{
  "best_metric": 1.7454155683517456,
  "best_model_checkpoint": "/data/user_data/gonilude/java_and_text_gpt2/checkpoint-200",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 243,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_accuracy": 0.19444444444444445,
      "eval_loss": 11.014116287231445,
      "eval_runtime": 1.1343,
      "eval_samples_per_second": 63.475,
      "eval_steps_per_second": 7.934,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.2768,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.576,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 143.01515197753906,
      "learning_rate": 5e-06,
      "loss": 8.9704,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 357.00616455078125,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 9.5348,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 436.4880676269531,
      "learning_rate": 1.9991958847061786e-05,
      "loss": 6.4758,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.30864197530864196,
      "grad_norm": 103.16507720947266,
      "learning_rate": 1.9942865292219837e-05,
      "loss": 5.3616,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 69.18275451660156,
      "learning_rate": 1.984936448731556e-05,
      "loss": 5.0694,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.43209876543209874,
      "grad_norm": 85.65583038330078,
      "learning_rate": 1.971187402964132e-05,
      "loss": 4.3876,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 23.326828002929688,
      "learning_rate": 1.9531007984957408e-05,
      "loss": 3.5825,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 31.104318618774414,
      "learning_rate": 1.9307574144925288e-05,
      "loss": 1.927,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 46.547122955322266,
      "learning_rate": 1.9042570419313927e-05,
      "loss": 2.3634,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6172839506172839,
      "eval_accuracy": 0.19444444444444445,
      "eval_loss": 2.2269253730773926,
      "eval_runtime": 0.9055,
      "eval_samples_per_second": 79.514,
      "eval_steps_per_second": 9.939,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6790123456790124,
      "grad_norm": 14.275629043579102,
      "learning_rate": 1.8737180379092536e-05,
      "loss": 1.8308,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 20.500579833984375,
      "learning_rate": 1.8392767970315314e-05,
      "loss": 1.7708,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8024691358024691,
      "grad_norm": 28.264705657958984,
      "learning_rate": 1.8010871422407238e-05,
      "loss": 1.8038,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 17.55794334411621,
      "learning_rate": 1.759319637805806e-05,
      "loss": 1.7319,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 16.978687286376953,
      "learning_rate": 1.714160827540801e-05,
      "loss": 1.6038,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 18.727697372436523,
      "learning_rate": 1.66581240165482e-05,
      "loss": 1.8072,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0493827160493827,
      "grad_norm": 18.814525604248047,
      "learning_rate": 1.6144902959546286e-05,
      "loss": 1.8374,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 10.187082290649414,
      "learning_rate": 1.560423727422915e-05,
      "loss": 1.5674,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.1728395061728394,
      "grad_norm": 24.2742862701416,
      "learning_rate": 1.5038541704796004e-05,
      "loss": 2.266,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 22.410181045532227,
      "learning_rate": 1.4450342784984632e-05,
      "loss": 2.003,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2345679012345678,
      "eval_accuracy": 0.2222222222222222,
      "eval_loss": 1.7976888418197632,
      "eval_runtime": 0.9046,
      "eval_samples_per_second": 79.592,
      "eval_steps_per_second": 9.949,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 21.811655044555664,
      "learning_rate": 1.3842267553958373e-05,
      "loss": 1.9257,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3580246913580247,
      "grad_norm": 13.7644624710083,
      "learning_rate": 1.3217031823311488e-05,
      "loss": 1.7949,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4197530864197532,
      "grad_norm": 16.891998291015625,
      "learning_rate": 1.2577428047595343e-05,
      "loss": 1.7427,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 9.613762855529785,
      "learning_rate": 1.1926312852538456e-05,
      "loss": 1.5529,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5432098765432098,
      "grad_norm": 11.176910400390625,
      "learning_rate": 1.126659427666257e-05,
      "loss": 1.7114,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6049382716049383,
      "grad_norm": 15.059788703918457,
      "learning_rate": 1.0601218783276673e-05,
      "loss": 1.7562,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 14.87260913848877,
      "learning_rate": 9.93315810085658e-06,
      "loss": 1.6257,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 11.261963844299316,
      "learning_rate": 9.265395950584181e-06,
      "loss": 1.574,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.7901234567901234,
      "grad_norm": 12.72499942779541,
      "learning_rate": 8.600914720324315e-06,
      "loss": 1.5799,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 13.012349128723145,
      "learning_rate": 7.942682144556605e-06,
      "loss": 1.7323,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8518518518518519,
      "eval_accuracy": 0.2222222222222222,
      "eval_loss": 1.7827554941177368,
      "eval_runtime": 0.9045,
      "eval_samples_per_second": 79.598,
      "eval_steps_per_second": 9.95,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9135802469135803,
      "grad_norm": 14.650065422058105,
      "learning_rate": 7.293638049752813e-06,
      "loss": 1.6441,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 14.940625190734863,
      "learning_rate": 6.656681224398182e-06,
      "loss": 1.8624,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 18.302019119262695,
      "learning_rate": 6.034656472298374e-06,
      "loss": 1.624,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.0987654320987654,
      "grad_norm": 13.879521369934082,
      "learning_rate": 5.430341906995064e-06,
      "loss": 1.5843,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.1604938271604937,
      "grad_norm": 11.124442100524902,
      "learning_rate": 4.846436544036505e-06,
      "loss": 1.6387,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 9.738484382629395,
      "learning_rate": 4.285548246518837e-06,
      "loss": 1.5708,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.2839506172839505,
      "grad_norm": 12.508370399475098,
      "learning_rate": 3.750182077736486e-06,
      "loss": 1.6141,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.3456790123456788,
      "grad_norm": 12.206828117370605,
      "learning_rate": 3.2427291129613502e-06,
      "loss": 1.6146,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 7.063596248626709,
      "learning_rate": 2.765455760320196e-06,
      "loss": 1.6204,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 12.646849632263184,
      "learning_rate": 2.3204936384657873e-06,
      "loss": 1.6991,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.4691358024691357,
      "eval_accuracy": 0.18055555555555555,
      "eval_loss": 1.7454155683517456,
      "eval_runtime": 0.9063,
      "eval_samples_per_second": 79.445,
      "eval_steps_per_second": 9.931,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5308641975308643,
      "grad_norm": 14.059237480163574,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 1.5533,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 18.09408950805664,
      "learning_rate": 1.5352991369226865e-06,
      "loss": 1.684,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.6543209876543212,
      "grad_norm": 15.153328895568848,
      "learning_rate": 1.198573626486751e-06,
      "loss": 1.5512,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 18.182266235351562,
      "learning_rate": 9.011574228136866e-07,
      "loss": 1.632,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 18.970129013061523,
      "learning_rate": 6.443788588679823e-07,
      "loss": 1.5761,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.8395061728395063,
      "grad_norm": 16.78023910522461,
      "learning_rate": 4.2938477005015853e-07,
      "loss": 1.6058,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9012345679012346,
      "grad_norm": 14.316130638122559,
      "learning_rate": 2.571353721514913e-07,
      "loss": 1.645,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 17.25787925720215,
      "learning_rate": 1.2839997279717075e-07,
      "loss": 1.6722,
      "num_input_tokens_seen": 1966080,
      "step": 240
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1990656,
      "step": 243,
      "total_flos": 3610849453277184.0,
      "train_loss": 2.4843275125134627,
      "train_runtime": 181.6704,
      "train_samples_per_second": 10.651,
      "train_steps_per_second": 1.338
    }
  ],
  "logging_steps": 5,
  "max_steps": 243,
  "num_input_tokens_seen": 1990656,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3610849453277184.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}