{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17543859649122806,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035087719298245615,
      "grad_norm": 0.7496554255485535,
      "learning_rate": 1e-05,
      "loss": 1.8772,
      "step": 1
    },
    {
      "epoch": 0.0035087719298245615,
      "eval_loss": 0.9869150519371033,
      "eval_runtime": 31.2293,
      "eval_samples_per_second": 7.685,
      "eval_steps_per_second": 0.961,
      "step": 1
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 0.3732806444168091,
      "learning_rate": 2e-05,
      "loss": 1.8954,
      "step": 2
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 6.0862202644348145,
      "learning_rate": 3e-05,
      "loss": 2.0455,
      "step": 3
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 1.8033699989318848,
      "learning_rate": 4e-05,
      "loss": 1.9689,
      "step": 4
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 0.37004604935646057,
      "learning_rate": 5e-05,
      "loss": 1.9241,
      "step": 5
    },
    {
      "epoch": 0.017543859649122806,
      "eval_loss": 0.9838016629219055,
      "eval_runtime": 31.2446,
      "eval_samples_per_second": 7.681,
      "eval_steps_per_second": 0.96,
      "step": 5
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.40420740842819214,
      "learning_rate": 6e-05,
      "loss": 1.9061,
      "step": 6
    },
    {
      "epoch": 0.02456140350877193,
      "grad_norm": 0.5557041168212891,
      "learning_rate": 7e-05,
      "loss": 1.7744,
      "step": 7
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.698968231678009,
      "learning_rate": 8e-05,
      "loss": 1.9837,
      "step": 8
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 1.37924325466156,
      "learning_rate": 9e-05,
      "loss": 1.955,
      "step": 9
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 1.4337043762207031,
      "learning_rate": 0.0001,
      "loss": 2.0508,
      "step": 10
    },
    {
      "epoch": 0.03508771929824561,
      "eval_loss": 0.9311538934707642,
      "eval_runtime": 31.2491,
      "eval_samples_per_second": 7.68,
      "eval_steps_per_second": 0.96,
      "step": 10
    },
    {
      "epoch": 0.03859649122807018,
      "grad_norm": 0.903275191783905,
      "learning_rate": 9.98458666866564e-05,
      "loss": 1.9695,
      "step": 11
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 2.571420907974243,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.9592,
      "step": 12
    },
    {
      "epoch": 0.0456140350877193,
      "grad_norm": 1.3438692092895508,
      "learning_rate": 9.861849601988383e-05,
      "loss": 1.8812,
      "step": 13
    },
    {
      "epoch": 0.04912280701754386,
      "grad_norm": 2.062797784805298,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6613,
      "step": 14
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.9957493543624878,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7236,
      "step": 15
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 0.8261042833328247,
      "eval_runtime": 31.2289,
      "eval_samples_per_second": 7.685,
      "eval_steps_per_second": 0.961,
      "step": 15
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 1.7317227125167847,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.5554,
      "step": 16
    },
    {
      "epoch": 0.05964912280701754,
      "grad_norm": 1.8487741947174072,
      "learning_rate": 9.263200821770461e-05,
      "loss": 1.6309,
      "step": 17
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.1379690170288086,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5855,
      "step": 18
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 2.604675769805908,
      "learning_rate": 8.802029828000156e-05,
      "loss": 1.745,
      "step": 19
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 0.8052600026130676,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6313,
      "step": 20
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 0.7486318945884705,
      "eval_runtime": 31.2421,
      "eval_samples_per_second": 7.682,
      "eval_steps_per_second": 0.96,
      "step": 20
    },
    {
      "epoch": 0.07368421052631578,
      "grad_norm": 0.8813563585281372,
      "learning_rate": 8.247240241650918e-05,
      "loss": 1.4947,
      "step": 21
    },
    {
      "epoch": 0.07719298245614035,
      "grad_norm": 0.6191761493682861,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5739,
      "step": 22
    },
    {
      "epoch": 0.08070175438596491,
      "grad_norm": 0.5111678838729858,
      "learning_rate": 7.612492823579745e-05,
      "loss": 1.5768,
      "step": 23
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.48126235604286194,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.2844,
      "step": 24
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 0.532455325126648,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3513,
      "step": 25
    },
    {
      "epoch": 0.08771929824561403,
      "eval_loss": 0.6969746947288513,
      "eval_runtime": 31.2545,
      "eval_samples_per_second": 7.679,
