{
  "best_metric": 0.5330188679245284,
  "best_model_checkpoint": "./Validated_Balanced_Raw_Data_model_boost3_outputs/checkpoint-640",
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 2400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.625,
      "grad_norm": 9.254714012145996,
      "learning_rate": 4.166666666666667e-06,
      "loss": 1.3971,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3584905660377358,
      "eval_loss": 1.33805251121521,
      "eval_runtime": 1.7498,
      "eval_samples_per_second": 121.156,
      "eval_steps_per_second": 15.43,
      "step": 80
    },
    {
      "epoch": 1.25,
      "grad_norm": 14.49019718170166,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.3703,
      "step": 100
    },
    {
      "epoch": 1.875,
      "grad_norm": 21.699073791503906,
      "learning_rate": 1.25e-05,
      "loss": 1.3299,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3632075471698113,
      "eval_loss": 1.2896820306777954,
      "eval_runtime": 1.7829,
      "eval_samples_per_second": 118.907,
      "eval_steps_per_second": 15.144,
      "step": 160
    },
    {
      "epoch": 2.5,
      "grad_norm": 16.081377029418945,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.2782,
      "step": 200
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.41509433962264153,
      "eval_loss": 1.242042064666748,
      "eval_runtime": 1.747,
      "eval_samples_per_second": 121.352,
      "eval_steps_per_second": 15.455,
      "step": 240
    },
    {
      "epoch": 3.125,
      "grad_norm": 15.81972885131836,
      "learning_rate": 1.9998942319271076e-05,
      "loss": 1.2726,
      "step": 250
    },
    {
      "epoch": 3.75,
      "grad_norm": 18.504892349243164,
      "learning_rate": 1.9961946980917457e-05,
      "loss": 1.2151,
      "step": 300
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4481132075471698,
      "eval_loss": 1.1927876472473145,
      "eval_runtime": 1.7636,
      "eval_samples_per_second": 120.21,
      "eval_steps_per_second": 15.31,
      "step": 320
    },
    {
      "epoch": 4.375,
      "grad_norm": 20.491024017333984,
      "learning_rate": 1.9872291131173743e-05,
      "loss": 1.2169,
      "step": 350
    },
    {
      "epoch": 5.0,
      "grad_norm": 34.251853942871094,
      "learning_rate": 1.973044870579824e-05,
      "loss": 1.1703,
      "step": 400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.49056603773584906,
      "eval_loss": 1.1870641708374023,
      "eval_runtime": 1.7599,
      "eval_samples_per_second": 120.459,
      "eval_steps_per_second": 15.341,
      "step": 400
    },
    {
      "epoch": 5.625,
      "grad_norm": 28.04253387451172,
      "learning_rate": 1.953716950748227e-05,
      "loss": 1.1426,
      "step": 450
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4811320754716981,
      "eval_loss": 1.1826516389846802,
      "eval_runtime": 1.7574,
      "eval_samples_per_second": 120.632,
      "eval_steps_per_second": 15.363,
      "step": 480
    },
    {
      "epoch": 6.25,
      "grad_norm": 16.116487503051758,
      "learning_rate": 1.9293475242268224e-05,
      "loss": 1.0804,
      "step": 500
    },
    {
      "epoch": 6.875,
      "grad_norm": 28.656999588012695,
      "learning_rate": 1.900065411864121e-05,
      "loss": 1.0837,
      "step": 550
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5094339622641509,
      "eval_loss": 1.1960099935531616,
      "eval_runtime": 1.7695,
      "eval_samples_per_second": 119.81,
      "eval_steps_per_second": 15.259,
      "step": 560
    },
    {
      "epoch": 7.5,
      "grad_norm": 22.728029251098633,
      "learning_rate": 1.866025403784439e-05,
      "loss": 1.0393,
      "step": 600
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5330188679245284,
      "eval_loss": 1.14811110496521,
