{
  "best_metric": 4.17286491394043,
  "best_model_checkpoint": "/home/bel3/portfolio-repo-TheBguy87/final project/model_folder/checkpoint-19500",
  "epoch": 2.9601518026565463,
  "global_step": 19500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.873488183796367e-05,
      "loss": 6.5463,
      "step": 500
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.21852576647097194,
      "eval_loss": 5.444242477416992,
      "eval_runtime": 27.5824,
      "eval_samples_per_second": 51.12,
      "eval_steps_per_second": 6.417,
      "step": 500
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.746976367592733e-05,
      "loss": 5.7814,
      "step": 1000
    },
    {
      "epoch": 0.15,
      "eval_accuracy": 0.2316206575897628,
      "eval_loss": 5.191591739654541,
      "eval_runtime": 27.5501,
      "eval_samples_per_second": 51.179,
      "eval_steps_per_second": 6.425,
      "step": 1000
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.6204645513891e-05,
      "loss": 5.5475,
      "step": 1500
    },
    {
      "epoch": 0.23,
      "eval_accuracy": 0.2393984816310669,
      "eval_loss": 5.062835693359375,
      "eval_runtime": 27.5707,
      "eval_samples_per_second": 51.141,
      "eval_steps_per_second": 6.42,
      "step": 1500
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.493952735185467e-05,
      "loss": 5.4202,
      "step": 2000
    },
    {
      "epoch": 0.3,
      "eval_accuracy": 0.24114169130199442,
      "eval_loss": 4.970830917358398,
      "eval_runtime": 27.5621,
      "eval_samples_per_second": 51.157,
      "eval_steps_per_second": 6.422,
      "step": 2000
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.367440918981833e-05,
      "loss": 5.3562,
      "step": 2500
    },
    {
      "epoch": 0.38,
      "eval_accuracy": 0.24209795839058446,
      "eval_loss": 4.920139312744141,
      "eval_runtime": 27.5764,
      "eval_samples_per_second": 51.131,
      "eval_steps_per_second": 6.419,
      "step": 2500
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.240929102778199e-05,
      "loss": 5.2881,
      "step": 3000
    },
    {
      "epoch": 0.46,
      "eval_accuracy": 0.2436371459105356,
      "eval_loss": 4.872959136962891,
      "eval_runtime": 27.5692,
      "eval_samples_per_second": 51.144,
      "eval_steps_per_second": 6.42,
      "step": 3000
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.114417286574566e-05,
      "loss": 5.2296,
      "step": 3500
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.2506516217679144,
      "eval_loss": 4.810730457305908,
      "eval_runtime": 27.5767,
      "eval_samples_per_second": 51.13,
      "eval_steps_per_second": 6.418,
      "step": 3500
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.987905470370933e-05,
      "loss": 5.1578,
      "step": 4000
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.2533899598895227,
      "eval_loss": 4.767050743103027,
      "eval_runtime": 27.5725,
      "eval_samples_per_second": 51.138,
      "eval_steps_per_second": 6.419,
      "step": 4000
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.8613936541672994e-05,
      "loss": 5.0779,
      "step": 4500
    },
    {
      "epoch": 0.68,
      "eval_accuracy": 0.2565418939362396,
      "eval_loss": 4.725719451904297,
      "eval_runtime": 27.5923,
      "eval_samples_per_second": 51.101,
      "eval_steps_per_second": 6.415,
      "step": 4500
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.734881837963666e-05,
      "loss": 5.0276,
      "step": 5000
    },
    {
      "epoch": 0.76,
      "eval_accuracy": 0.2623502796630165,
      "eval_loss": 4.667919635772705,
      "eval_runtime": 27.5734,
      "eval_samples_per_second": 51.136,
      "eval_steps_per_second": 6.419,
      "step": 5000
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.6083700217600326e-05,
      "loss": 5.0059,
      "step": 5500
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.2663904734146646,
      "eval_loss": 4.631860256195068,
      "eval_runtime": 27.5657,
      "eval_samples_per_second": 51.151,
      "eval_steps_per_second": 6.421,
      "step": 5500
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.481858205556399e-05,
      "loss": 4.9264,
      "step": 6000
    },
    {
      "epoch": 0.91,
      "eval_accuracy": 0.2692717658325353,
      "eval_loss": 4.584375858306885,
      "eval_runtime": 27.5605,
      "eval_samples_per_second": 51.16,
      "eval_steps_per_second": 6.422,
      "step": 6000
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.355346389352766e-05,
      "loss": 4.9049,
      "step": 6500
    },
    {
      "epoch": 0.99,
      "eval_accuracy": 0.272461173335554,
      "eval_loss": 4.553061485290527,
      "eval_runtime": 27.5742,
      "eval_samples_per_second": 51.135,
