{
  "best_metric": 0.009789057075977325,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.011268875366238449,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000225377507324769,
      "grad_norm": 11.222125053405762,
      "learning_rate": 5e-05,
      "loss": 6.9209,
      "step": 1
    },
    {
      "epoch": 0.000225377507324769,
      "eval_loss": 7.1420392990112305,
      "eval_runtime": 915.8971,
      "eval_samples_per_second": 32.637,
      "eval_steps_per_second": 4.08,
      "step": 1
    },
    {
      "epoch": 0.000450755014649538,
      "grad_norm": 11.997888565063477,
      "learning_rate": 0.0001,
      "loss": 6.7865,
      "step": 2
    },
    {
      "epoch": 0.000676132521974307,
      "grad_norm": 11.38868236541748,
      "learning_rate": 9.989294616193017e-05,
      "loss": 6.1872,
      "step": 3
    },
    {
      "epoch": 0.000901510029299076,
      "grad_norm": 11.744606018066406,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.135,
      "step": 4
    },
    {
      "epoch": 0.001126887536623845,
      "grad_norm": 10.756353378295898,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9713,
      "step": 5
    },
    {
      "epoch": 0.001352265043948614,
      "grad_norm": 6.225836753845215,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.6561,
      "step": 6
    },
    {
      "epoch": 0.0015776425512733828,
      "grad_norm": 1.7988471984863281,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.1613,
      "step": 7
    },
    {
      "epoch": 0.001803020058598152,
      "grad_norm": 1.5720716714859009,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0904,
      "step": 8
    },
    {
      "epoch": 0.002028397565922921,
      "grad_norm": 0.4129374623298645,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0191,
      "step": 9
    },
    {
      "epoch": 0.00225377507324769,
      "grad_norm": 1.2225449085235596,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0457,
      "step": 10
    },
    {
      "epoch": 0.0024791525805724587,
      "grad_norm": 0.7639326453208923,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0273,
      "step": 11
    },
    {
      "epoch": 0.002704530087897228,
      "grad_norm": 0.3936360776424408,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0195,
      "step": 12
    },
    {
      "epoch": 0.002929907595221997,
      "grad_norm": 0.6868224143981934,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0211,
      "step": 13
    },
    {
      "epoch": 0.0031552851025467656,
      "grad_norm": 0.9585989713668823,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0119,
      "step": 14
    },
    {
      "epoch": 0.0033806626098715348,
      "grad_norm": 0.6743549108505249,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0108,
      "step": 15
    },
    {
      "epoch": 0.003606040117196304,
      "grad_norm": 0.48703205585479736,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0174,
      "step": 16
    },
    {
      "epoch": 0.0038314176245210726,
      "grad_norm": 0.5217801928520203,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0102,
      "step": 17
    },
    {
      "epoch": 0.004056795131845842,
      "grad_norm": 0.7212764024734497,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0047,
      "step": 18
    },
    {
      "epoch": 0.00428217263917061,
      "grad_norm": 0.631219744682312,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0103,
      "step": 19
    },
    {
      "epoch": 0.00450755014649538,
      "grad_norm": 0.4086368680000305,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0096,
      "step": 20
    },
    {
      "epoch": 0.004732927653820149,
      "grad_norm": 0.2981169819831848,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0152,
      "step": 21
    },
    {
      "epoch": 0.004958305161144917,
      "grad_norm": 0.2883327007293701,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0114,
      "step": 22
    },
    {
      "epoch": 0.005183682668469687,
      "grad_norm": 0.7288554310798645,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.016,
      "step": 23
    },
    {
      "epoch": 0.005409060175794456,
      "grad_norm": 0.6198459267616272,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0139,
      "step": 24
    },
    {
      "epoch": 0.005634437683119224,
      "grad_norm": 0.46115440130233765,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0232,
      "step": 25
    },
    {
      "epoch": 0.005634437683119224,
