{
  "best_metric": 1.8761990070343018,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0755287009063444,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015105740181268882,
      "grad_norm": 38.372501373291016,
      "learning_rate": 5e-05,
      "loss": 2.0533,
      "step": 1
    },
    {
      "epoch": 0.0015105740181268882,
      "eval_loss": 2.11383318901062,
      "eval_runtime": 379.0141,
      "eval_samples_per_second": 23.535,
      "eval_steps_per_second": 2.942,
      "step": 1
    },
    {
      "epoch": 0.0030211480362537764,
      "grad_norm": 45.164649963378906,
      "learning_rate": 0.0001,
      "loss": 2.0999,
      "step": 2
    },
    {
      "epoch": 0.004531722054380665,
      "grad_norm": 22.255449295043945,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.0574,
      "step": 3
    },
    {
      "epoch": 0.006042296072507553,
      "grad_norm": 15.518555641174316,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.9927,
      "step": 4
    },
    {
      "epoch": 0.0075528700906344415,
      "grad_norm": 12.416341781616211,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9789,
      "step": 5
    },
    {
      "epoch": 0.00906344410876133,
      "grad_norm": 11.008262634277344,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9897,
      "step": 6
    },
    {
      "epoch": 0.010574018126888218,
      "grad_norm": 10.411260604858398,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.9794,
      "step": 7
    },
    {
      "epoch": 0.012084592145015106,
      "grad_norm": 10.190176010131836,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9458,
      "step": 8
    },
    {
      "epoch": 0.013595166163141994,
      "grad_norm": 10.882474899291992,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9277,
      "step": 9
    },
    {
      "epoch": 0.015105740181268883,
      "grad_norm": 12.2539701461792,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9583,
      "step": 10
    },
    {
      "epoch": 0.01661631419939577,
      "grad_norm": 13.870675086975098,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.9288,
      "step": 11
    },
    {
      "epoch": 0.01812688821752266,
      "grad_norm": 16.904359817504883,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.8735,
      "step": 12
    },
    {
      "epoch": 0.019637462235649546,
      "grad_norm": 20.735435485839844,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.9198,
      "step": 13
    },
    {
      "epoch": 0.021148036253776436,
      "grad_norm": 18.89630699157715,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9836,
      "step": 14
    },
    {
      "epoch": 0.022658610271903322,
      "grad_norm": 17.90799903869629,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.9534,
      "step": 15
    },
    {
      "epoch": 0.02416918429003021,
      "grad_norm": 11.054027557373047,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.9361,
      "step": 16
    },
    {
      "epoch": 0.0256797583081571,
      "grad_norm": 12.436798095703125,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.9447,
      "step": 17
    },
    {
      "epoch": 0.027190332326283987,
      "grad_norm": 14.795900344848633,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9125,
      "step": 18
    },
    {
      "epoch": 0.028700906344410877,
      "grad_norm": 14.699880599975586,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.941,
      "step": 19
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 9.646371841430664,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.9222,
      "step": 20
    },
    {
      "epoch": 0.03172205438066465,
      "grad_norm": 9.113815307617188,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.8951,
      "step": 21
    },
    {
      "epoch": 0.03323262839879154,
      "grad_norm": 73.9245376586914,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8928,
      "step": 22
    },
    {
      "epoch": 0.03474320241691843,
      "grad_norm": 56.74176025390625,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8689,
      "step": 23
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 10.495920181274414,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.8297,
      "step": 24
    },
    {
      "epoch": 0.0377643504531722,
      "grad_norm": 10.864616394042969,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7874,
      "step": 25
    },
    {
      "epoch": 0.0377643504531722,
      "eval_loss": 1.894762635231018,
      "eval_runtime": 367.8915,
      "eval_samples_per_second": 24.246,
      "eval_steps_per_second": 3.031,
      "step": 25
    },
    {
      "epoch": 0.03927492447129909,
      "grad_norm": 13.991535186767578,
      "learning_rate": 5e-05,
      "loss": 1.9516,
      "step": 26
    },
    {
      "epoch": 0.04078549848942598,
      "grad_norm": 12.654444694519043,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.9724,
      "step": 27
    },
    {
      "epoch": 0.04229607250755287,
      "grad_norm": 9.985688209533691,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.9129,
      "step": 28
    },
    {
      "epoch": 0.04380664652567976,
      "grad_norm": 8.882885932922363,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.9091,
      "step": 29
    },
    {
      "epoch": 0.045317220543806644,
      "grad_norm": 8.36329460144043,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.9237,
      "step": 30
    },
    {
      "epoch": 0.04682779456193353,
      "grad_norm": 8.64007568359375,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.886,
      "step": 31
    },
    {
      "epoch": 0.04833836858006042,
      "grad_norm": 9.498104095458984,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9173,
      "step": 32
    },
    {
      "epoch": 0.04984894259818731,
      "grad_norm": 9.14793586730957,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.9047,
      "step": 33
    },
    {
      "epoch": 0.0513595166163142,
      "grad_norm": 9.84379768371582,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.8504,
      "step": 34
    },
    {
      "epoch": 0.052870090634441085,
      "grad_norm": 10.553916931152344,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.8816,
      "step": 35
    },
    {
      "epoch": 0.054380664652567974,
      "grad_norm": 11.11711311340332,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.852,
      "step": 36
    },
    {
      "epoch": 0.055891238670694864,
      "grad_norm": 12.357012748718262,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.8347,
      "step": 37
    },
    {
      "epoch": 0.05740181268882175,
      "grad_norm": 10.349846839904785,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8391,
      "step": 38
    },
    {
      "epoch": 0.05891238670694864,
      "grad_norm": 7.760517597198486,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.9363,
      "step": 39
    },
    {
      "epoch": 0.06042296072507553,
      "grad_norm": 8.133441925048828,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.9542,
      "step": 40
    },
    {
      "epoch": 0.061933534743202415,
      "grad_norm": 7.650514125823975,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.927,
      "step": 41
    },
    {
      "epoch": 0.0634441087613293,
      "grad_norm": 7.582345008850098,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.9362,
      "step": 42
    },
    {
      "epoch": 0.0649546827794562,
      "grad_norm": 8.583966255187988,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.9035,
      "step": 43
    },
    {
      "epoch": 0.06646525679758308,
      "grad_norm": 8.344738960266113,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8908,
      "step": 44
    },
    {
      "epoch": 0.06797583081570997,
      "grad_norm": 7.929678440093994,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.871,
      "step": 45
    },
    {
      "epoch": 0.06948640483383686,
      "grad_norm": 7.730828285217285,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.8825,
      "step": 46
    },
    {
      "epoch": 0.07099697885196375,
      "grad_norm": 8.460161209106445,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.8743,
      "step": 47
    },
    {
      "epoch": 0.07250755287009064,
      "grad_norm": 8.845512390136719,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.8665,
      "step": 48
    },
    {
      "epoch": 0.07401812688821752,
      "grad_norm": 9.84435749053955,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.8485,
      "step": 49
    },
    {
      "epoch": 0.0755287009063444,
      "grad_norm": 12.877066612243652,
      "learning_rate": 0.0,
      "loss": 1.7575,
      "step": 50
    },
    {
      "epoch": 0.0755287009063444,
      "eval_loss": 1.8761990070343018,
      "eval_runtime": 367.8841,
      "eval_samples_per_second": 24.247,
      "eval_steps_per_second": 3.031,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1316042676568064e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}