{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007692307692307693,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 3.1196,
      "step": 1
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": Infinity,
      "learning_rate": 6.153846153846155e-06,
      "loss": 3.1223,
      "step": 5
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": Infinity,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 3.1246,
      "step": 10
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": Infinity,
      "learning_rate": 1.9996395276708856e-05,
      "loss": 3.1264,
      "step": 15
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 35.01002883911133,
      "learning_rate": 1.9870502626379127e-05,
      "loss": 2.9981,
      "step": 20
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 11.861149787902832,
      "learning_rate": 1.9566964208274254e-05,
      "loss": 2.531,
      "step": 25
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 7.360829830169678,
      "learning_rate": 1.909124299802724e-05,
      "loss": 2.2014,
      "step": 30
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 6.061845779418945,
      "learning_rate": 1.845190085543795e-05,
      "loss": 2.0137,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 3.25486421585083,
      "learning_rate": 1.766044443118978e-05,
      "loss": 1.8515,
      "step": 40
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 2.8577518463134766,
      "learning_rate": 1.67311180742757e-05,
      "loss": 1.7909,
      "step": 45
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.2024171352386475,
      "learning_rate": 1.568064746731156e-05,
      "loss": 1.7104,
      "step": 50
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 2.368898630142212,
      "learning_rate": 1.4527938603696376e-05,
      "loss": 1.6393,
      "step": 55
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 2.016225814819336,
      "learning_rate": 1.3293737524320798e-05,
      "loss": 1.5979,
      "step": 60
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.3714423179626465,
      "learning_rate": 1.2000256937760446e-05,
      "loss": 1.5492,
      "step": 65
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 2.853393793106079,
      "learning_rate": 1.0670776443910024e-05,
      "loss": 1.5275,
      "step": 70
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 1.7769665718078613,
      "learning_rate": 9.329223556089976e-06,
      "loss": 1.4923,
      "step": 75
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.4375193119049072,
      "learning_rate": 7.999743062239557e-06,
      "loss": 1.4681,
      "step": 80
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 2.583644151687622,
      "learning_rate": 6.706262475679205e-06,
      "loss": 1.4528,
      "step": 85
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 2.249284267425537,
      "learning_rate": 5.47206139630363e-06,
      "loss": 1.4174,
      "step": 90
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 2.0346739292144775,
      "learning_rate": 4.319352532688444e-06,
      "loss": 1.4044,
      "step": 95
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.5525047779083252,
      "learning_rate": 3.2688819257242963e-06,
      "loss": 1.3924,
      "step": 100
    },
    {
      "epoch": 0.7692307692307693,
      "eval_loss": 1.3881758451461792,
      "eval_runtime": 2.1626,
      "eval_samples_per_second": 413.847,
      "eval_steps_per_second": 3.237,
      "step": 100
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 1.5717474222183228,
      "learning_rate": 2.339555568810221e-06,
      "loss": 1.38,
      "step": 105
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 1.4260509014129639,
      "learning_rate": 1.5480991445620541e-06,
      "loss": 1.375,
      "step": 110
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 1.3539237976074219,
      "learning_rate": 9.08757001972762e-07,
      "loss": 1.3491,
      "step": 115
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 1.4586122035980225,
      "learning_rate": 4.3303579172574884e-07,
      "loss": 1.3533,
      "step": 120
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 1.3738539218902588,
      "learning_rate": 1.2949737362087156e-07,
      "loss": 1.3503,
      "step": 125
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.3676426410675049,
      "learning_rate": 3.6047232911462506e-09,
      "loss": 1.3395,
      "step": 130
    },
    {
      "epoch": 1.0,
      "step": 130,
      "total_flos": 4.795466914988032e+16,
      "train_loss": 1.8291644793290358,
      "train_runtime": 404.0129,
      "train_samples_per_second": 40.88,
      "train_steps_per_second": 0.322
    }
  ],
  "logging_steps": 5,
  "max_steps": 130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.795466914988032e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}