      "grad_norm": 631.08837890625,
      "learning_rate": 6.91341716182545e-05,
      "loss": 96.2517,
      "step": 25
    },
    {
      "epoch": 0.011400342010260307,
      "grad_norm": 594.5926513671875,
      "learning_rate": 5e-05,
      "loss": 115.9972,
      "step": 30
    },
    {
      "epoch": 0.011400342010260307,
      "eval_loss": 22.822322845458984,
      "eval_runtime": 7.992,
      "eval_samples_per_second": 138.639,
      "eval_steps_per_second": 69.319,
      "step": 30
    },
    {
      "epoch": 0.01330039901197036,
      "grad_norm": 846.1590576171875,
      "learning_rate": 3.086582838174551e-05,
      "loss": 72.7073,
      "step": 35
    },
    {
      "epoch": 0.01520045601368041,
      "grad_norm": 607.7332153320312,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 89.6675,
      "step": 40
    },
    {
      "epoch": 0.01520045601368041,
      "eval_loss": 22.692827224731445,
      "eval_runtime": 8.0814,
      "eval_samples_per_second": 137.104,
      "eval_steps_per_second": 68.552,
      "step": 40
    },
    {
      "epoch": 0.01710051301539046,
      "grad_norm": 776.9797973632812,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 90.7522,
      "step": 45
    },
    {
      "epoch": 0.019000570017100513,
      "grad_norm": 736.1396484375,
      "learning_rate": 0.0,
      "loss": 75.1007,
      "step": 50
    },
    {
      "epoch": 0.019000570017100513,
      "eval_loss": 22.678951263427734,
      "eval_runtime": 7.921,
      "eval_samples_per_second": 139.88,
      "eval_steps_per_second": 69.94,
      "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": 55928627920896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}