{
  "best_metric": 0.8612159490585327,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05664518869928485,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011329037739856971,
      "grad_norm": 24.65677261352539,
      "learning_rate": 5e-05,
      "loss": 29.7807,
      "step": 1
    },
    {
      "epoch": 0.0011329037739856971,
      "eval_loss": 2.4394071102142334,
      "eval_runtime": 208.2448,
      "eval_samples_per_second": 28.558,
      "eval_steps_per_second": 3.573,
      "step": 1
    },
    {
      "epoch": 0.0022658075479713943,
      "grad_norm": 27.222679138183594,
      "learning_rate": 0.0001,
      "loss": 32.3959,
      "step": 2
    },
    {
      "epoch": 0.003398711321957091,
      "grad_norm": 32.98060607910156,
      "learning_rate": 9.989294616193017e-05,
      "loss": 33.4299,
      "step": 3
    },
    {
      "epoch": 0.0045316150959427886,
      "grad_norm": 30.921926498413086,
      "learning_rate": 9.957224306869053e-05,
      "loss": 29.7122,
      "step": 4
    },
    {
      "epoch": 0.0056645188699284855,
      "grad_norm": 25.687549591064453,
      "learning_rate": 9.903926402016153e-05,
      "loss": 25.1131,
      "step": 5
    },
    {
      "epoch": 0.006797422643914182,
      "grad_norm": 23.132740020751953,
      "learning_rate": 9.829629131445342e-05,
      "loss": 23.3871,
      "step": 6
    },
    {
      "epoch": 0.00793032641789988,
      "grad_norm": 18.85443878173828,
      "learning_rate": 9.73465064747553e-05,
      "loss": 22.1671,
      "step": 7
    },
    {
      "epoch": 0.009063230191885577,
      "grad_norm": 17.62495231628418,
      "learning_rate": 9.619397662556435e-05,
      "loss": 20.573,
      "step": 8
    },
    {
      "epoch": 0.010196133965871273,
      "grad_norm": 14.434099197387695,
      "learning_rate": 9.484363707663442e-05,
      "loss": 17.8481,
      "step": 9
    },
    {
      "epoch": 0.011329037739856971,
      "grad_norm": 15.916144371032715,
      "learning_rate": 9.330127018922194e-05,
      "loss": 16.6761,
      "step": 10
    },
    {
      "epoch": 0.012461941513842669,
      "grad_norm": 14.026975631713867,
      "learning_rate": 9.157348061512727e-05,
      "loss": 14.7903,
      "step": 11
    },
    {
      "epoch": 0.013594845287828365,
      "grad_norm": 14.814682006835938,
      "learning_rate": 8.966766701456177e-05,
      "loss": 16.0327,
      "step": 12
    },
    {
      "epoch": 0.014727749061814063,
      "grad_norm": 16.0185604095459,
      "learning_rate": 8.759199037394887e-05,
      "loss": 18.155,
      "step": 13
    },
    {
      "epoch": 0.01586065283579976,
      "grad_norm": 16.92819595336914,
      "learning_rate": 8.535533905932738e-05,
      "loss": 18.8237,
      "step": 14
    },
    {
      "epoch": 0.016993556609785455,
      "grad_norm": 18.460590362548828,
      "learning_rate": 8.296729075500344e-05,
      "loss": 17.2702,
      "step": 15
    },
    {
      "epoch": 0.018126460383771154,
      "grad_norm": 14.221395492553711,
      "learning_rate": 8.043807145043604e-05,
      "loss": 17.6757,
      "step": 16
    },
    {
      "epoch": 0.01925936415775685,
      "grad_norm": 12.549836158752441,
      "learning_rate": 7.777851165098012e-05,
      "loss": 16.6149,
      "step": 17
    },
    {
      "epoch": 0.020392267931742546,
      "grad_norm": 12.436845779418945,
      "learning_rate": 7.500000000000001e-05,
      "loss": 16.0281,
      "step": 18
    },
    {
      "epoch": 0.021525171705728246,
      "grad_norm": 14.278661727905273,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.6214,
      "step": 19
    },
    {
      "epoch": 0.022658075479713942,
      "grad_norm": 10.886022567749023,
      "learning_rate": 6.91341716182545e-05,
      "loss": 12.6638,
      "step": 20
    },
    {
      "epoch": 0.023790979253699638,
      "grad_norm": 11.73347282409668,
      "learning_rate": 6.607197326515808e-05,
      "loss": 14.8879,
      "step": 21
    },
    {
      "epoch": 0.024923883027685338,
      "grad_norm": 10.711037635803223,
      "learning_rate": 6.294095225512603e-05,
      "loss": 12.5993,
      "step": 22
    },
    {
      "epoch": 0.026056786801671034,
      "grad_norm": 11.942070960998535,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 13.8089,
      "step": 23
    },
    {
      "epoch": 0.02718969057565673,
      "grad_norm": 12.257878303527832,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 14.9371,
      "step": 24
    },
    {
      "epoch": 0.028322594349642426,
      "grad_norm": 13.868196487426758,
      "learning_rate": 5.327015646150716e-05,
      "loss": 13.6081,
      "step": 25
    },
    {
      "epoch": 0.028322594349642426,
