{
  "best_metric": 9.093399047851562,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1725997842502697,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003451995685005394,
      "grad_norm": 5.186959266662598,
      "learning_rate": 5e-05,
      "loss": 10.0991,
      "step": 1
    },
    {
      "epoch": 0.003451995685005394,
      "eval_loss": 10.203469276428223,
      "eval_runtime": 4.1653,
      "eval_samples_per_second": 468.636,
      "eval_steps_per_second": 58.58,
      "step": 1
    },
    {
      "epoch": 0.006903991370010788,
      "grad_norm": 4.186983108520508,
      "learning_rate": 0.0001,
      "loss": 10.3691,
      "step": 2
    },
    {
      "epoch": 0.010355987055016181,
      "grad_norm": 3.8803439140319824,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.4165,
      "step": 3
    },
    {
      "epoch": 0.013807982740021575,
      "grad_norm": 3.760660171508789,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.4438,
      "step": 4
    },
    {
      "epoch": 0.017259978425026967,
      "grad_norm": 3.684460163116455,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.2526,
      "step": 5
    },
    {
      "epoch": 0.020711974110032363,
      "grad_norm": 3.600942611694336,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.1124,
      "step": 6
    },
    {
      "epoch": 0.024163969795037755,
      "grad_norm": 3.7263965606689453,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.1312,
      "step": 7
    },
    {
      "epoch": 0.02761596548004315,
      "grad_norm": 3.800443410873413,
      "learning_rate": 9.619397662556435e-05,
      "loss": 9.9276,
      "step": 8
    },
    {
      "epoch": 0.031067961165048542,
      "grad_norm": 3.1530959606170654,
      "learning_rate": 9.484363707663442e-05,
      "loss": 9.82,
      "step": 9
    },
    {
      "epoch": 0.034519956850053934,
      "grad_norm": 3.6164231300354004,
      "learning_rate": 9.330127018922194e-05,
      "loss": 9.6149,
      "step": 10
    },
    {
      "epoch": 0.03797195253505933,
      "grad_norm": 3.733968734741211,
      "learning_rate": 9.157348061512727e-05,
      "loss": 9.6499,
      "step": 11
    },
    {
      "epoch": 0.041423948220064725,
      "grad_norm": 3.502216339111328,
      "learning_rate": 8.966766701456177e-05,
      "loss": 9.4452,
      "step": 12
    },
    {
      "epoch": 0.04487594390507012,
      "grad_norm": 3.3876755237579346,
      "learning_rate": 8.759199037394887e-05,
      "loss": 9.4886,
      "step": 13
    },
    {
      "epoch": 0.04832793959007551,
      "grad_norm": 3.115715503692627,
      "learning_rate": 8.535533905932738e-05,
      "loss": 9.5224,
      "step": 14
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 2.66998028755188,
      "learning_rate": 8.296729075500344e-05,
      "loss": 9.7347,
      "step": 15
    },
    {
      "epoch": 0.0552319309600863,
      "grad_norm": 2.544126033782959,
      "learning_rate": 8.043807145043604e-05,
      "loss": 9.5851,
      "step": 16
    },
    {
      "epoch": 0.05868392664509169,
      "grad_norm": 2.5908780097961426,
      "learning_rate": 7.777851165098012e-05,
      "loss": 9.5565,
      "step": 17
    },
    {
      "epoch": 0.062135922330097085,
      "grad_norm": 2.6538479328155518,
      "learning_rate": 7.500000000000001e-05,
      "loss": 9.5356,
      "step": 18
    },
    {
      "epoch": 0.06558791801510248,
      "grad_norm": 2.6227550506591797,
      "learning_rate": 7.211443451095007e-05,
      "loss": 9.6462,
      "step": 19
    },
    {
      "epoch": 0.06903991370010787,
      "grad_norm": 2.5546512603759766,
      "learning_rate": 6.91341716182545e-05,
      "loss": 9.4895,
      "step": 20
    },
    {
      "epoch": 0.07249190938511327,
      "grad_norm": 2.6019227504730225,
      "learning_rate": 6.607197326515808e-05,
      "loss": 9.3282,
      "step": 21
    },
    {
      "epoch": 0.07594390507011867,
      "grad_norm": 2.911227226257324,
      "learning_rate": 6.294095225512603e-05,
      "loss": 9.26,
      "step": 22
    },
    {
      "epoch": 0.07939590075512405,
      "grad_norm": 3.020165205001831,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 9.1045,
      "step": 23
    },
    {
      "epoch": 0.08284789644012945,
      "grad_norm": 3.556004047393799,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 9.2547,
      "step": 24
    },
    {
      "epoch": 0.08629989212513485,
      "grad_norm": 4.306118011474609,
      "learning_rate": 5.327015646150716e-05,
      "loss": 9.2469,
      "step": 25
    },
    {
      "epoch": 0.08629989212513485,
      "eval_loss": 9.283263206481934,
