{
  "best_metric": 1.6594650745391846,
  "best_model_checkpoint": "/data/user_data/gonilude/python_and_text_pythia_70m/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": 0.22535211267605634,
      "eval_loss": 7.193855285644531,
      "eval_runtime": 0.2991,
      "eval_samples_per_second": 237.392,
      "eval_steps_per_second": 30.092,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 8.2293,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 8.6977,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 434.0960388183594,
      "learning_rate": 1e-05,
      "loss": 8.1873,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 457.978271484375,
      "learning_rate": 2e-05,
      "loss": 5.5601,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 342.55340576171875,
      "learning_rate": 1.9976483726428423e-05,
      "loss": 3.0969,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 1078.478271484375,
      "learning_rate": 1.9939835156657616e-05,
      "loss": 2.4498,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 316.6920166015625,
      "learning_rate": 1.9841388720031727e-05,
      "loss": 1.9535,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 692.9888916015625,
      "learning_rate": 1.9729275686705832e-05,
      "loss": 2.7533,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 223.78614807128906,
      "learning_rate": 1.9547993211399753e-05,
      "loss": 1.9428,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 218.17137145996094,
      "learning_rate": 1.932180409200991e-05,
      "loss": 2.6774,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 219.60426330566406,
      "learning_rate": 1.905177215357839e-05,
      "loss": 1.7511,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "eval_accuracy": 0.14084507042253522,
      "eval_loss": 1.9312864542007446,
      "eval_runtime": 0.1429,
      "eval_samples_per_second": 496.992,
      "eval_steps_per_second": 62.999,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 167.01634216308594,
      "learning_rate": 1.8739167425092644e-05,
      "loss": 1.8037,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 194.86444091796875,
      "learning_rate": 1.838546016621564e-05,
      "loss": 1.7087,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 182.9615478515625,
      "learning_rate": 1.7992313952280175e-05,
      "loss": 1.8595,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 387.1624450683594,
      "learning_rate": 1.7561577850070355e-05,
      "loss": 1.7605,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 115.52404022216797,
      "learning_rate": 1.709527772118953e-05,
      "loss": 1.8325,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 225.36166381835938,
      "learning_rate": 1.659560669391714e-05,
      "loss": 1.805,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 363.2311096191406,
      "learning_rate": 1.6064914848367818e-05,
      "loss": 2.0046,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 244.0623016357422,
      "learning_rate": 1.5505698163465986e-05,
      "loss": 1.7745,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 201.84446716308594,
      "learning_rate": 1.4920586777721231e-05,
      "loss": 1.7372,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 164.17694091796875,
      "learning_rate": 1.4312332619016964e-05,
      "loss": 1.8156,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2658227848101267,
      "eval_accuracy": 0.22535211267605634,
      "eval_loss": 1.7096410989761353,
      "eval_runtime": 0.1476,
      "eval_samples_per_second": 481.143,
      "eval_steps_per_second": 60.99,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 234.53009033203125,
      "learning_rate": 1.3683796461592604e-05,
      "loss": 1.7591,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 189.70046997070312,
      "learning_rate": 1.3037934471093683e-05,
      "loss": 1.6518,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 167.0009002685547,
      "learning_rate": 1.2377784300971807e-05,
      "loss": 1.7383,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 210.74073791503906,
      "learning_rate": 1.1706450805626762e-05,
      "loss": 1.6693,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 113.87993621826172,
      "learning_rate": 1.1027091437485404e-05,
      "loss": 1.5721,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 175.82958984375,
      "learning_rate": 1.0342901396698658e-05,
      "loss": 1.8908,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 94.99879455566406,
      "learning_rate": 9.657098603301347e-06,
      "loss": 1.7056,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 142.98709106445312,
      "learning_rate": 8.9729085625146e-06,
      "loss": 1.62,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 149.57101440429688,
      "learning_rate": 8.293549194373243e-06,
      "loss": 1.627,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 245.75396728515625,
      "learning_rate": 7.622215699028196e-06,
      "loss": 1.6432,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8987341772151898,
      "eval_accuracy": 0.2112676056338028,
      "eval_loss": 1.6594650745391846,
      "eval_runtime": 0.1424,
      "eval_samples_per_second": 498.688,
      "eval_steps_per_second": 63.214,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 89.35352325439453,
      "learning_rate": 6.962065528906321e-06,
      "loss": 1.6411,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 126.32188415527344,
      "learning_rate": 6.316203538407397e-06,
      "loss": 1.5683,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 127.23784637451172,
      "learning_rate": 5.687667380983037e-06,
      "loss": 1.7256,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 161.1302947998047,
      "learning_rate": 5.07941322227877e-06,
      "loss": 1.6769,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 203.9555206298828,
      "learning_rate": 4.494301836534016e-06,
      "loss": 1.561,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 234.33477783203125,
      "learning_rate": 3.935085151632185e-06,
      "loss": 1.5984,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 168.90626525878906,
      "learning_rate": 3.4043933060828606e-06,
      "loss": 1.5909,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 99.04336547851562,
      "learning_rate": 2.9047222788104712e-06,
      "loss": 1.5661,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 272.1407470703125,
      "learning_rate": 2.4384221499296466e-06,
      "loss": 1.5917,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 114.18236541748047,
      "learning_rate": 2.007686047719831e-06,
      "loss": 1.5408,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5316455696202533,
      "eval_accuracy": 0.19718309859154928,
      "eval_loss": 1.6633472442626953,
      "eval_runtime": 0.1412,
      "eval_samples_per_second": 502.839,
      "eval_steps_per_second": 63.74,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 157.7032928466797,
      "learning_rate": 1.6145398337843654e-06,
      "loss": 1.5757,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 88.51991271972656,
      "learning_rate": 1.2608325749073591e-06,
      "loss": 1.5955,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 139.67247009277344,
      "learning_rate": 9.482278464216121e-07,
      "loss": 1.558,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 130.27508544921875,
      "learning_rate": 6.781959079900958e-07,
      "loss": 1.5464,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 163.9243621826172,
      "learning_rate": 4.520067886002488e-07,
      "loss": 1.6119,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 116.64250946044922,
      "learning_rate": 2.707243132941717e-07,
      "loss": 1.5334,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 202.17108154296875,
      "learning_rate": 1.3520109972846918e-07,
      "loss": 1.5555,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1941504,
      "step": 237,
      "total_flos": 220374931341312.0,
      "train_loss": 2.1441552528349157,
      "train_runtime": 22.4706,
      "train_samples_per_second": 84.243,
      "train_steps_per_second": 10.547
    }
  ],
  "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": 220374931341312.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}