{
  "best_metric": 1.659671425819397,
  "best_model_checkpoint": "/data/user_data/gonilude/python_and_text_pythia_1b/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": 1.9329111576080322,
      "eval_runtime": 0.9209,
      "eval_samples_per_second": 77.098,
      "eval_steps_per_second": 9.773,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.8643,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": 98.8646469116211,
      "learning_rate": 2.5e-06,
      "loss": 2.0292,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 78.7982406616211,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.6274,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 44.39988327026367,
      "learning_rate": 1.999153201672344e-05,
      "loss": 1.9365,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 56.09316635131836,
      "learning_rate": 1.9953925451903757e-05,
      "loss": 2.8005,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 23.778945922851562,
      "learning_rate": 1.986479890027153e-05,
      "loss": 1.9282,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 22.14593505859375,
      "learning_rate": 1.9729275686705832e-05,
      "loss": 1.8437,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 21.635009765625,
      "learning_rate": 1.9547993211399753e-05,
      "loss": 2.1747,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 36.09115982055664,
      "learning_rate": 1.932180409200991e-05,
      "loss": 1.8426,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 21.926368713378906,
      "learning_rate": 1.905177215357839e-05,
      "loss": 2.0141,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 24.96376609802246,
      "learning_rate": 1.8739167425092644e-05,
      "loss": 1.7534,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "eval_accuracy": 0.1267605633802817,
      "eval_loss": 2.1001596450805664,
      "eval_runtime": 0.8338,
      "eval_samples_per_second": 85.15,
      "eval_steps_per_second": 10.794,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 25.672304153442383,
      "learning_rate": 1.838546016621564e-05,
      "loss": 1.8794,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 17.974288940429688,
      "learning_rate": 1.7992313952280175e-05,
      "loss": 1.6198,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 17.891626358032227,
      "learning_rate": 1.7561577850070355e-05,
      "loss": 1.8402,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 26.64494514465332,
      "learning_rate": 1.709527772118953e-05,
      "loss": 1.707,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 8.569857597351074,
      "learning_rate": 1.659560669391714e-05,
      "loss": 1.717,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 31.739055633544922,
      "learning_rate": 1.6064914848367818e-05,
      "loss": 1.687,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 28.70093536376953,
      "learning_rate": 1.5505698163465986e-05,
      "loss": 1.9082,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 28.82413673400879,
      "learning_rate": 1.4920586777721231e-05,
      "loss": 1.7321,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 20.39600372314453,
      "learning_rate": 1.4312332619016964e-05,
      "loss": 1.675,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 14.24821949005127,
      "learning_rate": 1.3683796461592604e-05,
      "loss": 1.737,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2658227848101267,
      "eval_accuracy": 0.2112676056338028,
      "eval_loss": 1.70565927028656,
      "eval_runtime": 0.8499,
      "eval_samples_per_second": 83.543,
      "eval_steps_per_second": 10.59,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 17.15838050842285,
      "learning_rate": 1.3037934471093683e-05,
      "loss": 1.6419,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 20.325576782226562,
      "learning_rate": 1.2377784300971807e-05,
      "loss": 1.6242,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 10.852635383605957,
      "learning_rate": 1.1706450805626762e-05,
      "loss": 1.676,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 13.203107833862305,
      "learning_rate": 1.1027091437485404e-05,
      "loss": 1.6001,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 13.230643272399902,
      "learning_rate": 1.0342901396698658e-05,
      "loss": 1.5378,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 14.586160659790039,
      "learning_rate": 9.657098603301347e-06,
      "loss": 1.7631,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 9.582100868225098,
      "learning_rate": 8.9729085625146e-06,
      "loss": 1.615,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 13.78858470916748,
      "learning_rate": 8.293549194373243e-06,
      "loss": 1.5787,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 15.993226051330566,
      "learning_rate": 7.622215699028196e-06,
      "loss": 1.6013,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 28.815187454223633,
      "learning_rate": 6.962065528906321e-06,
      "loss": 1.6248,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8987341772151898,
      "eval_accuracy": 0.19718309859154928,
      "eval_loss": 1.659671425819397,
      "eval_runtime": 0.8131,
      "eval_samples_per_second": 87.32,
      "eval_steps_per_second": 11.069,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 6.942416191101074,
      "learning_rate": 6.316203538407397e-06,
      "loss": 1.5599,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 10.559165954589844,
      "learning_rate": 5.687667380983037e-06,
      "loss": 1.4922,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 15.816205024719238,
      "learning_rate": 5.07941322227877e-06,
      "loss": 1.5809,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 17.880002975463867,
      "learning_rate": 4.494301836534016e-06,
      "loss": 1.6087,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 22.581768035888672,
      "learning_rate": 3.935085151632185e-06,
      "loss": 1.5043,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 24.53186798095703,
      "learning_rate": 3.4043933060828606e-06,
      "loss": 1.6017,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 19.106027603149414,
      "learning_rate": 2.9047222788104712e-06,
      "loss": 1.5861,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 10.13152027130127,
      "learning_rate": 2.4384221499296466e-06,
      "loss": 1.5453,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 29.276445388793945,
      "learning_rate": 2.007686047719831e-06,
      "loss": 1.4934,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 10.298810005187988,
      "learning_rate": 1.6145398337843654e-06,
      "loss": 1.4481,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5316455696202533,
      "eval_accuracy": 0.14084507042253522,
      "eval_loss": 1.7617015838623047,
      "eval_runtime": 0.8181,
      "eval_samples_per_second": 86.785,
      "eval_steps_per_second": 11.001,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 16.260913848876953,
      "learning_rate": 1.2608325749073591e-06,
      "loss": 1.529,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 12.57551383972168,
      "learning_rate": 9.482278464216121e-07,
      "loss": 1.552,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 13.254227638244629,
      "learning_rate": 6.781959079900958e-07,
      "loss": 1.4281,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 10.004585266113281,
      "learning_rate": 4.520067886002488e-07,
      "loss": 1.439,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 19.180036544799805,
      "learning_rate": 2.707243132941717e-07,
      "loss": 1.5696,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 13.415371894836426,
      "learning_rate": 1.3520109972846918e-07,
      "loss": 1.502,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 22.85205841064453,
      "learning_rate": 4.6074548096244346e-08,
      "loss": 1.5584,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1941504,
      "step": 237,
      "total_flos": 9386162506432512.0,
      "train_loss": 1.7149980520900292,
      "train_runtime": 273.4678,
      "train_samples_per_second": 6.922,
      "train_steps_per_second": 0.867
    }
  ],
  "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": 9386162506432512.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}