{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.4333694474539545,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00866738894907909,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 4942772.5,
      "step": 1
    },
    {
      "epoch": 0.00866738894907909,
      "eval_loss": NaN,
      "eval_runtime": 0.5663,
      "eval_samples_per_second": 88.298,
      "eval_steps_per_second": 22.957,
      "step": 1
    },
    {
      "epoch": 0.01733477789815818,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.02600216684723727,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.03466955579631636,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.04333694474539545,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.05200433369447454,
      "grad_norm": NaN,
      "learning_rate": 9.997539658034168e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.06067172264355363,
      "grad_norm": NaN,
      "learning_rate": 9.990161322484486e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.06933911159263272,
      "grad_norm": NaN,
      "learning_rate": 9.977873061452552e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0780065005417118,
      "grad_norm": NaN,
      "learning_rate": 9.96068831197139e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0866738894907909,
      "grad_norm": NaN,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.09534127843986999,
      "grad_norm": NaN,
      "learning_rate": 9.911709846436641e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.10400866738894908,
      "grad_norm": NaN,
      "learning_rate": 9.879969687616027e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": NaN,
      "learning_rate": 9.84344009624807e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.12134344528710726,
      "grad_norm": NaN,
      "learning_rate": 9.80216101690461e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.13001083423618634,
      "grad_norm": NaN,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.13867822318526543,
      "grad_norm": NaN,
      "learning_rate": 9.705540090697575e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.14734561213434452,
      "grad_norm": NaN,
      "learning_rate": 9.650303897398232e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.1560130010834236,
      "grad_norm": NaN,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.1646803900325027,
      "grad_norm": NaN,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.1733477789815818,
      "grad_norm": NaN,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.1820151679306609,
      "grad_norm": NaN,
      "learning_rate": 9.384654164309083e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.19068255687973998,
      "grad_norm": NaN,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.19934994582881907,
      "grad_norm": NaN,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.20801733477789816,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.21668472372697725,
      "grad_norm": NaN,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.21668472372697725,
      "eval_loss": NaN,
      "eval_runtime": 0.567,
      "eval_samples_per_second": 88.18,
      "eval_steps_per_second": 22.927,
      "step": 25
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": NaN,
      "learning_rate": 8.957804998855866e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.23401950162513543,
      "grad_norm": NaN,
      "learning_rate": 8.860696646428693e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.24268689057421453,
      "grad_norm": NaN,
      "learning_rate": 8.759913421559902e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.2513542795232936,
      "grad_norm": NaN,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.2600216684723727,
      "grad_norm": NaN,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.26868905742145177,
      "grad_norm": NaN,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.27735644637053086,
      "grad_norm": NaN,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.28602383531960995,
      "grad_norm": NaN,
      "learning_rate": 8.204865162773613e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.29469122426868904,
      "grad_norm": NaN,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.30335861321776814,
      "grad_norm": NaN,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.3120260021668472,
      "grad_norm": NaN,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.3206933911159263,
      "grad_norm": NaN,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.3293607800650054,
      "grad_norm": NaN,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": NaN,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.3466955579631636,
      "grad_norm": NaN,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.3553629469122427,
      "grad_norm": NaN,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.3640303358613218,
      "grad_norm": NaN,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.37269772481040087,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.38136511375947996,
      "grad_norm": NaN,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.39003250270855905,
      "grad_norm": NaN,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.39869989165763814,
      "grad_norm": NaN,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.40736728060671723,
      "grad_norm": NaN,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.4160346695557963,
      "grad_norm": NaN,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.4247020585048754,
      "grad_norm": NaN,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.4333694474539545,
      "grad_norm": NaN,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.4333694474539545,
      "eval_loss": NaN,
      "eval_runtime": 0.5598,
      "eval_samples_per_second": 89.311,
      "eval_steps_per_second": 23.221,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9144668088434688.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}