      "eval_runtime": 1.7557,
      "eval_samples_per_second": 120.75,
      "eval_steps_per_second": 15.378,
      "step": 640
    },
    {
      "epoch": 8.125,
      "grad_norm": 19.9659423828125,
      "learning_rate": 1.8274074411415104e-05,
      "loss": 1.0651,
      "step": 650
    },
    {
      "epoch": 8.75,
      "grad_norm": 28.96779441833496,
      "learning_rate": 1.784415664919576e-05,
      "loss": 1.0316,
      "step": 700
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.4858490566037736,
      "eval_loss": 1.193508267402649,
      "eval_runtime": 1.7697,
      "eval_samples_per_second": 119.791,
      "eval_steps_per_second": 15.256,
      "step": 720
    },
    {
      "epoch": 9.375,
      "grad_norm": 30.056156158447266,
      "learning_rate": 1.737277336810124e-05,
      "loss": 0.9686,
      "step": 750
    },
    {
      "epoch": 10.0,
      "grad_norm": 32.97503662109375,
      "learning_rate": 1.686241637868734e-05,
      "loss": 1.0134,
      "step": 800
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.49528301886792453,
      "eval_loss": 1.1633896827697754,
      "eval_runtime": 1.7634,
      "eval_samples_per_second": 120.222,
      "eval_steps_per_second": 15.311,
      "step": 800
    },
    {
      "epoch": 10.625,
      "grad_norm": 28.390098571777344,
      "learning_rate": 1.6315783513024977e-05,
      "loss": 0.9324,
      "step": 850
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.5094339622641509,
      "eval_loss": 1.186944603919983,
      "eval_runtime": 1.754,
      "eval_samples_per_second": 120.867,
      "eval_steps_per_second": 15.393,
      "step": 880
    },
    {
      "epoch": 11.25,
      "grad_norm": 23.563337326049805,
      "learning_rate": 1.573576436351046e-05,
      "loss": 0.9198,
      "step": 900
    },
    {
      "epoch": 11.875,
      "grad_norm": 24.938207626342773,
      "learning_rate": 1.5125425007998653e-05,
      "loss": 0.9005,
      "step": 950
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.4858490566037736,
      "eval_loss": 1.1605207920074463,
      "eval_runtime": 1.7703,
      "eval_samples_per_second": 119.756,
      "eval_steps_per_second": 15.252,
      "step": 960
    },
    {
      "epoch": 12.5,
      "grad_norm": 32.487918853759766,
      "learning_rate": 1.4487991802004625e-05,
      "loss": 0.8917,
      "step": 1000
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.4858490566037736,
      "eval_loss": 1.1817502975463867,
      "eval_runtime": 1.7512,
      "eval_samples_per_second": 121.057,
      "eval_steps_per_second": 15.418,
      "step": 1040
    },
    {
      "epoch": 13.125,
      "grad_norm": 36.24566650390625,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.8511,
      "step": 1050
    },
    {
      "epoch": 13.75,
      "grad_norm": 26.883840560913086,
      "learning_rate": 1.3145447561516138e-05,
      "loss": 0.8299,
      "step": 1100
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.49528301886792453,
      "eval_loss": 1.1758817434310913,
      "eval_runtime": 1.7567,
      "eval_samples_per_second": 120.677,
      "eval_steps_per_second": 15.369,
      "step": 1120
    },
    {
      "epoch": 14.375,
      "grad_norm": 14.808755874633789,
      "learning_rate": 1.2447433439543239e-05,
      "loss": 0.8226,
      "step": 1150
    },
    {
      "epoch": 15.0,
      "grad_norm": 36.614830017089844,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.8314,
      "step": 1200
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.49056603773584906,
      "eval_loss": 1.1998909711837769,
      "eval_runtime": 1.7606,
      "eval_samples_per_second": 120.41,
      "eval_steps_per_second": 15.335,
      "step": 1200
    },
    {
      "epoch": 15.625,
      "grad_norm": 23.366907119750977,
      "learning_rate": 1.101635078182802e-05,
