{
  "best_metric": 0.4826611280441284,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0019685814402141816,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.937162880428363e-05,
      "grad_norm": 0.1473366916179657,
      "learning_rate": 1e-05,
      "loss": 0.4842,
      "step": 1
    },
    {
      "epoch": 3.937162880428363e-05,
      "eval_loss": 0.6386224031448364,
      "eval_runtime": 1995.7368,
      "eval_samples_per_second": 21.435,
      "eval_steps_per_second": 5.359,
      "step": 1
    },
    {
      "epoch": 7.874325760856726e-05,
      "grad_norm": 0.1501932293176651,
      "learning_rate": 2e-05,
      "loss": 0.4723,
      "step": 2
    },
    {
      "epoch": 0.0001181148864128509,
      "grad_norm": 0.15301698446273804,
      "learning_rate": 3e-05,
      "loss": 0.465,
      "step": 3
    },
    {
      "epoch": 0.00015748651521713453,
      "grad_norm": 0.15504051744937897,
      "learning_rate": 4e-05,
      "loss": 0.4613,
      "step": 4
    },
    {
      "epoch": 0.00019685814402141817,
      "grad_norm": 0.17802225053310394,
      "learning_rate": 5e-05,
      "loss": 0.4573,
      "step": 5
    },
    {
      "epoch": 0.0002362297728257018,
      "grad_norm": 0.16927273571491241,
      "learning_rate": 6e-05,
      "loss": 0.4521,
      "step": 6
    },
    {
      "epoch": 0.00027560140162998545,
      "grad_norm": 0.17416727542877197,
      "learning_rate": 7e-05,
      "loss": 0.4688,
      "step": 7
    },
    {
      "epoch": 0.00031497303043426906,
      "grad_norm": 0.19252535700798035,
      "learning_rate": 8e-05,
      "loss": 0.4869,
      "step": 8
    },
    {
      "epoch": 0.0003543446592385527,
      "grad_norm": 0.21720175445079803,
      "learning_rate": 9e-05,
      "loss": 0.4392,
      "step": 9
    },
    {
      "epoch": 0.00039371628804283634,
      "grad_norm": 0.20339831709861755,
      "learning_rate": 0.0001,
      "loss": 0.4673,
      "step": 10
    },
    {
      "epoch": 0.00043308791684711995,
      "grad_norm": 0.188543438911438,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4404,
      "step": 11
    },
    {
      "epoch": 0.0004724595456514036,
      "grad_norm": 0.1840866506099701,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4308,
      "step": 12
    },
    {
      "epoch": 0.0005118311744556872,
      "grad_norm": 0.1921333223581314,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4258,
      "step": 13
    },
    {
      "epoch": 0.0005512028032599709,
      "grad_norm": 0.1822589933872223,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4197,
      "step": 14
    },
    {
      "epoch": 0.0005905744320642545,
      "grad_norm": 0.17518241703510284,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4372,
      "step": 15
    },
    {
      "epoch": 0.0006299460608685381,
      "grad_norm": 0.16869305074214935,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4088,
      "step": 16
    },
    {
      "epoch": 0.0006693176896728218,
      "grad_norm": 0.18317943811416626,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4121,
      "step": 17
    },
    {
      "epoch": 0.0007086893184771055,
      "grad_norm": 0.1914009302854538,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4111,
      "step": 18
    },
    {
      "epoch": 0.000748060947281389,
      "grad_norm": 0.17840923368930817,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4001,
      "step": 19
    },
    {
      "epoch": 0.0007874325760856727,
      "grad_norm": 0.19282005727291107,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4029,
      "step": 20
    },
    {
      "epoch": 0.0008268042048899563,
      "grad_norm": 0.2061193436384201,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3986,
      "step": 21
    },
    {
      "epoch": 0.0008661758336942399,
      "grad_norm": 0.20973272621631622,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4132,
      "step": 22
    },
    {
      "epoch": 0.0009055474624985236,
      "grad_norm": 0.20912733674049377,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.393,
      "step": 23
    },
    {
      "epoch": 0.0009449190913028072,
      "grad_norm": 0.20087695121765137,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.3943,
      "step": 24
    },
    {
      "epoch": 0.0009842907201070908,
      "grad_norm": 0.2549019157886505,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4077,
      "step": 25
    },
    {
