{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.114864864864865,
  "eval_steps": 25,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.2711382210254669,
      "learning_rate": 5e-05,
      "loss": 10.3715,
      "step": 1
    },
    {
      "epoch": 0.07207207207207207,
      "eval_loss": NaN,
      "eval_runtime": 0.1178,
      "eval_samples_per_second": 424.357,
      "eval_steps_per_second": 110.333,
      "step": 1
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.2941465973854065,
      "learning_rate": 0.0001,
      "loss": 10.38,
      "step": 2
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.3280700147151947,
      "learning_rate": 9.986128001799077e-05,
      "loss": 10.3772,
      "step": 3
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.25955256819725037,
      "learning_rate": 9.94459753267812e-05,
      "loss": 10.3711,
      "step": 4
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.2933718264102936,
      "learning_rate": 9.875664641789545e-05,
      "loss": 10.3694,
      "step": 5
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.31816211342811584,
      "learning_rate": 9.779754323328192e-05,
      "loss": 10.3844,
      "step": 6
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.2863932251930237,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3909,
      "step": 7
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.30337193608283997,
      "learning_rate": 9.509529358847655e-05,
      "loss": 10.3832,
      "step": 8
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.32591405510902405,
      "learning_rate": 9.336880739593416e-05,
      "loss": 10.3792,
      "step": 9
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.3342682719230652,
      "learning_rate": 9.140576474687264e-05,
      "loss": 10.3605,
      "step": 10
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.28455355763435364,
      "learning_rate": 8.921826845200139e-05,
      "loss": 10.3871,
      "step": 11
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.3578994870185852,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3726,
      "step": 12
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.44790729880332947,
      "learning_rate": 8.422516217485826e-05,
      "loss": 10.3726,
      "step": 13
    },
    {
      "epoch": 1.0382882882882882,
      "grad_norm": 0.5053783059120178,
      "learning_rate": 8.14503363531613e-05,
      "loss": 15.9327,
      "step": 14
    },
    {
      "epoch": 1.1103603603603605,
      "grad_norm": 0.3347855806350708,
      "learning_rate": 7.85124354122177e-05,
      "loss": 9.7211,
      "step": 15
    },
    {
      "epoch": 1.1824324324324325,
      "grad_norm": 0.4577144384384155,
      "learning_rate": 7.542957248827961e-05,
      "loss": 12.3588,
      "step": 16
    },
    {
      "epoch": 1.2545045045045045,
      "grad_norm": 0.30119043588638306,
      "learning_rate": 7.222075445642904e-05,
      "loss": 8.5601,
      "step": 17
    },
    {
      "epoch": 1.3265765765765765,
      "grad_norm": 0.3898301124572754,
      "learning_rate": 6.890576474687263e-05,
      "loss": 10.5993,
      "step": 18
    },
    {
      "epoch": 1.3986486486486487,
      "grad_norm": 0.4105931222438812,
      "learning_rate": 6.550504137351576e-05,
      "loss": 10.4923,
      "step": 19
    },
    {
      "epoch": 1.4707207207207207,
      "grad_norm": 0.40458568930625916,
      "learning_rate": 6.203955092681039e-05,
      "loss": 9.1102,
      "step": 20
    },
    {
      "epoch": 1.5427927927927927,
      "grad_norm": 0.37626734375953674,
      "learning_rate": 5.8530659307753036e-05,
      "loss": 11.0968,
      "step": 21
    },
    {
      "epoch": 1.614864864864865,
      "grad_norm": 0.425431489944458,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.8335,