      "loss": 0.7891,
      "step": 1250
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.211138129234314,
      "eval_runtime": 1.7578,
      "eval_samples_per_second": 120.609,
      "eval_steps_per_second": 15.361,
      "step": 1280
    },
    {
      "epoch": 16.25,
      "grad_norm": 59.76485824584961,
      "learning_rate": 1.0290847187431115e-05,
      "loss": 0.7951,
      "step": 1300
    },
    {
      "epoch": 16.875,
      "grad_norm": 23.98710823059082,
      "learning_rate": 9.563806126346643e-06,
      "loss": 0.7702,
      "step": 1350
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.47641509433962265,
      "eval_loss": 1.2256454229354858,
      "eval_runtime": 1.7428,
      "eval_samples_per_second": 121.644,
      "eval_steps_per_second": 15.492,
      "step": 1360
    },
    {
      "epoch": 17.5,
      "grad_norm": 25.670591354370117,
      "learning_rate": 8.839070858747697e-06,
      "loss": 0.7821,
      "step": 1400
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.5141509433962265,
      "eval_loss": 1.2363587617874146,
      "eval_runtime": 1.7717,
      "eval_samples_per_second": 119.661,
      "eval_steps_per_second": 15.24,
      "step": 1440
    },
    {
      "epoch": 18.125,
      "grad_norm": 21.44415855407715,
      "learning_rate": 8.120472455998882e-06,
      "loss": 0.7652,
      "step": 1450
    },
    {
      "epoch": 18.75,
      "grad_norm": 23.542112350463867,
      "learning_rate": 7.411809548974792e-06,
      "loss": 0.7391,
      "step": 1500
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.5047169811320755,
      "eval_loss": 1.2107821702957153,
      "eval_runtime": 1.7876,
      "eval_samples_per_second": 118.592,
      "eval_steps_per_second": 15.104,
      "step": 1520
    },
    {
      "epoch": 19.375,
      "grad_norm": 24.51466941833496,
      "learning_rate": 6.716828247864391e-06,
      "loss": 0.7376,
      "step": 1550
    },
    {
      "epoch": 20.0,
      "grad_norm": 6.434605598449707,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.7078,
      "step": 1600
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1987223625183105,
      "eval_runtime": 1.7661,
      "eval_samples_per_second": 120.04,
      "eval_steps_per_second": 15.288,
      "step": 1600
    },
    {
      "epoch": 20.625,
      "grad_norm": 32.26969528198242,
      "learning_rate": 5.382513867649663e-06,
      "loss": 0.7245,
      "step": 1650
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.5283018867924528,
      "eval_loss": 1.1981287002563477,
      "eval_runtime": 1.764,
      "eval_samples_per_second": 120.182,
      "eval_steps_per_second": 15.306,
      "step": 1680
    },
    {
      "epoch": 21.25,
      "grad_norm": 9.658790588378906,
      "learning_rate": 4.7502341966544e-06,
      "loss": 0.665,
      "step": 1700
    },
    {
      "epoch": 21.875,
      "grad_norm": 34.42046356201172,
      "learning_rate": 4.1457056623005954e-06,
      "loss": 0.6822,
      "step": 1750
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.5283018867924528,
      "eval_loss": 1.2109999656677246,
      "eval_runtime": 1.7742,
      "eval_samples_per_second": 119.493,
      "eval_steps_per_second": 15.218,
      "step": 1760
    },
    {
      "epoch": 22.5,
      "grad_norm": 43.55071258544922,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 0.6646,
      "step": 1800
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.5330188679245284,
      "eval_loss": 1.2094640731811523,
      "eval_runtime": 1.7778,
      "eval_samples_per_second": 119.246,
      "eval_steps_per_second": 15.187,
      "step": 1840
    },
    {
      "epoch": 23.125,
      "grad_norm": 29.20159149169922,
      "learning_rate": 3.032520967893453e-06,
      "loss": 0.7001,
      "step": 1850
    },
    {
