{
  "best_metric": 1.1364797353744507,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01098222252728396,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021964445054567917,
      "grad_norm": 132.0096435546875,
      "learning_rate": 5e-05,
      "loss": 56.2272,
      "step": 1
    },
    {
      "epoch": 0.00021964445054567917,
      "eval_loss": 4.680656433105469,
      "eval_runtime": 992.0807,
      "eval_samples_per_second": 30.917,
      "eval_steps_per_second": 3.865,
      "step": 1
    },
    {
      "epoch": 0.00043928890109135835,
      "grad_norm": 147.16964721679688,
      "learning_rate": 0.0001,
      "loss": 60.1614,
      "step": 2
    },
    {
      "epoch": 0.0006589333516370375,
      "grad_norm": 140.5137176513672,
      "learning_rate": 9.989294616193017e-05,
      "loss": 49.5918,
      "step": 3
    },
    {
      "epoch": 0.0008785778021827167,
      "grad_norm": 148.8556365966797,
      "learning_rate": 9.957224306869053e-05,
      "loss": 40.4332,
      "step": 4
    },
    {
      "epoch": 0.001098222252728396,
      "grad_norm": 129.59486389160156,
      "learning_rate": 9.903926402016153e-05,
      "loss": 28.5979,
      "step": 5
    },
    {
      "epoch": 0.001317866703274075,
      "grad_norm": 84.98336029052734,
      "learning_rate": 9.829629131445342e-05,
      "loss": 24.7141,
      "step": 6
    },
    {
      "epoch": 0.0015375111538197543,
      "grad_norm": 78.56539154052734,
      "learning_rate": 9.73465064747553e-05,
      "loss": 31.8631,
      "step": 7
    },
    {
      "epoch": 0.0017571556043654334,
      "grad_norm": 62.94215774536133,
      "learning_rate": 9.619397662556435e-05,
      "loss": 34.4402,
      "step": 8
    },
    {
      "epoch": 0.0019768000549111125,
      "grad_norm": 56.47575378417969,
      "learning_rate": 9.484363707663442e-05,
      "loss": 29.8337,
      "step": 9
    },
    {
      "epoch": 0.002196444505456792,
      "grad_norm": 56.237850189208984,
      "learning_rate": 9.330127018922194e-05,
      "loss": 29.8984,
      "step": 10
    },
    {
      "epoch": 0.002416088956002471,
      "grad_norm": 46.385520935058594,
      "learning_rate": 9.157348061512727e-05,
      "loss": 26.8258,
      "step": 11
    },
    {
      "epoch": 0.00263573340654815,
      "grad_norm": 49.22343826293945,
      "learning_rate": 8.966766701456177e-05,
      "loss": 24.3184,
      "step": 12
    },
    {
      "epoch": 0.002855377857093829,
      "grad_norm": 41.802608489990234,
      "learning_rate": 8.759199037394887e-05,
      "loss": 21.5658,
      "step": 13
    },
    {
      "epoch": 0.0030750223076395087,
      "grad_norm": 33.37959289550781,
      "learning_rate": 8.535533905932738e-05,
      "loss": 21.5485,
      "step": 14
    },
    {
      "epoch": 0.0032946667581851877,
      "grad_norm": 32.71705627441406,
      "learning_rate": 8.296729075500344e-05,
      "loss": 21.1938,
      "step": 15
    },
    {
      "epoch": 0.003514311208730867,
      "grad_norm": 29.703275680541992,
      "learning_rate": 8.043807145043604e-05,
      "loss": 19.3425,
      "step": 16
    },
    {
      "epoch": 0.0037339556592765463,
      "grad_norm": 30.31759262084961,
      "learning_rate": 7.777851165098012e-05,
      "loss": 18.1734,
      "step": 17
    },
    {
      "epoch": 0.003953600109822225,
      "grad_norm": 32.03312301635742,
      "learning_rate": 7.500000000000001e-05,
      "loss": 16.1639,
      "step": 18
    },
    {
      "epoch": 0.004173244560367904,
      "grad_norm": 32.516746520996094,
      "learning_rate": 7.211443451095007e-05,
      "loss": 17.4671,
      "step": 19
    },
    {
      "epoch": 0.004392889010913584,
      "grad_norm": 35.05018997192383,
      "learning_rate": 6.91341716182545e-05,
      "loss": 22.4038,
      "step": 20
    },
    {
      "epoch": 0.0046125334614592626,
      "grad_norm": 35.151702880859375,
      "learning_rate": 6.607197326515808e-05,
      "loss": 24.8124,
      "step": 21
    },
    {
      "epoch": 0.004832177912004942,
      "grad_norm": 33.55155944824219,
      "learning_rate": 6.294095225512603e-05,
      "loss": 24.1456,
      "step": 22
    },
    {
      "epoch": 0.0050518223625506216,
      "grad_norm": 34.70973205566406,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 25.0037,
      "step": 23
    },
    {
      "epoch": 0.0052714668130963,
      "grad_norm": 34.845760345458984,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 21.6553,
      "step": 24
    },
    {
      "epoch": 0.00549111126364198,
      "grad_norm": 36.462764739990234,
      "learning_rate": 5.327015646150716e-05,
      "loss": 19.4489,
      "step": 25
    },
    {
      "epoch": 0.00549111126364198,
      "eval_loss": 1.238913655281067,
