{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2074688796680498,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004149377593360996,
      "grad_norm": 338.5560302734375,
      "learning_rate": 1e-05,
      "loss": 17.0013,
      "step": 1
    },
    {
      "epoch": 0.004149377593360996,
      "eval_loss": 9.25258731842041,
      "eval_runtime": 1.5969,
      "eval_samples_per_second": 127.121,
      "eval_steps_per_second": 16.281,
      "step": 1
    },
    {
      "epoch": 0.008298755186721992,
      "grad_norm": 331.52618408203125,
      "learning_rate": 2e-05,
      "loss": 19.1385,
      "step": 2
    },
    {
      "epoch": 0.012448132780082987,
      "grad_norm": 303.5635681152344,
      "learning_rate": 3e-05,
      "loss": 19.0005,
      "step": 3
    },
    {
      "epoch": 0.016597510373443983,
      "grad_norm": 300.59466552734375,
      "learning_rate": 4e-05,
      "loss": 16.9304,
      "step": 4
    },
    {
      "epoch": 0.02074688796680498,
      "grad_norm": 407.1070556640625,
      "learning_rate": 5e-05,
      "loss": 18.6078,
      "step": 5
    },
    {
      "epoch": 0.02074688796680498,
      "eval_loss": 9.233301162719727,
      "eval_runtime": 0.9583,
      "eval_samples_per_second": 211.841,
      "eval_steps_per_second": 27.132,
      "step": 5
    },
    {
      "epoch": 0.024896265560165973,
      "grad_norm": 373.00823974609375,
      "learning_rate": 6e-05,
      "loss": 19.3471,
      "step": 6
    },
    {
      "epoch": 0.029045643153526972,
      "grad_norm": 259.5892639160156,
      "learning_rate": 7e-05,
      "loss": 16.4007,
      "step": 7
    },
    {
      "epoch": 0.03319502074688797,
      "grad_norm": 393.28839111328125,
      "learning_rate": 8e-05,
      "loss": 19.6328,
      "step": 8
    },
    {
      "epoch": 0.03734439834024896,
      "grad_norm": 375.2423095703125,
      "learning_rate": 9e-05,
      "loss": 18.0652,
      "step": 9
    },
    {
      "epoch": 0.04149377593360996,
      "grad_norm": 345.50579833984375,
      "learning_rate": 0.0001,
      "loss": 17.987,
      "step": 10
    },
    {
      "epoch": 0.04149377593360996,
      "eval_loss": 9.172691345214844,
      "eval_runtime": 0.9643,
      "eval_samples_per_second": 210.506,
      "eval_steps_per_second": 26.961,
      "step": 10
    },
    {
      "epoch": 0.04564315352697095,
      "grad_norm": 382.5924377441406,
      "learning_rate": 9.98458666866564e-05,
      "loss": 18.3821,
      "step": 11
    },
    {
      "epoch": 0.04979253112033195,
      "grad_norm": 306.32659912109375,
      "learning_rate": 9.938441702975689e-05,
      "loss": 17.1481,
      "step": 12
    },
    {
      "epoch": 0.05394190871369295,
      "grad_norm": 363.08477783203125,
      "learning_rate": 9.861849601988383e-05,
      "loss": 18.247,
      "step": 13
    },
    {
      "epoch": 0.058091286307053944,
      "grad_norm": 325.3434753417969,
      "learning_rate": 9.755282581475769e-05,
      "loss": 17.548,
      "step": 14
    },
    {
      "epoch": 0.06224066390041494,
      "grad_norm": 334.68536376953125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 16.0464,
      "step": 15
    },
    {
      "epoch": 0.06224066390041494,
      "eval_loss": 9.124333381652832,
      "eval_runtime": 0.9624,
      "eval_samples_per_second": 210.921,
      "eval_steps_per_second": 27.015,
      "step": 15
    },
    {
      "epoch": 0.06639004149377593,
      "grad_norm": 351.066162109375,
      "learning_rate": 9.45503262094184e-05,
      "loss": 17.6445,
      "step": 16
    },
    {
      "epoch": 0.07053941908713693,
      "grad_norm": 305.76983642578125,
