{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.16454134101192924,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003290826820238585,
      "grad_norm": 1.039158821105957,
      "learning_rate": 5e-05,
      "loss": 1.8771,
      "step": 1
    },
    {
      "epoch": 0.003290826820238585,
      "eval_loss": NaN,
      "eval_runtime": 69.799,
      "eval_samples_per_second": 29.327,
      "eval_steps_per_second": 3.668,
      "step": 1
    },
    {
      "epoch": 0.00658165364047717,
      "grad_norm": 1.0197597742080688,
      "learning_rate": 0.0001,
      "loss": 1.8875,
      "step": 2
    },
    {
      "epoch": 0.009872480460715755,
      "grad_norm": 0.9108155965805054,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.8816,
      "step": 3
    },
    {
      "epoch": 0.01316330728095434,
      "grad_norm": 0.7009238600730896,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.759,
      "step": 4
    },
    {
      "epoch": 0.016454134101192924,
      "grad_norm": 1.2861307859420776,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7925,
      "step": 5
    },
    {
      "epoch": 0.01974496092143151,
      "grad_norm": 0.8928821086883545,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7698,
      "step": 6
    },
    {
      "epoch": 0.023035787741670095,
      "grad_norm": 0.5309975743293762,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.7075,
      "step": 7
    },
    {
      "epoch": 0.02632661456190868,
      "grad_norm": 0.4590210020542145,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6672,
      "step": 8
    },
    {
      "epoch": 0.029617441382147263,
      "grad_norm": 0.48888978362083435,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6435,
      "step": 9
    },
    {
      "epoch": 0.03290826820238585,
      "grad_norm": 0.510526716709137,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6777,
      "step": 10
    },
    {
      "epoch": 0.03619909502262444,
      "grad_norm": 0.5071189403533936,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.6886,
      "step": 11
    },
    {
      "epoch": 0.03948992184286302,
      "grad_norm": 0.528242826461792,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.6991,
      "step": 12
    },
    {
      "epoch": 0.0427807486631016,
      "grad_norm": 0.5126593708992004,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.5474,
      "step": 13
    },
    {
      "epoch": 0.04607157548334019,
      "grad_norm": 0.5633126497268677,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5923,
      "step": 14
    },
    {
      "epoch": 0.04936240230357877,
      "grad_norm": 0.5548191666603088,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5197,
      "step": 15
    },
    {
      "epoch": 0.05265322912381736,
      "grad_norm": 0.4316805601119995,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5417,
      "step": 16
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.3394129276275635,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.5373,
      "step": 17
    },
    {
      "epoch": 0.059234882764294526,
      "grad_norm": 0.3246888816356659,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5475,
      "step": 18
    },
    {
      "epoch": 0.06252570958453312,
      "grad_norm": 0.3448064625263214,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.5234,
      "step": 19
    },
    {
      "epoch": 0.0658165364047717,
      "grad_norm": 0.3767080307006836,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5428,
      "step": 20
    },
    {
      "epoch": 0.06910736322501028,
      "grad_norm": 0.3699794411659241,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.4891,
      "step": 21
    },
    {
      "epoch": 0.07239819004524888,
      "grad_norm": 0.39573559165000916,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5128,
      "step": 22
    },
    {
      "epoch": 0.07568901686548746,
      "grad_norm": 0.3921695649623871,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5184,
      "step": 23
    },
    {
      "epoch": 0.07897984368572604,
      "grad_norm": 0.43741467595100403,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.5545,
      "step": 24
    },
    {
      "epoch": 0.08227067050596462,
      "grad_norm": 0.5433678030967712,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5304,
      "step": 25
    },
    {
      "epoch": 0.08227067050596462,
      "eval_loss": NaN,
      "eval_runtime": 69.5401,
      "eval_samples_per_second": 29.436,
      "eval_steps_per_second": 3.681,
      "step": 25
    },
    {
      "epoch": 0.0855614973262032,
      "grad_norm": 0.3675021231174469,
      "learning_rate": 5e-05,
      "loss": 1.4677,
      "step": 26
    },
    {
      "epoch": 0.0888523241464418,
      "grad_norm": 0.3743444085121155,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.4981,
      "step": 27
    },
    {
      "epoch": 0.09214315096668038,
      "grad_norm": 0.38730910420417786,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.4948,
      "step": 28
    },
    {
      "epoch": 0.09543397778691896,
      "grad_norm": 0.3946470618247986,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.4812,
      "step": 29
    },
    {
      "epoch": 0.09872480460715755,
      "grad_norm": 0.3759434223175049,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.4756,
      "step": 30
    },
    {
      "epoch": 0.10201563142739613,
      "grad_norm": 0.36649543046951294,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.4756,
      "step": 31
    },
    {
      "epoch": 0.10530645824763472,
      "grad_norm": 0.397172212600708,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4794,
      "step": 32
    },
    {
      "epoch": 0.1085972850678733,
      "grad_norm": 0.3425104022026062,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.4798,
      "step": 33
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 0.37429553270339966,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.4882,
      "step": 34
    },
    {
      "epoch": 0.11517893870835047,
      "grad_norm": 0.4080633521080017,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.4917,
      "step": 35
    },
    {
      "epoch": 0.11846976552858905,
      "grad_norm": 0.40952998399734497,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.4858,
      "step": 36
    },
    {
      "epoch": 0.12176059234882765,
      "grad_norm": 0.5022099614143372,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.5295,
      "step": 37
    },
    {
      "epoch": 0.12505141916906623,
      "grad_norm": 0.38732391595840454,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4484,
      "step": 38
    },
    {
      "epoch": 0.12834224598930483,
      "grad_norm": 0.3115442097187042,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.4107,
      "step": 39
    },
    {
      "epoch": 0.1316330728095434,
      "grad_norm": 0.29826825857162476,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.4337,
      "step": 40
    },
    {
      "epoch": 0.134923899629782,
      "grad_norm": 0.26260218024253845,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.4357,
      "step": 41
    },
    {
      "epoch": 0.13821472645002056,
      "grad_norm": 0.27064716815948486,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4669,
      "step": 42
    },
    {
      "epoch": 0.14150555327025915,
      "grad_norm": 0.2965468168258667,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.476,
      "step": 43
    },
    {
      "epoch": 0.14479638009049775,
      "grad_norm": 0.2908375859260559,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4166,
      "step": 44
    },
    {
      "epoch": 0.14808720691073632,
      "grad_norm": 0.2952311336994171,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.4736,
      "step": 45
    },
    {
      "epoch": 0.15137803373097491,
      "grad_norm": 0.3133932650089264,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.4653,
      "step": 46
    },
    {
      "epoch": 0.15466886055121348,
      "grad_norm": 0.3325834572315216,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.5009,
      "step": 47
    },
    {
      "epoch": 0.15795968737145208,
      "grad_norm": 0.3826364278793335,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.4529,
      "step": 48
    },
    {
      "epoch": 0.16125051419169067,
      "grad_norm": 0.42253777384757996,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.4926,
      "step": 49
    },
    {
      "epoch": 0.16454134101192924,
      "grad_norm": 0.6342712640762329,
      "learning_rate": 0.0,
      "loss": 1.5481,
      "step": 50
    },
    {
      "epoch": 0.16454134101192924,
      "eval_loss": NaN,
      "eval_runtime": 69.9353,
      "eval_samples_per_second": 29.27,
      "eval_steps_per_second": 3.661,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.26462276232151e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}