{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14035087719298245,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 2.8504276275634766,
      "learning_rate": 1e-05,
      "loss": 17.487,
      "step": 1
    },
    {
      "epoch": 0.007017543859649123,
      "eval_loss": 1.1553192138671875,
      "eval_runtime": 95.7389,
      "eval_samples_per_second": 2.507,
      "eval_steps_per_second": 1.253,
      "step": 1
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 3.5421972274780273,
      "learning_rate": 2e-05,
      "loss": 19.4668,
      "step": 2
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 3.372083902359009,
      "learning_rate": 3e-05,
      "loss": 17.2781,
      "step": 3
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 2.8809428215026855,
      "learning_rate": 4e-05,
      "loss": 16.4683,
      "step": 4
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 3.473324775695801,
      "learning_rate": 5e-05,
      "loss": 19.2854,
      "step": 5
    },
    {
      "epoch": 0.03508771929824561,
      "eval_loss": 1.127090573310852,
      "eval_runtime": 8.9521,
      "eval_samples_per_second": 26.809,
      "eval_steps_per_second": 13.405,
      "step": 5
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 4.122745990753174,
      "learning_rate": 6e-05,
      "loss": 20.2028,
      "step": 6
    },
    {
      "epoch": 0.04912280701754386,
      "grad_norm": 3.8199222087860107,
      "learning_rate": 7e-05,
      "loss": 17.6577,
      "step": 7
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 4.428239822387695,
      "learning_rate": 8e-05,
      "loss": 17.0906,
      "step": 8
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 4.9802751541137695,
      "learning_rate": 9e-05,
      "loss": 16.6059,
      "step": 9
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 5.734658241271973,
      "learning_rate": 0.0001,
      "loss": 16.6593,
      "step": 10
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 1.0094025135040283,
      "eval_runtime": 9.0546,
      "eval_samples_per_second": 26.506,
      "eval_steps_per_second": 13.253,
      "step": 10
    },
    {
      "epoch": 0.07719298245614035,
      "grad_norm": 6.979969501495361,
      "learning_rate": 9.755282581475769e-05,
      "loss": 16.7988,
      "step": 11
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 6.168642997741699,
      "learning_rate": 9.045084971874738e-05,
      "loss": 15.2197,
      "step": 12
    },
    {
      "epoch": 0.0912280701754386,
      "grad_norm": 7.531093120574951,
      "learning_rate": 7.938926261462366e-05,
      "loss": 14.5283,
      "step": 13
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 6.556507110595703,
      "learning_rate": 6.545084971874738e-05,
      "loss": 15.0155,
      "step": 14
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 6.081122398376465,
      "learning_rate": 5e-05,
      "loss": 13.9098,
      "step": 15
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 0.8202072381973267,
      "eval_runtime": 8.9737,
      "eval_samples_per_second": 26.745,
      "eval_steps_per_second": 13.372,
      "step": 15
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 6.341962814331055,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.5136,
      "step": 16
    },
    {
      "epoch": 0.11929824561403508,
      "grad_norm": 6.404966831207275,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9517,
      "step": 17
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 6.500393867492676,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.8158,
      "step": 18
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 6.19280481338501,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 11.0811,
      "step": 19
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 6.322799205780029,
      "learning_rate": 0.0,
      "loss": 12.8055,
      "step": 20
    },
    {
      "epoch": 0.14035087719298245,
      "eval_loss": 0.7703096866607666,
      "eval_runtime": 10.4663,
      "eval_samples_per_second": 22.931,
      "eval_steps_per_second": 11.465,
      "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": 2.13773338017792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}