{
  "best_metric": 1.6491321325302124,
  "best_model_checkpoint": "/data/user_data/gonilude/python_and_text_pythia_160m/checkpoint-150",
  "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": 0.19718309859154928,
      "eval_loss": 9.814414978027344,
      "eval_runtime": 0.3368,
      "eval_samples_per_second": 210.811,
      "eval_steps_per_second": 26.723,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.425,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 7.9382,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": Infinity,
      "learning_rate": 5e-06,
      "loss": 8.0612,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 377.5516662597656,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 6.289,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 519.905517578125,
      "learning_rate": 1.9984947460216708e-05,
      "loss": 3.6305,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 137.5762939453125,
      "learning_rate": 1.9923874174311394e-05,
      "loss": 2.816,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 152.59420776367188,
      "learning_rate": 1.9816126380411478e-05,
      "loss": 1.8783,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 184.83087158203125,
      "learning_rate": 1.9662210843836574e-05,
      "loss": 2.1072,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 186.87013244628906,
      "learning_rate": 1.946285146855968e-05,
      "loss": 1.958,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 170.01846313476562,
      "learning_rate": 1.921898589250242e-05,
      "loss": 2.15,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 156.2119598388672,
      "learning_rate": 1.8931761077585037e-05,
      "loss": 2.0211,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "eval_accuracy": 0.1267605633802817,
      "eval_loss": 1.9534826278686523,
      "eval_runtime": 0.2174,
      "eval_samples_per_second": 326.596,
      "eval_steps_per_second": 41.4,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 125.18607330322266,
      "learning_rate": 1.860252791527236e-05,
      "loss": 1.8652,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 131.51097106933594,
      "learning_rate": 1.8232834872987147e-05,
      "loss": 1.6875,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 132.37973022460938,
      "learning_rate": 1.782442071127338e-05,
      "loss": 1.8354,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 158.42999267578125,
      "learning_rate": 1.7379206305962525e-05,
      "loss": 1.8209,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 67.9870834350586,
      "learning_rate": 1.6899285613805246e-05,
      "loss": 1.7624,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 178.30116271972656,
      "learning_rate": 1.6386915824059427e-05,
      "loss": 1.7832,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 185.28076171875,
      "learning_rate": 1.5844506742354163e-05,
      "loss": 2.1439,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 157.6683807373047,
      "learning_rate": 1.5274609456760073e-05,
      "loss": 1.8426,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 107.63882446289062,
      "learning_rate": 1.4679904339372301e-05,
      "loss": 1.7307,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 126.8455581665039,
      "learning_rate": 1.4063188439837831e-05,
      "loss": 1.916,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2658227848101267,
      "eval_accuracy": 0.19718309859154928,
      "eval_loss": 1.6971796751022339,
      "eval_runtime": 0.219,
      "eval_samples_per_second": 324.264,
      "eval_steps_per_second": 41.104,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 104.72110748291016,
      "learning_rate": 1.3427362330118542e-05,
      "loss": 1.7162,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 93.7473373413086,
      "learning_rate": 1.2775416462362458e-05,
      "loss": 1.6155,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 83.0439682006836,
      "learning_rate": 1.2110417104045575e-05,
      "loss": 1.7444,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 88.41893768310547,
      "learning_rate": 1.1435491916534919e-05,
      "loss": 1.6476,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 49.397403717041016,
      "learning_rate": 1.0753815244900459e-05,
      "loss": 1.5816,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 87.76904296875,
      "learning_rate": 1.0068593188161698e-05,
      "loss": 2.0688,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 60.90505599975586,
      "learning_rate": 9.383048520187344e-06,
      "loss": 1.6899,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 80.01156616210938,
      "learning_rate": 8.700405532168921e-06,
      "loss": 1.6115,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 92.96195983886719,
      "learning_rate": 8.023874867958027e-06,
      "loss": 1.5858,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 149.9720001220703,
      "learning_rate": 7.3566384235904855e-06,
      "loss": 1.6616,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8987341772151898,
      "eval_accuracy": 0.19718309859154928,
      "eval_loss": 1.6491321325302124,
      "eval_runtime": 0.1676,
      "eval_samples_per_second": 423.615,
      "eval_steps_per_second": 53.698,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 57.700984954833984,
      "learning_rate": 6.7018343820188324e-06,
      "loss": 1.5952,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 66.33654022216797,
      "learning_rate": 6.0625424534385425e-06,
      "loss": 1.5148,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 91.3177490234375,
      "learning_rate": 5.441769390626537e-06,
      "loss": 1.6566,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 91.95642852783203,
      "learning_rate": 4.842434847417001e-06,
      "loss": 1.6347,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 118.14971160888672,
      "learning_rate": 4.267357646825746e-06,
      "loss": 1.5415,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 154.98838806152344,
      "learning_rate": 3.719242523407539e-06,
      "loss": 1.6275,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 97.98387908935547,
      "learning_rate": 3.2006674022005857e-06,
      "loss": 1.6091,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 51.0837287902832,
      "learning_rate": 2.714071274088438e-06,
      "loss": 1.5801,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 158.22381591796875,
      "learning_rate": 2.2617427246045976e-06,
      "loss": 1.6031,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 66.8087387084961,
      "learning_rate": 1.8458091701318504e-06,
      "loss": 1.565,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5316455696202533,
      "eval_accuracy": 0.14084507042253522,
      "eval_loss": 1.6663732528686523,
      "eval_runtime": 0.2173,
      "eval_samples_per_second": 326.688,
      "eval_steps_per_second": 41.411,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 82.30987548828125,
      "learning_rate": 1.4682268521211075e-06,
      "loss": 1.5668,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 54.035919189453125,
      "learning_rate": 1.130771636389596e-06,
      "loss": 1.5857,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 80.6180191040039,
      "learning_rate": 8.350306607715774e-07,
      "loss": 1.593,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 38.75018310546875,
      "learning_rate": 5.823948704048443e-07,
      "loss": 1.5226,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 99.82989501953125,
      "learning_rate": 3.7405247576144055e-07,
      "loss": 1.6135,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 74.42279815673828,
      "learning_rate": 2.1098336419116628e-07,
      "loss": 1.5738,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 124.18939208984375,
      "learning_rate": 9.395449126177291e-08,
      "loss": 1.5493,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1941504,
      "step": 237,
      "total_flos": 990864117596160.0,
      "train_loss": 2.1522638506024196,
      "train_runtime": 52.4434,
      "train_samples_per_second": 36.096,
      "train_steps_per_second": 4.519
    }
  ],
  "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": 990864117596160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}