{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012326656394453005,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002465331278890601,
      "eval_loss": 2.9199776649475098,
      "eval_runtime": 45.1913,
      "eval_samples_per_second": 37.795,
      "eval_steps_per_second": 18.897,
      "step": 1
    },
    {
      "epoch": 0.0012326656394453005,
      "grad_norm": 0.990307629108429,
      "learning_rate": 5e-05,
      "loss": 2.7756,
      "step": 5
    },
    {
      "epoch": 0.002465331278890601,
      "grad_norm": 1.2646774053573608,
      "learning_rate": 0.0001,
      "loss": 2.9447,
      "step": 10
    },
    {
      "epoch": 0.002465331278890601,
      "eval_loss": 2.782742977142334,
      "eval_runtime": 45.0708,
      "eval_samples_per_second": 37.896,
      "eval_steps_per_second": 18.948,
      "step": 10
    },
    {
      "epoch": 0.0036979969183359015,
      "grad_norm": 1.765432596206665,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.6895,
      "step": 15
    },
    {
      "epoch": 0.004930662557781202,
      "grad_norm": 1.6517176628112793,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.4638,
      "step": 20
    },
    {
      "epoch": 0.004930662557781202,
      "eval_loss": 2.421093702316284,
      "eval_runtime": 44.7743,
      "eval_samples_per_second": 38.147,
      "eval_steps_per_second": 19.073,
      "step": 20
    },
    {
      "epoch": 0.0061633281972265025,
      "grad_norm": 1.9980548620224,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.4485,
      "step": 25
    },
    {
      "epoch": 0.007395993836671803,
      "grad_norm": 1.813212275505066,
      "learning_rate": 5e-05,
      "loss": 2.3923,
      "step": 30
    },
    {
      "epoch": 0.007395993836671803,
      "eval_loss": 2.327768564224243,
      "eval_runtime": 45.358,
      "eval_samples_per_second": 37.656,
      "eval_steps_per_second": 18.828,
      "step": 30
    },
    {
      "epoch": 0.008628659476117103,
      "grad_norm": 1.662560224533081,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.2099,
      "step": 35
    },
    {
      "epoch": 0.009861325115562404,
      "grad_norm": 1.5937579870224,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.2899,
      "step": 40
    },
    {
      "epoch": 0.009861325115562404,
      "eval_loss": 2.298952579498291,
      "eval_runtime": 45.2841,
      "eval_samples_per_second": 37.717,
      "eval_steps_per_second": 18.859,
      "step": 40
    },
    {
      "epoch": 0.011093990755007704,
      "grad_norm": 1.6355552673339844,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.2645,
      "step": 45
    },
    {
      "epoch": 0.012326656394453005,
      "grad_norm": 1.5542072057724,
      "learning_rate": 0.0,
      "loss": 2.324,
      "step": 50
    },
    {
      "epoch": 0.012326656394453005,
      "eval_loss": 2.294262409210205,
      "eval_runtime": 45.1146,
      "eval_samples_per_second": 37.859,
      "eval_steps_per_second": 18.93,
      "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": 1202727577190400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}