      "learning_rate": 9.263200821770461e-05,
      "loss": 18.055,
      "step": 17
    },
    {
      "epoch": 0.07468879668049792,
      "grad_norm": 317.046875,
      "learning_rate": 9.045084971874738e-05,
      "loss": 17.8924,
      "step": 18
    },
    {
      "epoch": 0.07883817427385892,
      "grad_norm": 317.98626708984375,
      "learning_rate": 8.802029828000156e-05,
      "loss": 17.5157,
      "step": 19
    },
    {
      "epoch": 0.08298755186721991,
      "grad_norm": 366.4814147949219,
      "learning_rate": 8.535533905932738e-05,
      "loss": 17.1351,
      "step": 20
    },
    {
      "epoch": 0.08298755186721991,
      "eval_loss": 9.038752555847168,
      "eval_runtime": 0.9692,
      "eval_samples_per_second": 209.46,
      "eval_steps_per_second": 26.827,
      "step": 20
    },
    {
      "epoch": 0.08713692946058091,
      "grad_norm": 374.20440673828125,
      "learning_rate": 8.247240241650918e-05,
      "loss": 19.3179,
      "step": 21
    },
    {
      "epoch": 0.0912863070539419,
      "grad_norm": 405.3846740722656,
      "learning_rate": 7.938926261462366e-05,
      "loss": 17.5574,
      "step": 22
    },
    {
      "epoch": 0.0954356846473029,
      "grad_norm": 358.61627197265625,
      "learning_rate": 7.612492823579745e-05,
      "loss": 18.0677,
      "step": 23
    },
    {
      "epoch": 0.0995850622406639,
      "grad_norm": 303.9383850097656,
      "learning_rate": 7.269952498697734e-05,
      "loss": 17.038,
      "step": 24
    },
    {
      "epoch": 0.1037344398340249,
      "grad_norm": 315.915771484375,
      "learning_rate": 6.91341716182545e-05,
      "loss": 16.808,
      "step": 25
    },
    {
      "epoch": 0.1037344398340249,
      "eval_loss": 9.01609992980957,
      "eval_runtime": 0.962,
      "eval_samples_per_second": 211.022,
      "eval_steps_per_second": 27.027,
      "step": 25
    },
    {
      "epoch": 0.1078838174273859,
      "grad_norm": 454.03875732421875,
      "learning_rate": 6.545084971874738e-05,
      "loss": 19.4273,
      "step": 26
    },
    {
      "epoch": 0.11203319502074689,
      "grad_norm": 303.0365905761719,
      "learning_rate": 6.167226819279528e-05,
      "loss": 16.5833,
      "step": 27
    },
    {
      "epoch": 0.11618257261410789,
      "grad_norm": 367.9336242675781,
      "learning_rate": 5.782172325201155e-05,
      "loss": 17.764,
      "step": 28
    },
    {
      "epoch": 0.12033195020746888,
      "grad_norm": 384.99786376953125,
      "learning_rate": 5.392295478639225e-05,
      "loss": 17.9249,
      "step": 29
    },
    {
      "epoch": 0.12448132780082988,
      "grad_norm": 371.46588134765625,
      "learning_rate": 5e-05,
      "loss": 17.159,
      "step": 30
    },
    {
      "epoch": 0.12448132780082988,
      "eval_loss": 9.035653114318848,
      "eval_runtime": 0.9953,
      "eval_samples_per_second": 203.95,
      "eval_steps_per_second": 26.122,
      "step": 30
    },
    {
      "epoch": 0.12863070539419086,
      "grad_norm": 358.5752868652344,
      "learning_rate": 4.607704521360776e-05,
      "loss": 17.0919,
      "step": 31
    },
    {
      "epoch": 0.13278008298755187,
      "grad_norm": 370.85333251953125,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 17.5422,
      "step": 32
    },
    {
      "epoch": 0.13692946058091288,
      "grad_norm": 346.4546813964844,
      "learning_rate": 3.832773180720475e-05,
      "loss": 17.4615,
      "step": 33
    },
    {
      "epoch": 0.14107883817427386,
      "grad_norm": 365.4295959472656,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 17.6874,
      "step": 34
    },