      "eval_steps_per_second": 6.419,
      "step": 6500
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.228834573149132e-05,
      "loss": 4.8232,
      "step": 7000
    },
    {
      "epoch": 1.06,
      "eval_accuracy": 0.27501491998723127,
      "eval_loss": 4.517702579498291,
      "eval_runtime": 27.5623,
      "eval_samples_per_second": 51.157,
      "eval_steps_per_second": 6.422,
      "step": 7000
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.102322756945499e-05,
      "loss": 4.751,
      "step": 7500
    },
    {
      "epoch": 1.14,
      "eval_accuracy": 0.2793854353166507,
      "eval_loss": 4.4822540283203125,
      "eval_runtime": 27.5718,
      "eval_samples_per_second": 51.139,
      "eval_steps_per_second": 6.42,
      "step": 7500
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.9758109407418657e-05,
      "loss": 4.7553,
      "step": 8000
    },
    {
      "epoch": 1.21,
      "eval_accuracy": 0.2807802806345505,
      "eval_loss": 4.459610939025879,
      "eval_runtime": 27.5709,
      "eval_samples_per_second": 51.141,
      "eval_steps_per_second": 6.42,
      "step": 8000
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.8495521481706393e-05,
      "loss": 4.7213,
      "step": 8500
    },
    {
      "epoch": 1.29,
      "eval_accuracy": 0.28297872340425534,
      "eval_loss": 4.435904026031494,
      "eval_runtime": 27.5742,
      "eval_samples_per_second": 51.135,
      "eval_steps_per_second": 6.419,
      "step": 8500
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.7230403319670056e-05,
      "loss": 4.6646,
      "step": 9000
    },
    {
      "epoch": 1.37,
      "eval_accuracy": 0.28641656604349697,
      "eval_loss": 4.399264335632324,
      "eval_runtime": 27.5882,
      "eval_samples_per_second": 51.109,
      "eval_steps_per_second": 6.416,
      "step": 9000
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.597034563028187e-05,
      "loss": 4.6709,
      "step": 9500
    },
    {
      "epoch": 1.44,
      "eval_accuracy": 0.2876531901014559,
      "eval_loss": 4.388927936553955,
      "eval_runtime": 27.5803,
      "eval_samples_per_second": 51.123,
      "eval_steps_per_second": 6.418,
      "step": 9500
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.4705227468245535e-05,
      "loss": 4.6179,
      "step": 10000
    },
    {
      "epoch": 1.52,
      "eval_accuracy": 0.2888079277178665,
      "eval_loss": 4.365257263183594,
      "eval_runtime": 27.58,
      "eval_samples_per_second": 51.124,
      "eval_steps_per_second": 6.418,
      "step": 10000
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.34401093062092e-05,
      "loss": 4.5984,
      "step": 10500
    },
    {
      "epoch": 1.59,
      "eval_accuracy": 0.2886746887621268,
      "eval_loss": 4.34913444519043,
      "eval_runtime": 27.5823,
      "eval_samples_per_second": 51.12,
      "eval_steps_per_second": 6.417,
      "step": 10500
    },
    {
      "epoch": 1.67,
      "learning_rate": 2.2174991144172867e-05,
      "loss": 4.5868,
      "step": 11000
    },
    {
      "epoch": 1.67,
      "eval_accuracy": 0.29093697519812356,
      "eval_loss": 4.338951587677002,
      "eval_runtime": 27.5873,
      "eval_samples_per_second": 51.11,
      "eval_steps_per_second": 6.416,
      "step": 11000
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.0909872982136533e-05,
      "loss": 4.5543,
      "step": 11500
    },
    {
      "epoch": 1.75,
      "eval_accuracy": 0.29370307143551094,
      "eval_loss": 4.3105316162109375,
      "eval_runtime": 27.5819,
      "eval_samples_per_second": 51.12,
      "eval_steps_per_second": 6.417,
      "step": 11500
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.9644754820100196e-05,
      "loss": 4.5493,
      "step": 12000
    },
    {
      "epoch": 1.82,
      "eval_accuracy": 0.29424019097583654,
      "eval_loss": 4.301023483276367,
      "eval_runtime": 27.5881,
      "eval_samples_per_second": 51.109,
      "eval_steps_per_second": 6.416,
      "step": 12000
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.8379636658063865e-05,
      "loss": 4.5038,
      "step": 12500
    },
    {
      "epoch": 1.9,
      "eval_accuracy": 0.294011186520659,
      "eval_loss": 4.281564235687256,
      "eval_runtime": 27.5889,
      "eval_samples_per_second": 51.107,
      "eval_steps_per_second": 6.416,
      "step": 12500
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.7114518496027528e-05,
      "loss": 4.4836,
      "step": 13000
    },
    {
      "epoch": 1.97,
      "eval_accuracy": 0.29663155265020613,
      "eval_loss": 4.268117427825928,
      "eval_runtime": 27.5869,
      "eval_samples_per_second": 51.111,
      "eval_steps_per_second": 6.416,
      "step": 13000
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.5849400333991198e-05,
