{
  "best_metric": 0.4557400643825531,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.061354398343431246,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012270879668686248,
      "grad_norm": 0.16277451813220978,
      "learning_rate": 5e-05,
      "loss": 0.3831,
      "step": 1
    },
    {
      "epoch": 0.0012270879668686248,
      "eval_loss": 0.5771195292472839,
      "eval_runtime": 166.9944,
      "eval_samples_per_second": 32.875,
      "eval_steps_per_second": 4.114,
      "step": 1
    },
    {
      "epoch": 0.0024541759337372497,
      "grad_norm": 0.22337406873703003,
      "learning_rate": 0.0001,
      "loss": 0.5452,
      "step": 2
    },
    {
      "epoch": 0.0036812639006058748,
      "grad_norm": 0.24125908315181732,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.592,
      "step": 3
    },
    {
      "epoch": 0.004908351867474499,
      "grad_norm": 0.20937132835388184,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.576,
      "step": 4
    },
    {
      "epoch": 0.0061354398343431244,
      "grad_norm": 0.31259530782699585,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5725,
      "step": 5
    },
    {
      "epoch": 0.0073625278012117495,
      "grad_norm": 0.2729087769985199,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5477,
      "step": 6
    },
    {
      "epoch": 0.008589615768080374,
      "grad_norm": 0.18559280037879944,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5244,
      "step": 7
    },
    {
      "epoch": 0.009816703734948999,
      "grad_norm": 0.18070900440216064,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5123,
      "step": 8
    },
    {
      "epoch": 0.011043791701817624,
      "grad_norm": 0.1876116245985031,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.4676,
      "step": 9
    },
    {
      "epoch": 0.012270879668686249,
      "grad_norm": 0.1876431703567505,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4238,
      "step": 10
    },
    {
      "epoch": 0.013497967635554874,
      "grad_norm": 0.21667154133319855,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.4415,
      "step": 11
    },
    {
      "epoch": 0.014725055602423499,
      "grad_norm": 0.2874070107936859,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.4583,
      "step": 12
    },
    {
      "epoch": 0.015952143569292122,
      "grad_norm": 0.15309716761112213,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3069,
      "step": 13
    },
    {
      "epoch": 0.017179231536160747,
      "grad_norm": 0.20805510878562927,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4467,
      "step": 14
    },
    {
      "epoch": 0.018406319503029372,
      "grad_norm": 0.2222377508878708,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.5267,
      "step": 15
    },
    {
      "epoch": 0.019633407469897998,
      "grad_norm": 0.17002098262310028,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.5049,
      "step": 16
    },
    {
      "epoch": 0.020860495436766623,
      "grad_norm": 0.1514810174703598,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5431,
      "step": 17
    },
    {
      "epoch": 0.022087583403635248,
      "grad_norm": 0.16354860365390778,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5318,
      "step": 18
    },
    {
      "epoch": 0.023314671370503873,
      "grad_norm": 0.18680204451084137,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.5211,
      "step": 19
    },
    {
      "epoch": 0.024541759337372498,
      "grad_norm": 0.17450307309627533,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5126,
      "step": 20
    },
    {
      "epoch": 0.025768847304241123,
      "grad_norm": 0.16676221787929535,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.4745,
      "step": 21
    },
    {
      "epoch": 0.026995935271109748,
      "grad_norm": 0.1670372188091278,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.4372,
      "step": 22
    },
    {
      "epoch": 0.028223023237978373,
      "grad_norm": 0.17722724378108978,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.4098,
      "step": 23
    },
    {
      "epoch": 0.029450111204846998,
      "grad_norm": 0.2052060216665268,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.406,
      "step": 24
    },
    {
      "epoch": 0.030677199171715623,
      "grad_norm": 0.32859280705451965,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4281,
      "step": 25
    },
    {
      "epoch": 0.030677199171715623,
      "eval_loss": 0.4649864137172699,