      "eval_loss": 0.016865907236933708,
      "eval_runtime": 2000.6321,
      "eval_samples_per_second": 14.941,
      "eval_steps_per_second": 1.868,
      "step": 25
    },
    {
      "epoch": 0.005859815190443994,
      "grad_norm": 0.43277430534362793,
      "learning_rate": 5e-05,
      "loss": 0.0169,
      "step": 26
    },
    {
      "epoch": 0.006085192697768763,
      "grad_norm": 0.12261365354061127,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0088,
      "step": 27
    },
    {
      "epoch": 0.006310570205093531,
      "grad_norm": 0.36166757345199585,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0105,
      "step": 28
    },
    {
      "epoch": 0.006535947712418301,
      "grad_norm": 0.2865087389945984,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0072,
      "step": 29
    },
    {
      "epoch": 0.0067613252197430695,
      "grad_norm": 0.13543976843357086,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0089,
      "step": 30
    },
    {
      "epoch": 0.006986702727067838,
      "grad_norm": 0.32603442668914795,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0081,
      "step": 31
    },
    {
      "epoch": 0.007212080234392608,
      "grad_norm": 0.07940559834241867,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0042,
      "step": 32
    },
    {
      "epoch": 0.0074374577417173765,
      "grad_norm": 0.6605622172355652,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0211,
      "step": 33
    },
    {
      "epoch": 0.007662835249042145,
      "grad_norm": 0.45941802859306335,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0177,
      "step": 34
    },
    {
      "epoch": 0.007888212756366914,
      "grad_norm": 0.34309831261634827,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0087,
      "step": 35
    },
    {
      "epoch": 0.008113590263691683,
      "grad_norm": 0.34011223912239075,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0104,
      "step": 36
    },
    {
      "epoch": 0.008338967771016453,
      "grad_norm": 0.2117564082145691,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.005,
      "step": 37
    },
    {
      "epoch": 0.00856434527834122,
      "grad_norm": 0.09729141741991043,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0082,
      "step": 38
    },
    {
      "epoch": 0.00878972278566599,
      "grad_norm": 0.10410496592521667,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0044,
      "step": 39
    },
    {
      "epoch": 0.00901510029299076,
      "grad_norm": 0.3540576696395874,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0212,
      "step": 40
    },
    {
      "epoch": 0.009240477800315528,
      "grad_norm": 0.6972055435180664,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.013,
      "step": 41
    },
    {
      "epoch": 0.009465855307640297,
      "grad_norm": 0.43922847509384155,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0087,
      "step": 42
    },
    {
      "epoch": 0.009691232814965067,
      "grad_norm": 0.1131017655134201,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0029,
      "step": 43
    },
    {
      "epoch": 0.009916610322289835,
      "grad_norm": 0.3094264566898346,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0085,
      "step": 44
    },
    {
      "epoch": 0.010141987829614604,
      "grad_norm": 0.7499658465385437,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0167,
      "step": 45
    },
    {
      "epoch": 0.010367365336939374,
      "grad_norm": 0.12543810904026031,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0081,
      "step": 46
    },
    {
      "epoch": 0.010592742844264142,
      "grad_norm": 0.12715910375118256,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0063,
      "step": 47
    },
    {
      "epoch": 0.010818120351588911,
      "grad_norm": 0.33462029695510864,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0123,
      "step": 48
    },
    {
      "epoch": 0.01104349785891368,
      "grad_norm": 0.30533668398857117,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0052,
      "step": 49
    },
    {
      "epoch": 0.011268875366238449,
      "grad_norm": 0.3823198676109314,
      "learning_rate": 0.0,
      "loss": 0.0208,
      "step": 50
    },
    {
      "epoch": 0.011268875366238449,
      "eval_loss": 0.009789057075977325,
      "eval_runtime": 1999.7394,
      "eval_samples_per_second": 14.948,
      "eval_steps_per_second": 1.869,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}