{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.127867018300967,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00255734036601934,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00255734036601934,
      "eval_loss": NaN,
      "eval_runtime": 1.4852,
      "eval_samples_per_second": 33.666,
      "eval_steps_per_second": 8.753,
      "step": 1
    },
    {
      "epoch": 0.00511468073203868,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.007672021098058019,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.01022936146407736,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.012786701830096699,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.015344042196116039,
      "grad_norm": NaN,
      "learning_rate": 9.997539658034168e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.01790138256213538,
      "grad_norm": NaN,
      "learning_rate": 9.990161322484486e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.02045872292815472,
      "grad_norm": NaN,
      "learning_rate": 9.977873061452552e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.02301606329417406,
      "grad_norm": NaN,
      "learning_rate": 9.96068831197139e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.025573403660193398,
      "grad_norm": NaN,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.02813074402621274,
      "grad_norm": NaN,
      "learning_rate": 9.911709846436641e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.030688084392232078,
      "grad_norm": NaN,
      "learning_rate": 9.879969687616027e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.033245424758251416,
      "grad_norm": NaN,
      "learning_rate": 9.84344009624807e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.03580276512427076,
      "grad_norm": NaN,
      "learning_rate": 9.80216101690461e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0383601054902901,
      "grad_norm": NaN,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.04091744585630944,
      "grad_norm": NaN,
      "learning_rate": 9.705540090697575e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.043474786222328775,
      "grad_norm": NaN,
      "learning_rate": 9.650303897398232e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.04603212658834812,
      "grad_norm": NaN,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04858946695436746,
      "grad_norm": NaN,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.051146807320386796,
      "grad_norm": NaN,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.05370414768640614,
      "grad_norm": NaN,
      "learning_rate": 9.384654164309083e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.05626148805242548,
      "grad_norm": NaN,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.05881882841844482,
      "grad_norm": NaN,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.061376168784464155,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0639335091504835,
      "grad_norm": NaN,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0639335091504835,
      "eval_loss": NaN,
      "eval_runtime": 1.485,
      "eval_samples_per_second": 33.67,
      "eval_steps_per_second": 8.754,
      "step": 25
    },
    {
      "epoch": 0.06649084951650283,
      "grad_norm": NaN,
      "learning_rate": 8.957804998855866e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.06904818988252218,
      "grad_norm": NaN,
      "learning_rate": 8.860696646428693e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.07160553024854152,
      "grad_norm": NaN,
      "learning_rate": 8.759913421559902e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.07416287061456085,
      "grad_norm": NaN,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0767202109805802,
      "grad_norm": NaN,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.07927755134659954,
      "grad_norm": NaN,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.08183489171261887,
      "grad_norm": NaN,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.08439223207863822,
      "grad_norm": NaN,
      "learning_rate": 8.204865162773613e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.08694957244465755,
      "grad_norm": NaN,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0895069128106769,
      "grad_norm": NaN,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.09206425317669624,
      "grad_norm": NaN,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.09462159354271557,
      "grad_norm": NaN,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.09717893390873492,
      "grad_norm": NaN,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.09973627427475426,
      "grad_norm": NaN,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.10229361464077359,
      "grad_norm": NaN,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.10485095500679294,
      "grad_norm": NaN,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.10740829537281228,
      "grad_norm": NaN,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.11252297610485096,
      "grad_norm": NaN,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.11508031647087029,
      "grad_norm": NaN,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.11763765683688963,
      "grad_norm": NaN,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.12019499720290898,
      "grad_norm": NaN,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.12275233756892831,
      "grad_norm": NaN,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.12530967793494766,
      "grad_norm": NaN,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.127867018300967,
      "grad_norm": NaN,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.127867018300967,
      "eval_loss": NaN,
      "eval_runtime": 1.4845,
      "eval_samples_per_second": 33.681,
      "eval_steps_per_second": 8.757,
      "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": 5.259104775831552e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}