      "eval_steps_per_second": 0.96,
      "step": 25
    },
    {
      "epoch": 0.0912280701754386,
      "grad_norm": 0.45586490631103516,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5082,
      "step": 26
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 0.4288429021835327,
      "learning_rate": 6.167226819279528e-05,
      "loss": 1.5074,
      "step": 27
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 0.516413688659668,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.465,
      "step": 28
    },
    {
      "epoch": 0.10175438596491228,
      "grad_norm": 0.3883686363697052,
      "learning_rate": 5.392295478639225e-05,
      "loss": 1.3339,
      "step": 29
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.36578112840652466,
      "learning_rate": 5e-05,
      "loss": 1.3305,
      "step": 30
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 0.6721018552780151,
      "eval_runtime": 31.2422,
      "eval_samples_per_second": 7.682,
      "eval_steps_per_second": 0.96,
      "step": 30
    },
    {
      "epoch": 0.10877192982456141,
      "grad_norm": 0.4528491795063019,
      "learning_rate": 4.607704521360776e-05,
      "loss": 1.3054,
      "step": 31
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 0.5230074524879456,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.3127,
      "step": 32
    },
    {
      "epoch": 0.11578947368421053,
      "grad_norm": 0.3589520752429962,
      "learning_rate": 3.832773180720475e-05,
      "loss": 1.2494,
      "step": 33
    },
    {
      "epoch": 0.11929824561403508,
      "grad_norm": 0.37137433886528015,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2876,
      "step": 34
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 0.3676114082336426,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4231,
      "step": 35
    },
    {
      "epoch": 0.12280701754385964,
      "eval_loss": 0.6568540930747986,
      "eval_runtime": 31.2484,
      "eval_samples_per_second": 7.68,
      "eval_steps_per_second": 0.96,
      "step": 35
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.3397810459136963,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.2656,
      "step": 36
    },
    {
      "epoch": 0.12982456140350876,
      "grad_norm": 0.4330822229385376,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 1.3152,
      "step": 37
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.34625089168548584,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.242,
      "step": 38
    },
    {
      "epoch": 0.1368421052631579,
      "grad_norm": 0.4436972141265869,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 1.3669,
      "step": 39
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 0.42210957407951355,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2976,
      "step": 40
    },
    {
      "epoch": 0.14035087719298245,
      "eval_loss": 0.6486957669258118,
      "eval_runtime": 31.2372,
      "eval_samples_per_second": 7.683,
      "eval_steps_per_second": 0.96,
      "step": 40
    },
    {
      "epoch": 0.14385964912280702,
      "grad_norm": 0.3705242872238159,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 1.3034,
      "step": 41
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 0.355709046125412,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3322,
      "step": 42
    },
    {
      "epoch": 0.15087719298245614,
      "grad_norm": 0.5023610591888428,
      "learning_rate": 7.367991782295391e-06,
      "loss": 1.272,
      "step": 43
    },
    {
      "epoch": 0.1543859649122807,
      "grad_norm": 0.3548582196235657,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.303,
      "step": 44
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.3477891683578491,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.2135,
      "step": 45
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 0.6452772617340088,
      "eval_runtime": 31.2471,
      "eval_samples_per_second": 7.681,
      "eval_steps_per_second": 0.96,
      "step": 45
    },
    {
      "epoch": 0.16140350877192983,
      "grad_norm": 0.38610097765922546,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.4095,
      "step": 46
    },
    {
      "epoch": 0.1649122807017544,
      "grad_norm": 0.37943798303604126,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 1.4977,
      "step": 47
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.41213494539260864,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.4309,
      "step": 48
    },
    {
      "epoch": 0.17192982456140352,
      "grad_norm": 0.39028602838516235,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 1.2883,
      "step": 49
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 0.38540011644363403,
      "learning_rate": 0.0,
      "loss": 1.3353,
      "step": 50
    },
    {
      "epoch": 0.17543859649122806,
      "eval_loss": 0.6447344422340393,
      "eval_runtime": 31.2434,
      "eval_samples_per_second": 7.682,
      "eval_steps_per_second": 0.96,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3980161506410496e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}