{
  "best_metric": 1.6777832508087158,
  "best_model_checkpoint": "/data/user_data/gonilude/cpp_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": 0.2,
      "eval_loss": 4.986144065856934,
      "eval_runtime": 1.1285,
      "eval_samples_per_second": 62.027,
      "eval_steps_per_second": 7.975,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.4794,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.133,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 1133.67919921875,
      "learning_rate": 5e-06,
      "loss": 5.5324,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 198.05026245117188,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 6.6948,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 115.6029052734375,
      "learning_rate": 1.9984947460216708e-05,
      "loss": 4.4825,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 88.50775909423828,
      "learning_rate": 1.9923874174311394e-05,
      "loss": 4.1532,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 107.87947082519531,
      "learning_rate": 1.9816126380411478e-05,
      "loss": 4.0467,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 23.852434158325195,
      "learning_rate": 1.9662210843836574e-05,
      "loss": 1.649,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 12.68623161315918,
      "learning_rate": 1.946285146855968e-05,
      "loss": 1.8697,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 13.480600357055664,
      "learning_rate": 1.921898589250242e-05,
      "loss": 1.8013,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 18.860410690307617,
      "learning_rate": 1.8931761077585037e-05,
      "loss": 1.8815,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "eval_accuracy": 0.18571428571428572,
      "eval_loss": 1.7072056531906128,
      "eval_runtime": 0.9042,
      "eval_samples_per_second": 77.413,
      "eval_steps_per_second": 9.953,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 38.59328842163086,
      "learning_rate": 1.860252791527236e-05,
      "loss": 1.7259,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 12.516915321350098,
      "learning_rate": 1.8232834872987147e-05,
      "loss": 1.8872,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 30.57850456237793,
      "learning_rate": 1.782442071127338e-05,
      "loss": 1.8078,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 15.95567512512207,
      "learning_rate": 1.7379206305962525e-05,
      "loss": 1.7026,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 16.61585235595703,
      "learning_rate": 1.6899285613805246e-05,
      "loss": 1.6721,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 17.780010223388672,
      "learning_rate": 1.6386915824059427e-05,
      "loss": 1.4982,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 15.395638465881348,
      "learning_rate": 1.5844506742354163e-05,
      "loss": 1.7322,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 18.798755645751953,
      "learning_rate": 1.5274609456760073e-05,
      "loss": 1.6946,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 15.229305267333984,
      "learning_rate": 1.4679904339372301e-05,
      "loss": 1.6712,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 14.479815483093262,
      "learning_rate": 1.4063188439837831e-05,
      "loss": 1.6129,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2658227848101267,
      "eval_accuracy": 0.15714285714285714,
      "eval_loss": 1.7499092817306519,
      "eval_runtime": 0.9052,
      "eval_samples_per_second": 77.327,
      "eval_steps_per_second": 9.942,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 15.65237045288086,
      "learning_rate": 1.3427362330118542e-05,
      "loss": 1.6163,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 12.068513870239258,
      "learning_rate": 1.2775416462362458e-05,
      "loss": 1.6507,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 18.504961013793945,
      "learning_rate": 1.2110417104045575e-05,
      "loss": 1.6317,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 13.793102264404297,
      "learning_rate": 1.1435491916534919e-05,
      "loss": 1.7895,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 22.34800148010254,
      "learning_rate": 1.0753815244900459e-05,
      "loss": 1.6955,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 19.815095901489258,
      "learning_rate": 1.0068593188161698e-05,
      "loss": 1.686,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 22.263498306274414,
      "learning_rate": 9.383048520187344e-06,
      "loss": 1.6595,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 19.161380767822266,
      "learning_rate": 8.700405532168921e-06,
      "loss": 1.5961,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 27.031253814697266,
      "learning_rate": 8.023874867958027e-06,
      "loss": 1.7879,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 18.79669952392578,
      "learning_rate": 7.3566384235904855e-06,
      "loss": 1.6363,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8987341772151898,
      "eval_accuracy": 0.15714285714285714,
      "eval_loss": 1.7443429231643677,
      "eval_runtime": 0.9046,
      "eval_samples_per_second": 77.387,
      "eval_steps_per_second": 9.95,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 15.857290267944336,
      "learning_rate": 6.7018343820188324e-06,
      "loss": 1.7356,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 14.174161911010742,
      "learning_rate": 6.0625424534385425e-06,
      "loss": 1.6213,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 19.495052337646484,
      "learning_rate": 5.441769390626537e-06,
      "loss": 1.6586,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 9.598532676696777,
      "learning_rate": 4.842434847417001e-06,
      "loss": 1.4322,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 17.1945858001709,
      "learning_rate": 4.267357646825746e-06,
      "loss": 1.5919,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 17.863174438476562,
      "learning_rate": 3.719242523407539e-06,
      "loss": 1.5252,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 8.82008171081543,
      "learning_rate": 3.2006674022005857e-06,
      "loss": 1.6203,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 10.616914749145508,
      "learning_rate": 2.714071274088438e-06,
      "loss": 1.5487,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 10.994531631469727,
      "learning_rate": 2.2617427246045976e-06,
      "loss": 1.6295,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 18.025531768798828,
      "learning_rate": 1.8458091701318504e-06,
      "loss": 1.5486,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5316455696202533,
      "eval_accuracy": 0.15714285714285714,
      "eval_loss": 1.6777832508087158,
      "eval_runtime": 0.909,
      "eval_samples_per_second": 77.011,
      "eval_steps_per_second": 9.901,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 11.53801155090332,
      "learning_rate": 1.4682268521211075e-06,
      "loss": 1.5443,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 9.935652732849121,
      "learning_rate": 1.130771636389596e-06,
      "loss": 1.5573,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 11.843810081481934,
      "learning_rate": 8.350306607715774e-07,
      "loss": 1.5242,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 14.085565567016602,
      "learning_rate": 5.823948704048443e-07,
      "loss": 1.5748,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 12.15102767944336,
      "learning_rate": 3.7405247576144055e-07,
      "loss": 1.5469,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 15.505411148071289,
      "learning_rate": 2.1098336419116628e-07,
      "loss": 1.5503,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 11.011249542236328,
      "learning_rate": 9.395449126177291e-08,
      "loss": 1.4825,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1941504,
      "step": 237,
      "total_flos": 3521692676653056.0,
      "train_loss": 2.0961106618245444,
      "train_runtime": 196.5081,
      "train_samples_per_second": 9.587,
      "train_steps_per_second": 1.206
    }
  ],
  "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
}