      "eval_runtime": 167.4814,
      "eval_samples_per_second": 32.78,
      "eval_steps_per_second": 4.102,
      "step": 25
    },
    {
      "epoch": 0.031904287138584245,
      "grad_norm": 0.10585936903953552,
      "learning_rate": 5e-05,
      "loss": 0.3251,
      "step": 26
    },
    {
      "epoch": 0.03313137510545287,
      "grad_norm": 0.18751554191112518,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.4752,
      "step": 27
    },
    {
      "epoch": 0.034358463072321495,
      "grad_norm": 0.21235325932502747,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.5146,
      "step": 28
    },
    {
      "epoch": 0.03558555103919012,
      "grad_norm": 0.20149441063404083,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.5263,
      "step": 29
    },
    {
      "epoch": 0.036812639006058745,
      "grad_norm": 0.17985205352306366,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.5507,
      "step": 30
    },
    {
      "epoch": 0.038039726972927373,
      "grad_norm": 0.1699896901845932,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.5189,
      "step": 31
    },
    {
      "epoch": 0.039266814939795995,
      "grad_norm": 0.143082857131958,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5119,
      "step": 32
    },
    {
      "epoch": 0.040493902906664624,
      "grad_norm": 0.15867877006530762,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.4714,
      "step": 33
    },
    {
      "epoch": 0.041720990873533245,
      "grad_norm": 0.18457220494747162,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4246,
      "step": 34
    },
    {
      "epoch": 0.042948078840401874,
      "grad_norm": 0.18785923719406128,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.4165,
      "step": 35
    },
    {
      "epoch": 0.044175166807270495,
      "grad_norm": 0.20624688267707825,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.3954,
      "step": 36
    },
    {
      "epoch": 0.045402254774139124,
      "grad_norm": 0.2417033463716507,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3974,
      "step": 37
    },
    {
      "epoch": 0.046629342741007745,
      "grad_norm": 0.12633183598518372,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2882,
      "step": 38
    },
    {
      "epoch": 0.047856430707876374,
      "grad_norm": 0.12885819375514984,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.419,
      "step": 39
    },
    {
      "epoch": 0.049083518674744996,
      "grad_norm": 0.15089887380599976,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.5052,
      "step": 40
    },
    {
      "epoch": 0.050310606641613624,
      "grad_norm": 0.15001189708709717,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.5051,
      "step": 41
    },
    {
      "epoch": 0.051537694608482246,
      "grad_norm": 0.15896552801132202,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5382,
      "step": 42
    },
    {
      "epoch": 0.05276478257535087,
      "grad_norm": 0.1471940577030182,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.5069,
      "step": 43
    },
    {
      "epoch": 0.053991870542219496,
      "grad_norm": 0.15487565100193024,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5298,
      "step": 44
    },
    {
      "epoch": 0.05521895850908812,
      "grad_norm": 0.1594659984111786,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.5101,
      "step": 45
    },
    {
      "epoch": 0.056446046475956746,
      "grad_norm": 0.1511322557926178,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.4587,
      "step": 46
    },
    {
      "epoch": 0.05767313444282537,
      "grad_norm": 0.1548001766204834,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.4077,
      "step": 47
    },
    {
      "epoch": 0.058900222409693996,
      "grad_norm": 0.16782091557979584,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.3926,
      "step": 48
    },
    {
      "epoch": 0.06012731037656262,
      "grad_norm": 0.2028161883354187,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.3914,
      "step": 49
    },
    {
      "epoch": 0.061354398343431246,
      "grad_norm": 0.3365857005119324,
      "learning_rate": 0.0,
      "loss": 0.3852,
      "step": 50
    },
    {
      "epoch": 0.061354398343431246,
      "eval_loss": 0.4557400643825531,
      "eval_runtime": 167.4314,
      "eval_samples_per_second": 32.79,
      "eval_steps_per_second": 4.103,
      "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": 5.969948642440643e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}