      "epoch": 0.0010236623489113745,
      "grad_norm": 0.21350446343421936,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3767,
      "step": 26
    },
    {
      "epoch": 0.0010630339777156581,
      "grad_norm": 0.2284364104270935,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.3941,
      "step": 27
    },
    {
      "epoch": 0.0011024056065199418,
      "grad_norm": 0.20515067875385284,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.3623,
      "step": 28
    },
    {
      "epoch": 0.0011417772353242255,
      "grad_norm": 0.22672885656356812,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3734,
      "step": 29
    },
    {
      "epoch": 0.001181148864128509,
      "grad_norm": 0.2223028987646103,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3831,
      "step": 30
    },
    {
      "epoch": 0.0012205204929327926,
      "grad_norm": 0.22611401975154877,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3728,
      "step": 31
    },
    {
      "epoch": 0.0012598921217370762,
      "grad_norm": 0.23607665300369263,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.387,
      "step": 32
    },
    {
      "epoch": 0.00129926375054136,
      "grad_norm": 0.24884606897830963,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3784,
      "step": 33
    },
    {
      "epoch": 0.0013386353793456436,
      "grad_norm": 0.2478945106267929,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3671,
      "step": 34
    },
    {
      "epoch": 0.0013780070081499272,
      "grad_norm": 0.2744622230529785,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3852,
      "step": 35
    },
    {
      "epoch": 0.001417378636954211,
      "grad_norm": 0.2842346727848053,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3984,
      "step": 36
    },
    {
      "epoch": 0.0014567502657584943,
      "grad_norm": 0.3080979585647583,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4233,
      "step": 37
    },
    {
      "epoch": 0.001496121894562778,
      "grad_norm": 0.32813560962677,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3906,
      "step": 38
    },
    {
      "epoch": 0.0015354935233670617,
      "grad_norm": 0.3377130627632141,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3866,
      "step": 39
    },
    {
      "epoch": 0.0015748651521713453,
      "grad_norm": 0.38843271136283875,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4104,
      "step": 40
    },
    {
      "epoch": 0.001614236780975629,
      "grad_norm": 0.3918204605579376,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4434,
      "step": 41
    },
    {
      "epoch": 0.0016536084097799127,
      "grad_norm": 0.4351727068424225,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4251,
      "step": 42
    },
    {
      "epoch": 0.0016929800385841961,
      "grad_norm": 0.5044992566108704,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4586,
      "step": 43
    },
    {
      "epoch": 0.0017323516673884798,
      "grad_norm": 0.4990330636501312,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4392,
      "step": 44
    },
    {
      "epoch": 0.0017717232961927635,
      "grad_norm": 0.5468814373016357,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5086,
      "step": 45
    },
    {
      "epoch": 0.0018110949249970471,
      "grad_norm": 0.6528873443603516,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.4761,
      "step": 46
    },
    {
      "epoch": 0.0018504665538013308,
      "grad_norm": 0.7145413160324097,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.4981,
      "step": 47
    },
    {
      "epoch": 0.0018898381826056145,
      "grad_norm": 0.8748348951339722,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4825,
      "step": 48
    },
    {
      "epoch": 0.0019292098114098981,
      "grad_norm": 1.0368186235427856,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.5143,
      "step": 49
    },
    {
      "epoch": 0.0019685814402141816,
      "grad_norm": 1.806100606918335,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.736,
      "step": 50
    },
    {
      "epoch": 0.0019685814402141816,
      "eval_loss": 0.4826611280441284,
      "eval_runtime": 2007.0233,
      "eval_samples_per_second": 21.314,
      "eval_steps_per_second": 5.329,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.62025180463104e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}