      "epoch": 23.75,
      "grad_norm": 32.616455078125,
      "learning_rate": 2.529749287590042e-06,
      "loss": 0.7144,
      "step": 1900
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.5235849056603774,
      "eval_loss": 1.207753300666809,
      "eval_runtime": 1.7715,
      "eval_samples_per_second": 119.672,
      "eval_steps_per_second": 15.241,
      "step": 1920
    },
    {
      "epoch": 24.375,
      "grad_norm": 33.372379302978516,
      "learning_rate": 2.0664665970876496e-06,
      "loss": 0.6557,
      "step": 1950
    },
    {
      "epoch": 25.0,
      "grad_norm": 58.919925689697266,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 0.7271,
      "step": 2000
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.5188679245283019,
      "eval_loss": 1.2087972164154053,
      "eval_runtime": 1.7765,
      "eval_samples_per_second": 119.336,
      "eval_steps_per_second": 15.198,
      "step": 2000
    },
    {
      "epoch": 25.625,
      "grad_norm": 15.74853515625,
      "learning_rate": 1.2679424522780426e-06,
      "loss": 0.6563,
      "step": 2050
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.5094339622641509,
      "eval_loss": 1.213672399520874,
      "eval_runtime": 1.7824,
      "eval_samples_per_second": 118.944,
      "eval_steps_per_second": 15.148,
      "step": 2080
    },
    {
      "epoch": 26.25,
      "grad_norm": 21.280942916870117,
      "learning_rate": 9.369221296335007e-07,
      "loss": 0.681,
      "step": 2100
    },
    {
      "epoch": 26.875,
      "grad_norm": 5.9813551902771,
      "learning_rate": 6.538107465101162e-07,
      "loss": 0.6447,
      "step": 2150
    },
    {
      "epoch": 27.0,
      "eval_accuracy": 0.5235849056603774,
      "eval_loss": 1.2157169580459595,
      "eval_runtime": 1.7502,
      "eval_samples_per_second": 121.129,
      "eval_steps_per_second": 15.427,
      "step": 2160
    },
    {
      "epoch": 27.5,
      "grad_norm": 26.834735870361328,
      "learning_rate": 4.2010487684511105e-07,
      "loss": 0.6763,
      "step": 2200
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.5188679245283019,
      "eval_loss": 1.213538408279419,
      "eval_runtime": 1.7574,
      "eval_samples_per_second": 120.634,
      "eval_steps_per_second": 15.364,
      "step": 2240
    },
    {
      "epoch": 28.125,
      "grad_norm": 11.102935791015625,
      "learning_rate": 2.370399288006664e-07,
      "loss": 0.6374,
      "step": 2250
    },
    {
      "epoch": 28.75,
      "grad_norm": 33.84370803833008,
      "learning_rate": 1.055836141905553e-07,
      "loss": 0.6434,
      "step": 2300
    },
    {
      "epoch": 29.0,
      "eval_accuracy": 0.5188679245283019,
      "eval_loss": 1.21367347240448,
      "eval_runtime": 1.7659,
      "eval_samples_per_second": 120.05,
      "eval_steps_per_second": 15.289,
      "step": 2320
    },
    {
      "epoch": 29.375,
      "grad_norm": 20.113740921020508,
      "learning_rate": 2.643083299427751e-08,
      "loss": 0.6788,
      "step": 2350
    },
    {
      "epoch": 30.0,
      "grad_norm": 13.546830177307129,
      "learning_rate": 0.0,
      "loss": 0.6727,
      "step": 2400
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.5188679245283019,
      "eval_loss": 1.213610291481018,
      "eval_runtime": 3.0973,
      "eval_samples_per_second": 68.446,
      "eval_steps_per_second": 8.717,
      "step": 2400
    },
    {
      "epoch": 30.0,
      "step": 2400,
      "total_flos": 1.5090549662800282e+18,
      "train_loss": 0.886767615477244,
      "train_runtime": 578.1499,
      "train_samples_per_second": 33.002,
      "train_steps_per_second": 4.151
    }
  ],
  "logging_steps": 50,
  "max_steps": 2400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5090549662800282e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}