      "eval_loss": 0.8853906393051147,
      "eval_runtime": 208.362,
      "eval_samples_per_second": 28.542,
      "eval_steps_per_second": 3.571,
      "step": 25
    },
    {
      "epoch": 0.029455498123628125,
      "grad_norm": 8.992348670959473,
      "learning_rate": 5e-05,
      "loss": 17.9547,
      "step": 26
    },
    {
      "epoch": 0.03058840189761382,
      "grad_norm": 9.770459175109863,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 14.1764,
      "step": 27
    },
    {
      "epoch": 0.03172130567159952,
      "grad_norm": 10.085947036743164,
      "learning_rate": 4.347369038899744e-05,
      "loss": 14.82,
      "step": 28
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 12.546303749084473,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 14.5786,
      "step": 29
    },
    {
      "epoch": 0.03398711321957091,
      "grad_norm": 8.8180513381958,
      "learning_rate": 3.705904774487396e-05,
      "loss": 13.0714,
      "step": 30
    },
    {
      "epoch": 0.03512001699355661,
      "grad_norm": 11.411664962768555,
      "learning_rate": 3.392802673484193e-05,
      "loss": 13.3333,
      "step": 31
    },
    {
      "epoch": 0.03625292076754231,
      "grad_norm": 9.17128849029541,
      "learning_rate": 3.086582838174551e-05,
      "loss": 12.3617,
      "step": 32
    },
    {
      "epoch": 0.037385824541528,
      "grad_norm": 10.2019681930542,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 13.0738,
      "step": 33
    },
    {
      "epoch": 0.0385187283155137,
      "grad_norm": 10.263218879699707,
      "learning_rate": 2.500000000000001e-05,
      "loss": 13.7404,
      "step": 34
    },
    {
      "epoch": 0.0396516320894994,
      "grad_norm": 10.263712882995605,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 12.2719,
      "step": 35
    },
    {
      "epoch": 0.04078453586348509,
      "grad_norm": 12.365837097167969,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 14.4749,
      "step": 36
    },
    {
      "epoch": 0.04191743963747079,
      "grad_norm": 10.982479095458984,
      "learning_rate": 1.703270924499656e-05,
      "loss": 12.8875,
      "step": 37
    },
    {
      "epoch": 0.04305034341145649,
      "grad_norm": 10.957509994506836,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 17.0494,
      "step": 38
    },
    {
      "epoch": 0.044183247185442184,
      "grad_norm": 9.524374961853027,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 16.3195,
      "step": 39
    },
    {
      "epoch": 0.045316150959427884,
      "grad_norm": 8.716954231262207,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 15.2658,
      "step": 40
    },
    {
      "epoch": 0.04644905473341358,
      "grad_norm": 9.489079475402832,
      "learning_rate": 8.426519384872733e-06,
      "loss": 14.4491,
      "step": 41
    },
    {
      "epoch": 0.047581958507399276,
      "grad_norm": 8.325908660888672,
      "learning_rate": 6.698729810778065e-06,
      "loss": 12.4704,
      "step": 42
    },
    {
      "epoch": 0.048714862281384975,
      "grad_norm": 9.202627182006836,
      "learning_rate": 5.156362923365588e-06,
      "loss": 14.4045,
      "step": 43
    },
    {
      "epoch": 0.049847766055370675,
      "grad_norm": 9.588567733764648,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 14.0462,
      "step": 44
    },
    {
      "epoch": 0.05098066982935637,
      "grad_norm": 9.506434440612793,
      "learning_rate": 2.653493525244721e-06,
      "loss": 11.2175,
      "step": 45
    },
    {
      "epoch": 0.05211357360334207,
      "grad_norm": 18.916034698486328,
      "learning_rate": 1.70370868554659e-06,
      "loss": 13.1203,
      "step": 46
    },
    {
      "epoch": 0.05324647737732777,
      "grad_norm": 9.236392974853516,
      "learning_rate": 9.607359798384785e-07,
      "loss": 12.2845,
      "step": 47
    },
    {
      "epoch": 0.05437938115131346,
      "grad_norm": 11.271123886108398,
      "learning_rate": 4.277569313094809e-07,
      "loss": 13.8317,
      "step": 48
    },
    {
      "epoch": 0.05551228492529916,
      "grad_norm": 10.629317283630371,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 13.7083,
      "step": 49
    },
    {
      "epoch": 0.05664518869928485,
      "grad_norm": 13.823080062866211,
      "learning_rate": 0.0,
      "loss": 12.8755,
      "step": 50
    },
    {
      "epoch": 0.05664518869928485,
      "eval_loss": 0.8612159490585327,
      "eval_runtime": 208.3794,
      "eval_samples_per_second": 28.539,
      "eval_steps_per_second": 3.57,
      "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": 2.967137622687744e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}