{
  "best_metric": 1.6996692419052124,
  "best_model_checkpoint": "./python_and_text_gpt2/checkpoint-200",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 237,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_accuracy": 0.11267605633802817,
      "eval_loss": 8.402484893798828,
      "eval_runtime": 1.1735,
      "eval_samples_per_second": 60.505,
      "eval_steps_per_second": 7.67,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.7173,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 7.5816,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": Infinity,
      "learning_rate": 2.5e-06,
      "loss": 10.0592,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 218.1217803955078,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 8.4642,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 296.8869934082031,
      "learning_rate": 1.999153201672344e-05,
      "loss": 5.9304,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 61.51658630371094,
      "learning_rate": 1.9939835156657616e-05,
      "loss": 2.9233,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 40.88030242919922,
      "learning_rate": 1.9841388720031727e-05,
      "loss": 2.6465,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 47.827491760253906,
      "learning_rate": 1.9696655725512933e-05,
      "loss": 2.7127,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 20.431304931640625,
      "learning_rate": 1.9506316889240027e-05,
      "loss": 1.8677,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 29.551557540893555,
      "learning_rate": 1.9271267423242028e-05,
      "loss": 2.5811,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 16.11282730102539,
      "learning_rate": 1.8992612825027978e-05,
      "loss": 2.0715,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "eval_accuracy": 0.18309859154929578,
      "eval_loss": 1.8793463706970215,
      "eval_runtime": 0.9197,
      "eval_samples_per_second": 77.198,
      "eval_steps_per_second": 9.786,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 19.049699783325195,
      "learning_rate": 1.8671663678150605e-05,
      "loss": 1.8742,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 13.142491340637207,
      "learning_rate": 1.8309929488198012e-05,
      "loss": 1.5956,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 19.499195098876953,
      "learning_rate": 1.790911158320442e-05,
      "loss": 2.0677,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 13.254035949707031,
      "learning_rate": 1.7471095111871076e-05,
      "loss": 1.8408,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 13.480071067810059,
      "learning_rate": 1.6997940177231722e-05,
      "loss": 1.73,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 16.7222900390625,
      "learning_rate": 1.6491872147463307e-05,
      "loss": 2.0164,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 20.90951156616211,
      "learning_rate": 1.5955271189412596e-05,
      "loss": 1.838,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 20.80415153503418,
      "learning_rate": 1.5390661074065257e-05,
      "loss": 1.8573,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 21.243846893310547,
      "learning_rate": 1.4800697306608043e-05,
      "loss": 1.7605,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 9.170429229736328,
      "learning_rate": 1.4188154636911524e-05,
      "loss": 1.5544,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2658227848101267,
      "eval_accuracy": 0.2112676056338028,
      "eval_loss": 1.8253157138824463,
      "eval_runtime": 0.9307,
      "eval_samples_per_second": 76.288,
      "eval_steps_per_second": 9.67,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 11.778152465820312,
      "learning_rate": 1.3555914009174665e-05,
      "loss": 1.7069,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 17.081523895263672,
      "learning_rate": 1.2906949012110456e-05,
      "loss": 1.5678,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 8.573921203613281,
      "learning_rate": 1.2244311893400761e-05,
      "loss": 1.6158,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 10.426651000976562,
      "learning_rate": 1.1571119204198038e-05,
      "loss": 1.6879,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 16.324264526367188,
      "learning_rate": 1.0890537141191417e-05,
      "loss": 1.7929,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 16.601455688476562,
      "learning_rate": 1.0205766655177217e-05,
      "loss": 1.5528,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 8.302882194519043,
      "learning_rate": 9.520028396172002e-06,
      "loss": 1.6046,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 14.192557334899902,
      "learning_rate": 8.836547565875227e-06,
      "loss": 1.5904,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 11.201437950134277,
      "learning_rate": 8.158538748724139e-06,
      "loss": 1.5891,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 20.305402755737305,
      "learning_rate": 7.489190792884338e-06,
      "loss": 1.7587,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8987341772151898,
      "eval_accuracy": 0.14084507042253522,
      "eval_loss": 1.7602745294570923,
      "eval_runtime": 0.938,
      "eval_samples_per_second": 75.69,
      "eval_steps_per_second": 9.594,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 8.459460258483887,
      "learning_rate": 6.831651812284652e-06,
      "loss": 1.5431,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 15.566550254821777,
      "learning_rate": 6.18901438023543e-06,
      "loss": 1.6141,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 15.074378967285156,
      "learning_rate": 5.564300984268556e-06,
      "loss": 1.7919,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 12.48886775970459,
      "learning_rate": 4.960449810608705e-06,
      "loss": 1.6343,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 13.26822566986084,
      "learning_rate": 4.380300925135138e-06,
      "loss": 1.6183,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 16.358903884887695,
      "learning_rate": 3.826582915828468e-06,
      "loss": 1.5828,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 9.541784286499023,
      "learning_rate": 3.3019000595263573e-06,
      "loss": 1.6376,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 7.097592830657959,
      "learning_rate": 2.8087200733462427e-06,
      "loss": 1.6106,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 21.592899322509766,
      "learning_rate": 2.3493625083831217e-06,
      "loss": 1.571,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 11.701766967773438,
      "learning_rate": 1.9259878402699704e-06,
      "loss": 1.5982,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5316455696202533,
      "eval_accuracy": 0.2112676056338028,
      "eval_loss": 1.6996692419052124,
      "eval_runtime": 0.9416,
      "eval_samples_per_second": 75.403,
      "eval_steps_per_second": 9.558,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 11.591459274291992,
      "learning_rate": 1.5405873079105083e-06,
      "loss": 1.5655,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 7.575652599334717,
      "learning_rate": 1.1949735481754565e-06,
      "loss": 1.5902,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 11.8199462890625,
      "learning_rate": 8.907720706096223e-07,
      "loss": 1.5801,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 8.641218185424805,
      "learning_rate": 6.294136122464701e-07,
      "loss": 1.5755,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 13.54507064819336,
      "learning_rate": 4.121274084874194e-07,
      "loss": 1.6523,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 8.669917106628418,
      "learning_rate": 2.399354116946584e-07,
      "loss": 1.5707,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 15.19518756866455,
      "learning_rate": 1.1364748468886688e-07,
      "loss": 1.5997,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1941504,
      "step": 237,
      "total_flos": 3521692676653056.0,
      "train_loss": 2.3182458032535602,
      "train_runtime": 206.8614,
      "train_samples_per_second": 9.151,
      "train_steps_per_second": 1.146
    }
  ],
  "logging_steps": 5,
  "max_steps": 237,
  "num_input_tokens_seen": 1941504,
  "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": 3521692676653056.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}