      "step": 22
    },
    {
      "epoch": 1.686936936936937,
      "grad_norm": 0.47822538018226624,
      "learning_rate": 5.1469340692246995e-05,
      "loss": 10.5662,
      "step": 23
    },
    {
      "epoch": 1.759009009009009,
      "grad_norm": 0.3679811656475067,
      "learning_rate": 4.7960449073189606e-05,
      "loss": 10.1607,
      "step": 24
    },
    {
      "epoch": 1.8310810810810811,
      "grad_norm": 0.4539155662059784,
      "learning_rate": 4.4494958626484276e-05,
      "loss": 10.2808,
      "step": 25
    },
    {
      "epoch": 1.8310810810810811,
      "eval_loss": NaN,
      "eval_runtime": 0.1008,
      "eval_samples_per_second": 495.946,
      "eval_steps_per_second": 128.946,
      "step": 25
    },
    {
      "epoch": 1.9031531531531531,
      "grad_norm": 0.6299550533294678,
      "learning_rate": 4.109423525312738e-05,
      "loss": 11.6034,
      "step": 26
    },
    {
      "epoch": 2.0045045045045047,
      "grad_norm": 0.6582178473472595,
      "learning_rate": 3.777924554357096e-05,
      "loss": 14.3429,
      "step": 27
    },
    {
      "epoch": 2.0765765765765765,
      "grad_norm": 0.4390489459037781,
      "learning_rate": 3.45704275117204e-05,
      "loss": 10.5127,
      "step": 28
    },
    {
      "epoch": 2.1486486486486487,
      "grad_norm": 0.5411266088485718,
      "learning_rate": 3.1487564587782306e-05,
      "loss": 10.7874,
      "step": 29
    },
    {
      "epoch": 2.220720720720721,
      "grad_norm": 0.5138953328132629,
      "learning_rate": 2.854966364683872e-05,
      "loss": 9.6413,
      "step": 30
    },
    {
      "epoch": 2.2927927927927927,
      "grad_norm": 0.45892640948295593,
      "learning_rate": 2.577483782514174e-05,
      "loss": 10.7246,
      "step": 31
    },
    {
      "epoch": 2.364864864864865,
      "grad_norm": 0.4862615466117859,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.6531,
      "step": 32
    },
    {
      "epoch": 2.436936936936937,
      "grad_norm": 0.5631672143936157,
      "learning_rate": 2.0781731547998614e-05,
      "loss": 10.1699,
      "step": 33
    },
    {
      "epoch": 2.509009009009009,
      "grad_norm": 0.4757976233959198,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 9.9347,
      "step": 34
    },
    {
      "epoch": 2.581081081081081,
      "grad_norm": 0.5032361745834351,
      "learning_rate": 1.6631192604065855e-05,
      "loss": 10.5629,
      "step": 35
    },
    {
      "epoch": 2.653153153153153,
      "grad_norm": 0.514340877532959,
      "learning_rate": 1.490470641152345e-05,
      "loss": 10.7382,
      "step": 36
    },
    {
      "epoch": 2.725225225225225,
      "grad_norm": 0.501396656036377,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.0469,
      "step": 37
    },
    {
      "epoch": 2.7972972972972974,
      "grad_norm": 0.4644583463668823,
      "learning_rate": 1.2202456766718093e-05,
      "loss": 10.503,
      "step": 38
    },
    {
      "epoch": 2.8693693693693696,
      "grad_norm": 0.5667948126792908,
      "learning_rate": 1.1243353582104556e-05,
      "loss": 10.8346,
      "step": 39
    },
    {
      "epoch": 2.9414414414414414,
      "grad_norm": 0.5867165923118591,
      "learning_rate": 1.0554024673218807e-05,
      "loss": 10.6693,
      "step": 40
    },
    {
      "epoch": 3.0427927927927927,
      "grad_norm": 0.7453739047050476,
      "learning_rate": 1.0138719982009242e-05,
      "loss": 15.0657,
      "step": 41
    },
    {
      "epoch": 3.114864864864865,
      "grad_norm": 0.5105739235877991,
      "learning_rate": 1e-05,
      "loss": 10.1017,
      "step": 42
    }
  ],
  "logging_steps": 1,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 35925170061312.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}