      "eval_runtime": 4.1585,
      "eval_samples_per_second": 469.395,
      "eval_steps_per_second": 58.674,
      "step": 25
    },
    {
      "epoch": 0.08975188781014024,
      "grad_norm": 2.569988489151001,
      "learning_rate": 5e-05,
      "loss": 9.0943,
      "step": 26
    },
    {
      "epoch": 0.09320388349514563,
      "grad_norm": 2.2123172283172607,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 9.2223,
      "step": 27
    },
    {
      "epoch": 0.09665587918015102,
      "grad_norm": 2.1677656173706055,
      "learning_rate": 4.347369038899744e-05,
      "loss": 9.3813,
      "step": 28
    },
    {
      "epoch": 0.10010787486515642,
      "grad_norm": 2.015392541885376,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 9.4298,
      "step": 29
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 2.0585849285125732,
      "learning_rate": 3.705904774487396e-05,
      "loss": 9.3846,
      "step": 30
    },
    {
      "epoch": 0.1070118662351672,
      "grad_norm": 2.1032018661499023,
      "learning_rate": 3.392802673484193e-05,
      "loss": 9.3408,
      "step": 31
    },
    {
      "epoch": 0.1104638619201726,
      "grad_norm": 2.1967952251434326,
      "learning_rate": 3.086582838174551e-05,
      "loss": 9.2355,
      "step": 32
    },
    {
      "epoch": 0.113915857605178,
      "grad_norm": 2.1703479290008545,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 9.1367,
      "step": 33
    },
    {
      "epoch": 0.11736785329018339,
      "grad_norm": 2.362610340118408,
      "learning_rate": 2.500000000000001e-05,
      "loss": 9.1484,
      "step": 34
    },
    {
      "epoch": 0.12081984897518878,
      "grad_norm": 2.4542195796966553,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 9.0256,
      "step": 35
    },
    {
      "epoch": 0.12427184466019417,
      "grad_norm": 2.764089584350586,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 8.9048,
      "step": 36
    },
    {
      "epoch": 0.12772384034519957,
      "grad_norm": 3.768209457397461,
      "learning_rate": 1.703270924499656e-05,
      "loss": 9.0051,
      "step": 37
    },
    {
      "epoch": 0.13117583603020497,
      "grad_norm": 2.35390305519104,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.9384,
      "step": 38
    },
    {
      "epoch": 0.13462783171521037,
      "grad_norm": 2.088468074798584,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 9.0535,
      "step": 39
    },
    {
      "epoch": 0.13807982740021574,
      "grad_norm": 2.1855905055999756,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 8.9569,
      "step": 40
    },
    {
      "epoch": 0.14153182308522114,
      "grad_norm": 1.9022825956344604,
      "learning_rate": 8.426519384872733e-06,
      "loss": 9.2798,
      "step": 41
    },
    {
      "epoch": 0.14498381877022654,
      "grad_norm": 1.9557679891586304,
      "learning_rate": 6.698729810778065e-06,
      "loss": 9.2705,
      "step": 42
    },
    {
      "epoch": 0.14843581445523193,
      "grad_norm": 1.954206943511963,
      "learning_rate": 5.156362923365588e-06,
      "loss": 9.2386,
      "step": 43
    },
    {
      "epoch": 0.15188781014023733,
      "grad_norm": 1.9455832242965698,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 9.2428,
      "step": 44
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": 2.080592393875122,
      "learning_rate": 2.653493525244721e-06,
      "loss": 9.2137,
      "step": 45
    },
    {
      "epoch": 0.1587918015102481,
      "grad_norm": 2.2040107250213623,
      "learning_rate": 1.70370868554659e-06,
      "loss": 9.1182,
      "step": 46
    },
    {
      "epoch": 0.1622437971952535,
      "grad_norm": 2.43825626373291,
      "learning_rate": 9.607359798384785e-07,
      "loss": 9.0065,
      "step": 47
    },
    {
      "epoch": 0.1656957928802589,
      "grad_norm": 2.649735927581787,
      "learning_rate": 4.277569313094809e-07,
      "loss": 8.9781,
      "step": 48
    },
    {
      "epoch": 0.1691477885652643,
      "grad_norm": 3.2177460193634033,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 8.872,
      "step": 49
    },
    {
      "epoch": 0.1725997842502697,
      "grad_norm": 4.085848808288574,
      "learning_rate": 0.0,
      "loss": 8.8525,
      "step": 50
    },
    {
      "epoch": 0.1725997842502697,
      "eval_loss": 9.093399047851562,
      "eval_runtime": 4.1559,
      "eval_samples_per_second": 469.689,
      "eval_steps_per_second": 58.711,
      "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": 232013797785600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}