      "loss": 4.4394,
      "step": 13500
    },
    {
      "epoch": 2.05,
      "eval_accuracy": 0.2960416926899002,
      "eval_loss": 4.262997150421143,
      "eval_runtime": 27.5906,
      "eval_samples_per_second": 51.104,
      "eval_steps_per_second": 6.415,
      "step": 13500
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.458428217195486e-05,
      "loss": 4.4429,
      "step": 14000
    },
    {
      "epoch": 2.13,
      "eval_accuracy": 0.2994989660101872,
      "eval_loss": 4.247574329376221,
      "eval_runtime": 27.5874,
      "eval_samples_per_second": 51.11,
      "eval_steps_per_second": 6.416,
      "step": 14000
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.3319164009918528e-05,
      "loss": 4.4404,
      "step": 14500
    },
    {
      "epoch": 2.2,
      "eval_accuracy": 0.3004260870772092,
      "eval_loss": 4.236292839050293,
      "eval_runtime": 27.9352,
      "eval_samples_per_second": 50.474,
      "eval_steps_per_second": 6.336,
      "step": 14500
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.2054045847882193e-05,
      "loss": 4.4148,
      "step": 15000
    },
    {
      "epoch": 2.28,
      "eval_accuracy": 0.3013920695063219,
      "eval_loss": 4.226977825164795,
      "eval_runtime": 27.9368,
      "eval_samples_per_second": 50.471,
      "eval_steps_per_second": 6.336,
      "step": 15000
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.0791457922169932e-05,
      "loss": 4.3944,
      "step": 15500
    },
    {
      "epoch": 2.35,
      "eval_accuracy": 0.3011366948411542,
      "eval_loss": 4.218454360961914,
      "eval_runtime": 28.163,
      "eval_samples_per_second": 50.066,
      "eval_steps_per_second": 6.285,
      "step": 15500
    },
    {
      "epoch": 2.43,
      "learning_rate": 9.526339760133597e-06,
      "loss": 4.3942,
      "step": 16000
    },
    {
      "epoch": 2.43,
      "eval_accuracy": 0.3020194029229296,
      "eval_loss": 4.213292121887207,
      "eval_runtime": 28.5992,
      "eval_samples_per_second": 49.302,
      "eval_steps_per_second": 6.189,
      "step": 16000
    },
    {
      "epoch": 2.5,
      "learning_rate": 8.261221598097263e-06,
      "loss": 4.3789,
      "step": 16500
    },
    {
      "epoch": 2.5,
      "eval_accuracy": 0.3029826095404644,
      "eval_loss": 4.205790996551514,
      "eval_runtime": 28.126,
      "eval_samples_per_second": 50.131,
      "eval_steps_per_second": 6.293,
      "step": 16500
    },
    {
      "epoch": 2.58,
      "learning_rate": 6.996103436060929e-06,
      "loss": 4.3444,
      "step": 17000
    },
    {
      "epoch": 2.58,
      "eval_accuracy": 0.3037764916517467,
      "eval_loss": 4.199104309082031,
      "eval_runtime": 27.8045,
      "eval_samples_per_second": 50.711,
      "eval_steps_per_second": 6.366,
      "step": 17000
    },
    {
      "epoch": 2.66,
      "learning_rate": 5.733515510348667e-06,
      "loss": 4.3503,
      "step": 17500
    },
    {
      "epoch": 2.66,
      "eval_accuracy": 0.3041026495121511,
      "eval_loss": 4.189632415771484,
      "eval_runtime": 28.554,
      "eval_samples_per_second": 49.38,
      "eval_steps_per_second": 6.199,
      "step": 17500
    },
    {
      "epoch": 2.73,
      "learning_rate": 4.468397348312332e-06,
      "loss": 4.3445,
      "step": 18000
    },
    {
      "epoch": 2.73,
      "eval_accuracy": 0.30501727942707246,
      "eval_loss": 4.184421062469482,
      "eval_runtime": 27.7494,
      "eval_samples_per_second": 50.812,
      "eval_steps_per_second": 6.379,
      "step": 18000
    },
    {
      "epoch": 2.81,
      "learning_rate": 3.2058094226000707e-06,
      "loss": 4.3081,
      "step": 18500
    },
    {
      "epoch": 2.81,
      "eval_accuracy": 0.3053531526279996,
      "eval_loss": 4.178225994110107,
      "eval_runtime": 27.5642,
      "eval_samples_per_second": 51.153,
      "eval_steps_per_second": 6.421,
      "step": 18500
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.9406912605637364e-06,
      "loss": 4.3215,
      "step": 19000
    },
    {
      "epoch": 2.88,
      "eval_accuracy": 0.30591109075515954,
      "eval_loss": 4.176368713378906,
      "eval_runtime": 27.554,
      "eval_samples_per_second": 51.172,
      "eval_steps_per_second": 6.424,
      "step": 19000
    },
    {
      "epoch": 2.96,
      "learning_rate": 6.755730985274025e-07,
      "loss": 4.3413,
      "step": 19500
    },
    {
      "epoch": 2.96,
      "eval_accuracy": 0.30599714091407476,
      "eval_loss": 4.17286491394043,
      "eval_runtime": 27.9537,
      "eval_samples_per_second": 50.441,
      "eval_steps_per_second": 6.332,
      "step": 19500
    }
  ],
  "max_steps": 19761,
  "num_train_epochs": 3,
  "total_flos": 2.0380255911936e+16,
  "trial_name": null,
  "trial_params": null
}