    {
      "epoch": 0.14522821576763487,
      "grad_norm": 308.52362060546875,
      "learning_rate": 3.086582838174551e-05,
      "loss": 17.1988,
      "step": 35
    },
    {
      "epoch": 0.14522821576763487,
      "eval_loss": 9.000443458557129,
      "eval_runtime": 0.9787,
      "eval_samples_per_second": 207.409,
      "eval_steps_per_second": 26.565,
      "step": 35
    },
    {
      "epoch": 0.14937759336099585,
      "grad_norm": 384.09722900390625,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 17.3598,
      "step": 36
    },
    {
      "epoch": 0.15352697095435686,
      "grad_norm": 401.5643310546875,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 16.8225,
      "step": 37
    },
    {
      "epoch": 0.15767634854771784,
      "grad_norm": 367.50152587890625,
      "learning_rate": 2.061073738537635e-05,
      "loss": 19.3024,
      "step": 38
    },
    {
      "epoch": 0.16182572614107885,
      "grad_norm": 454.1186218261719,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 19.1394,
      "step": 39
    },
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 510.416015625,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 17.7996,
      "step": 40
    },
    {
      "epoch": 0.16597510373443983,
      "eval_loss": 8.98484992980957,
      "eval_runtime": 0.9687,
      "eval_samples_per_second": 209.557,
      "eval_steps_per_second": 26.84,
      "step": 40
    },
    {
      "epoch": 0.17012448132780084,
      "grad_norm": 440.44830322265625,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 19.084,
      "step": 41
    },
    {
      "epoch": 0.17427385892116182,
      "grad_norm": 377.33685302734375,
      "learning_rate": 9.549150281252633e-06,
      "loss": 16.044,
      "step": 42
    },
    {
      "epoch": 0.17842323651452283,
      "grad_norm": 399.070556640625,
      "learning_rate": 7.367991782295391e-06,
      "loss": 18.5397,
      "step": 43
    },
    {
      "epoch": 0.1825726141078838,
      "grad_norm": 389.1490478515625,
      "learning_rate": 5.449673790581611e-06,
      "loss": 16.4042,
      "step": 44
    },
    {
      "epoch": 0.18672199170124482,
      "grad_norm": 483.7464904785156,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 19.0675,
      "step": 45
    },
    {
      "epoch": 0.18672199170124482,
      "eval_loss": 8.964590072631836,
      "eval_runtime": 0.9679,
      "eval_samples_per_second": 209.736,
      "eval_steps_per_second": 26.863,
      "step": 45
    },
    {
      "epoch": 0.1908713692946058,
      "grad_norm": 331.3105773925781,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 16.7486,
      "step": 46
    },
    {
      "epoch": 0.1950207468879668,
      "grad_norm": 455.8272705078125,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 18.3657,
      "step": 47
    },
    {
      "epoch": 0.1991701244813278,
      "grad_norm": 365.6001281738281,
      "learning_rate": 6.15582970243117e-07,
      "loss": 17.0653,
      "step": 48
    },
    {
      "epoch": 0.2033195020746888,
      "grad_norm": 483.4586181640625,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 17.313,
      "step": 49
    },
    {
      "epoch": 0.2074688796680498,
      "grad_norm": 367.5295104980469,
      "learning_rate": 0.0,
      "loss": 17.9008,
      "step": 50
    },
    {
      "epoch": 0.2074688796680498,
      "eval_loss": 8.979755401611328,
      "eval_runtime": 0.9676,
      "eval_samples_per_second": 209.789,
      "eval_steps_per_second": 26.869,
      "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": 223432251801600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}