{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1153984853948792,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00576992426974396,
      "grad_norm": 1.6163705587387085,
      "learning_rate": 1e-05,
      "loss": 3.4564,
      "step": 1
    },
    {
      "epoch": 0.00576992426974396,
      "eval_loss": 3.3881170749664307,
      "eval_runtime": 61.3847,
      "eval_samples_per_second": 4.757,
      "eval_steps_per_second": 2.378,
      "step": 1
    },
    {
      "epoch": 0.01153984853948792,
      "grad_norm": 1.5159244537353516,
      "learning_rate": 2e-05,
      "loss": 3.2534,
      "step": 2
    },
    {
      "epoch": 0.01730977280923188,
      "grad_norm": 1.5761823654174805,
      "learning_rate": 3e-05,
      "loss": 3.3012,
      "step": 3
    },
    {
      "epoch": 0.02307969707897584,
      "grad_norm": 1.3649775981903076,
      "learning_rate": 4e-05,
      "loss": 3.1929,
      "step": 4
    },
    {
      "epoch": 0.0288496213487198,
      "grad_norm": 1.6219135522842407,
      "learning_rate": 5e-05,
      "loss": 3.1662,
      "step": 5
    },
    {
      "epoch": 0.0288496213487198,
      "eval_loss": 3.279860734939575,
      "eval_runtime": 9.8167,
      "eval_samples_per_second": 29.745,
      "eval_steps_per_second": 14.873,
      "step": 5
    },
    {
      "epoch": 0.03461954561846376,
      "grad_norm": 1.826447606086731,
      "learning_rate": 6e-05,
      "loss": 3.2932,
      "step": 6
    },
    {
      "epoch": 0.04038946988820772,
      "grad_norm": 1.667511224746704,
      "learning_rate": 7e-05,
      "loss": 3.0192,
      "step": 7
    },
    {
      "epoch": 0.04615939415795168,
      "grad_norm": 1.9313197135925293,
      "learning_rate": 8e-05,
      "loss": 3.1254,
      "step": 8
    },
    {
      "epoch": 0.05192931842769564,
      "grad_norm": 2.0608596801757812,
      "learning_rate": 9e-05,
      "loss": 2.9198,
      "step": 9
    },
    {
      "epoch": 0.0576992426974396,
      "grad_norm": 1.804194688796997,
      "learning_rate": 0.0001,
      "loss": 2.9576,
      "step": 10
    },
    {
      "epoch": 0.0576992426974396,
      "eval_loss": 2.8470706939697266,
      "eval_runtime": 11.6882,
      "eval_samples_per_second": 24.983,
      "eval_steps_per_second": 12.491,
      "step": 10
    },
    {
      "epoch": 0.06346916696718355,
      "grad_norm": 1.805935263633728,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.6093,
      "step": 11
    },
    {
      "epoch": 0.06923909123692752,
      "grad_norm": 1.9544267654418945,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4161,
      "step": 12
    },
    {
      "epoch": 0.07500901550667148,
      "grad_norm": 1.7214800119400024,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.6141,
      "step": 13
    },
    {
      "epoch": 0.08077893977641544,
      "grad_norm": 1.9497193098068237,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.3451,
      "step": 14
    },
    {
      "epoch": 0.0865488640461594,
      "grad_norm": 1.9425095319747925,
      "learning_rate": 5e-05,
      "loss": 2.6124,
      "step": 15
    },
    {
      "epoch": 0.0865488640461594,
      "eval_loss": 2.3446483612060547,
      "eval_runtime": 9.7749,
      "eval_samples_per_second": 29.872,
      "eval_steps_per_second": 14.936,
      "step": 15
    },
    {
      "epoch": 0.09231878831590336,
      "grad_norm": 1.9382221698760986,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0512,
      "step": 16
    },
    {
      "epoch": 0.09808871258564732,
      "grad_norm": 2.202096939086914,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.5403,
      "step": 17
    },
    {
      "epoch": 0.10385863685539128,
      "grad_norm": 2.173708915710449,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.2741,
      "step": 18
    },
    {
      "epoch": 0.10962856112513523,
      "grad_norm": 2.0655319690704346,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.3893,
      "step": 19
    },
    {
      "epoch": 0.1153984853948792,
      "grad_norm": 2.22983717918396,
      "learning_rate": 0.0,
      "loss": 2.2451,
      "step": 20
    },
    {
      "epoch": 0.1153984853948792,
      "eval_loss": 2.270918130874634,
      "eval_runtime": 16.3547,
      "eval_samples_per_second": 17.854,
      "eval_steps_per_second": 8.927,
      "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": 1.479651398516736e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}