{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006670947191114298,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026683788764457196,
      "grad_norm": 21.58336067199707,
      "learning_rate": 5e-05,
      "loss": 99.4744,
      "step": 1
    },
    {
      "epoch": 0.00026683788764457196,
      "eval_loss": 3.534377336502075,
      "eval_runtime": 2.9302,
      "eval_samples_per_second": 17.063,
      "eval_steps_per_second": 4.437,
      "step": 1
    },
    {
      "epoch": 0.0005336757752891439,
      "grad_norm": 22.419708251953125,
      "learning_rate": 0.0001,
      "loss": 103.3411,
      "step": 2
    },
    {
      "epoch": 0.0008005136629337158,
      "grad_norm": 44.11233901977539,
      "learning_rate": 9.990365154573717e-05,
      "loss": 101.998,
      "step": 3
    },
    {
      "epoch": 0.0010673515505782878,
      "grad_norm": 39.20323181152344,
      "learning_rate": 9.961501876182148e-05,
      "loss": 102.6876,
      "step": 4
    },
    {
      "epoch": 0.0013341894382228596,
      "grad_norm": 33.18415069580078,
      "learning_rate": 9.913533761814537e-05,
      "loss": 98.8706,
      "step": 5
    },
    {
      "epoch": 0.0016010273258674317,
      "grad_norm": 35.75772476196289,
      "learning_rate": 9.846666218300807e-05,
      "loss": 96.6055,
      "step": 6
    },
    {
      "epoch": 0.0018678652135120035,
      "grad_norm": 36.51875686645508,
      "learning_rate": 9.761185582727977e-05,
      "loss": 94.8261,
      "step": 7
    },
    {
      "epoch": 0.0021347031011565757,
      "grad_norm": 33.68272018432617,
      "learning_rate": 9.657457896300791e-05,
      "loss": 93.3615,
      "step": 8
    },
    {
      "epoch": 0.0024015409888011475,
      "grad_norm": 30.13109016418457,
      "learning_rate": 9.535927336897098e-05,
      "loss": 91.072,
      "step": 9
    },
    {
      "epoch": 0.0026683788764457193,
      "grad_norm": 32.036537170410156,
      "learning_rate": 9.397114317029975e-05,
      "loss": 93.589,
      "step": 10
    },
    {
      "epoch": 0.002935216764090291,
      "grad_norm": 24.110986709594727,
      "learning_rate": 9.241613255361455e-05,
      "loss": 93.6183,
      "step": 11
    },
    {
      "epoch": 0.0032020546517348633,
      "grad_norm": 59.20383071899414,
      "learning_rate": 9.070090031310558e-05,
      "loss": 100.723,
      "step": 12
    },
    {
      "epoch": 0.003468892539379435,
      "grad_norm": 72.5294418334961,
      "learning_rate": 8.883279133655399e-05,
      "loss": 103.4235,
      "step": 13
    },
    {
      "epoch": 0.003735730427024007,
      "grad_norm": 49.615962982177734,
      "learning_rate": 8.681980515339464e-05,
      "loss": 90.5619,
      "step": 14
    },
    {
      "epoch": 0.004002568314668579,
      "grad_norm": 36.85390853881836,
      "learning_rate": 8.467056167950311e-05,
      "loss": 90.9424,
      "step": 15
    },
    {
      "epoch": 0.004269406202313151,
      "grad_norm": 28.41231346130371,
      "learning_rate": 8.239426430539243e-05,
      "loss": 86.9021,
      "step": 16
    },
    {
      "epoch": 0.004536244089957723,
      "grad_norm": 19.181047439575195,
      "learning_rate": 8.000066048588211e-05,
      "loss": 87.2284,
      "step": 17
    },
    {
      "epoch": 0.004803081977602295,
      "grad_norm": 16.206340789794922,
      "learning_rate": 7.75e-05,
      "loss": 87.68,
      "step": 18
    },
    {
      "epoch": 0.005069919865246866,
      "grad_norm": 13.560489654541016,
      "learning_rate": 7.490299105985507e-05,
      "loss": 87.0709,
      "step": 19
    },
    {
      "epoch": 0.0053367577528914386,
      "grad_norm": 13.36911678314209,
      "learning_rate": 7.222075445642904e-05,
      "loss": 87.0837,
      "step": 20
    },
    {
      "epoch": 0.005603595640536011,
      "grad_norm": 13.232701301574707,
      "learning_rate": 6.946477593864228e-05,
      "loss": 87.4922,
      "step": 21
    },
    {
      "epoch": 0.005870433528180582,
      "grad_norm": 19.99480438232422,
      "learning_rate": 6.664685702961344e-05,
      "loss": 86.7508,
      "step": 22
    },
    {
      "epoch": 0.006137271415825154,
      "grad_norm": 19.568359375,
      "learning_rate": 6.377906449072578e-05,
      "loss": 88.3357,
      "step": 23
    },
    {
      "epoch": 0.006404109303469727,
      "grad_norm": 30.02350425720215,
      "learning_rate": 6.087367864990233e-05,
      "loss": 89.6037,
      "step": 24
    },
    {
      "epoch": 0.006670947191114298,
      "grad_norm": 132.76075744628906,
      "learning_rate": 5.794314081535644e-05,
      "loss": 106.9513,
      "step": 25
    },
    {
      "epoch": 0.006670947191114298,
      "eval_loss": 2.699881076812744,
      "eval_runtime": 2.969,
      "eval_samples_per_second": 16.841,
      "eval_steps_per_second": 4.379,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.629578157719552e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}