      "eval_runtime": 1018.5102,
      "eval_samples_per_second": 30.115,
      "eval_steps_per_second": 3.764,
      "step": 25
    },
    {
      "epoch": 0.005710755714187658,
      "grad_norm": 38.344783782958984,
      "learning_rate": 5e-05,
      "loss": 19.6379,
      "step": 26
    },
    {
      "epoch": 0.005930400164733338,
      "grad_norm": 32.68745422363281,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 18.0308,
      "step": 27
    },
    {
      "epoch": 0.006150044615279017,
      "grad_norm": 29.66469955444336,
      "learning_rate": 4.347369038899744e-05,
      "loss": 17.3707,
      "step": 28
    },
    {
      "epoch": 0.006369689065824696,
      "grad_norm": 26.52182388305664,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 15.5194,
      "step": 29
    },
    {
      "epoch": 0.0065893335163703754,
      "grad_norm": 28.181365966796875,
      "learning_rate": 3.705904774487396e-05,
      "loss": 14.7521,
      "step": 30
    },
    {
      "epoch": 0.006808977966916055,
      "grad_norm": 25.07322120666504,
      "learning_rate": 3.392802673484193e-05,
      "loss": 15.3409,
      "step": 31
    },
    {
      "epoch": 0.007028622417461734,
      "grad_norm": 31.03534507751465,
      "learning_rate": 3.086582838174551e-05,
      "loss": 22.3768,
      "step": 32
    },
    {
      "epoch": 0.007248266868007413,
      "grad_norm": 32.72694396972656,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 22.6606,
      "step": 33
    },
    {
      "epoch": 0.007467911318553093,
      "grad_norm": 29.681062698364258,
      "learning_rate": 2.500000000000001e-05,
      "loss": 23.0873,
      "step": 34
    },
    {
      "epoch": 0.007687555769098771,
      "grad_norm": 30.46506118774414,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 22.9483,
      "step": 35
    },
    {
      "epoch": 0.00790720021964445,
      "grad_norm": 29.355850219726562,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 20.3716,
      "step": 36
    },
    {
      "epoch": 0.00812684467019013,
      "grad_norm": 28.247610092163086,
      "learning_rate": 1.703270924499656e-05,
      "loss": 19.0221,
      "step": 37
    },
    {
      "epoch": 0.008346489120735809,
      "grad_norm": 27.88100814819336,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 16.6165,
      "step": 38
    },
    {
      "epoch": 0.008566133571281487,
      "grad_norm": 25.673690795898438,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 17.2327,
      "step": 39
    },
    {
      "epoch": 0.008785778021827168,
      "grad_norm": 25.04754638671875,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 16.4663,
      "step": 40
    },
    {
      "epoch": 0.009005422472372846,
      "grad_norm": 25.1225528717041,
      "learning_rate": 8.426519384872733e-06,
      "loss": 15.2518,
      "step": 41
    },
    {
      "epoch": 0.009225066922918525,
      "grad_norm": 24.92913246154785,
      "learning_rate": 6.698729810778065e-06,
      "loss": 15.0262,
      "step": 42
    },
    {
      "epoch": 0.009444711373464205,
      "grad_norm": 24.988466262817383,
      "learning_rate": 5.156362923365588e-06,
      "loss": 12.7022,
      "step": 43
    },
    {
      "epoch": 0.009664355824009884,
      "grad_norm": 26.765302658081055,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 18.6385,
      "step": 44
    },
    {
      "epoch": 0.009884000274555563,
      "grad_norm": 26.349815368652344,
      "learning_rate": 2.653493525244721e-06,
      "loss": 22.6444,
      "step": 45
    },
    {
      "epoch": 0.010103644725101243,
      "grad_norm": 28.357736587524414,
      "learning_rate": 1.70370868554659e-06,
      "loss": 23.0244,
      "step": 46
    },
    {
      "epoch": 0.010323289175646922,
      "grad_norm": 28.125967025756836,
      "learning_rate": 9.607359798384785e-07,
      "loss": 20.9472,
      "step": 47
    },
    {
      "epoch": 0.0105429336261926,
      "grad_norm": 27.11406707763672,
      "learning_rate": 4.277569313094809e-07,
      "loss": 19.9431,
      "step": 48
    },
    {
      "epoch": 0.01076257807673828,
      "grad_norm": 31.245771408081055,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 21.9699,
      "step": 49
    },
    {
      "epoch": 0.01098222252728396,
      "grad_norm": 28.27548599243164,
      "learning_rate": 0.0,
      "loss": 17.7171,
      "step": 50
    },
    {
      "epoch": 0.01098222252728396,
      "eval_loss": 1.1364797353744507,
      "eval_runtime": 1003.4143,
      "eval_samples_per_second": 30.568,
      "eval_steps_per_second": 3.821,
      "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": 5.896147371137434e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}