{
  "best_metric": 1.05935800075531,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4155844155844156,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008311688311688312,
      "grad_norm": 0.5688855648040771,
      "learning_rate": 5e-05,
      "loss": 1.2675,
      "step": 1
    },
    {
      "epoch": 0.008311688311688312,
      "eval_loss": 1.5061113834381104,
      "eval_runtime": 25.9468,
      "eval_samples_per_second": 31.256,
      "eval_steps_per_second": 3.931,
      "step": 1
    },
    {
      "epoch": 0.016623376623376623,
      "grad_norm": 1.2492280006408691,
      "learning_rate": 0.0001,
      "loss": 1.3997,
      "step": 2
    },
    {
      "epoch": 0.024935064935064935,
      "grad_norm": 1.0303261280059814,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.3554,
      "step": 3
    },
    {
      "epoch": 0.03324675324675325,
      "grad_norm": 0.8673217296600342,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2871,
      "step": 4
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 0.4088221490383148,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.3092,
      "step": 5
    },
    {
      "epoch": 0.04987012987012987,
      "grad_norm": 0.48258668184280396,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4485,
      "step": 6
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 0.5833405256271362,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.4425,
      "step": 7
    },
    {
      "epoch": 0.0664935064935065,
      "grad_norm": 0.6449804306030273,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.4168,
      "step": 8
    },
    {
      "epoch": 0.0748051948051948,
      "grad_norm": 0.8527534008026123,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.3239,
      "step": 9
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 1.1389973163604736,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2837,
      "step": 10
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.9949864745140076,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.1449,
      "step": 11
    },
    {
      "epoch": 0.09974025974025974,
      "grad_norm": 0.9292828440666199,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.0885,
      "step": 12
    },
    {
      "epoch": 0.10805194805194805,
      "grad_norm": 0.516069769859314,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.0868,
      "step": 13
    },
    {
      "epoch": 0.11636363636363636,
      "grad_norm": 1.1467220783233643,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.052,
      "step": 14
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 0.8350916504859924,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.9652,
      "step": 15
    },
    {
      "epoch": 0.132987012987013,
      "grad_norm": 0.5265994071960449,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8324,
      "step": 16
    },
    {
      "epoch": 0.1412987012987013,
      "grad_norm": 0.3528784215450287,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8969,
      "step": 17
    },
    {
      "epoch": 0.1496103896103896,
      "grad_norm": 0.39343854784965515,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3175,
      "step": 18
    },
    {
      "epoch": 0.15792207792207794,
      "grad_norm": 0.41462719440460205,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.352,
      "step": 19
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 0.4772951602935791,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3498,
      "step": 20
    },
    {
      "epoch": 0.17454545454545456,
      "grad_norm": 0.5342058539390564,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.309,
      "step": 21
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.9034503102302551,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.1314,
      "step": 22
    },
    {
      "epoch": 0.19116883116883118,
      "grad_norm": 0.613511860370636,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.1097,
      "step": 23
    },
    {
      "epoch": 0.19948051948051948,
      "grad_norm": 0.6167203783988953,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8848,
      "step": 24
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 1.535559058189392,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.2438,
      "step": 25
    },
    {
      "epoch": 0.2077922077922078,
      "eval_loss": 1.0861386060714722,
      "eval_runtime": 26.149,
      "eval_samples_per_second": 31.015,
      "eval_steps_per_second": 3.901,
      "step": 25
    },
    {
      "epoch": 0.2161038961038961,
      "grad_norm": 0.23987476527690887,
      "learning_rate": 5e-05,
      "loss": 0.9859,
      "step": 26
    },
    {
      "epoch": 0.22441558441558443,
      "grad_norm": 0.36977705359458923,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.9489,
      "step": 27
    },
    {
      "epoch": 0.23272727272727273,
      "grad_norm": 0.28386303782463074,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.8192,
      "step": 28
    },
    {
      "epoch": 0.24103896103896105,
      "grad_norm": 0.28928664326667786,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.8652,
      "step": 29
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 0.4036184549331665,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.0874,
      "step": 30
    },
    {
      "epoch": 0.25766233766233765,
      "grad_norm": 0.4978172481060028,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.3074,
      "step": 31
    },
    {
      "epoch": 0.265974025974026,
      "grad_norm": 0.5747013688087463,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3194,
      "step": 32
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.4833392798900604,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.2504,
      "step": 33
    },
    {
      "epoch": 0.2825974025974026,
      "grad_norm": 0.573775589466095,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.2703,
      "step": 34
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.5862915515899658,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.1775,
      "step": 35
    },
    {
      "epoch": 0.2992207792207792,
      "grad_norm": 0.483033686876297,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.9526,
      "step": 36
    },
    {
      "epoch": 0.30753246753246755,
      "grad_norm": 0.6226116418838501,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.984,
      "step": 37
    },
    {
      "epoch": 0.31584415584415587,
      "grad_norm": 0.2604388892650604,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8811,
      "step": 38
    },
    {
      "epoch": 0.32415584415584414,
      "grad_norm": 0.19333459436893463,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.9441,
      "step": 39
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 0.201664999127388,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.9568,
      "step": 40
    },
    {
      "epoch": 0.3407792207792208,
      "grad_norm": 0.20325258374214172,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.7732,
      "step": 41
    },
    {
      "epoch": 0.3490909090909091,
      "grad_norm": 0.2257876992225647,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8841,
      "step": 42
    },
    {
      "epoch": 0.3574025974025974,
      "grad_norm": 0.3107191026210785,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.307,
      "step": 43
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.3348431885242462,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.2376,
      "step": 44
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 0.35244983434677124,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.3097,
      "step": 45
    },
    {
      "epoch": 0.38233766233766237,
      "grad_norm": 0.3649301826953888,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.1649,
      "step": 46
    },
    {
      "epoch": 0.39064935064935064,
      "grad_norm": 0.412195086479187,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.1256,
      "step": 47
    },
    {
      "epoch": 0.39896103896103896,
      "grad_norm": 0.4812576174736023,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.0379,
      "step": 48
    },
    {
      "epoch": 0.4072727272727273,
      "grad_norm": 0.43518587946891785,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7584,
      "step": 49
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.9060344696044922,
      "learning_rate": 0.0,
      "loss": 1.162,
      "step": 50
    },
    {
      "epoch": 0.4155844155844156,
      "eval_loss": 1.05935800075531,
      "eval_runtime": 26.4737,
      "eval_samples_per_second": 30.634,
      "eval_steps_per_second": 3.853,
      "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": 6.010979195163771e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}