{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11619462599854757,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005809731299927378,
      "grad_norm": 2.741241455078125,
      "learning_rate": 1e-05,
      "loss": 1.3625,
      "step": 1
    },
    {
      "epoch": 0.005809731299927378,
      "eval_loss": 1.4765580892562866,
      "eval_runtime": 44.8895,
      "eval_samples_per_second": 6.46,
      "eval_steps_per_second": 3.23,
      "step": 1
    },
    {
      "epoch": 0.011619462599854757,
      "grad_norm": 2.9708011150360107,
      "learning_rate": 2e-05,
      "loss": 1.4631,
      "step": 2
    },
    {
      "epoch": 0.017429193899782137,
      "grad_norm": 2.6576545238494873,
      "learning_rate": 3e-05,
      "loss": 1.3745,
      "step": 3
    },
    {
      "epoch": 0.023238925199709513,
      "grad_norm": 2.884458541870117,
      "learning_rate": 4e-05,
      "loss": 1.5179,
      "step": 4
    },
    {
      "epoch": 0.029048656499636893,
      "grad_norm": 2.372880697250366,
      "learning_rate": 5e-05,
      "loss": 1.3964,
      "step": 5
    },
    {
      "epoch": 0.029048656499636893,
      "eval_loss": 1.3319202661514282,
      "eval_runtime": 4.1636,
      "eval_samples_per_second": 69.652,
      "eval_steps_per_second": 34.826,
      "step": 5
    },
    {
      "epoch": 0.034858387799564274,
      "grad_norm": 2.502950429916382,
      "learning_rate": 6e-05,
      "loss": 1.2606,
      "step": 6
    },
    {
      "epoch": 0.04066811909949165,
      "grad_norm": 2.5630197525024414,
      "learning_rate": 7e-05,
      "loss": 1.2473,
      "step": 7
    },
    {
      "epoch": 0.04647785039941903,
      "grad_norm": 2.3424484729766846,
      "learning_rate": 8e-05,
      "loss": 1.1437,
      "step": 8
    },
    {
      "epoch": 0.05228758169934641,
      "grad_norm": 2.0302140712738037,
      "learning_rate": 9e-05,
      "loss": 0.9926,
      "step": 9
    },
    {
      "epoch": 0.05809731299927379,
      "grad_norm": 2.140005111694336,
      "learning_rate": 0.0001,
      "loss": 0.9833,
      "step": 10
    },
    {
      "epoch": 0.05809731299927379,
      "eval_loss": 0.9422959089279175,
      "eval_runtime": 4.1796,
      "eval_samples_per_second": 69.385,
      "eval_steps_per_second": 34.693,
      "step": 10
    },
    {
      "epoch": 0.06390704429920116,
      "grad_norm": 2.665182113647461,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9545,
      "step": 11
    },
    {
      "epoch": 0.06971677559912855,
      "grad_norm": 2.2438454627990723,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.863,
      "step": 12
    },
    {
      "epoch": 0.07552650689905592,
      "grad_norm": 2.2425379753112793,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.755,
      "step": 13
    },
    {
      "epoch": 0.0813362381989833,
      "grad_norm": 1.502351999282837,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7284,
      "step": 14
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 1.436643123626709,
      "learning_rate": 5e-05,
      "loss": 0.5585,
      "step": 15
    },
    {
      "epoch": 0.08714596949891068,
      "eval_loss": 0.6648338437080383,
      "eval_runtime": 4.1764,
      "eval_samples_per_second": 69.437,
      "eval_steps_per_second": 34.719,
      "step": 15
    },
    {
      "epoch": 0.09295570079883805,
      "grad_norm": 1.2568418979644775,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5991,
      "step": 16
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 1.415218472480774,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6339,
      "step": 17
    },
    {
      "epoch": 0.10457516339869281,
      "grad_norm": 1.306711196899414,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5651,
      "step": 18
    },
    {
      "epoch": 0.11038489469862019,
      "grad_norm": 1.4163092374801636,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5494,
      "step": 19
    },
    {
      "epoch": 0.11619462599854757,
      "grad_norm": 1.318520426750183,
      "learning_rate": 0.0,
      "loss": 0.6674,
      "step": 20
    },
    {
      "epoch": 0.11619462599854757,
      "eval_loss": 0.6370882987976074,
      "eval_runtime": 4.169,
      "eval_samples_per_second": 69.561,
      "eval_steps_per_second": 34.781,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 712305310433280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}