{
  "best_metric": 1.5269875526428223,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.012006423436538549,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024012846873077096,
      "grad_norm": 0.18527132272720337,
      "learning_rate": 5e-05,
      "loss": 1.4195,
      "step": 1
    },
    {
      "epoch": 0.00024012846873077096,
      "eval_loss": 2.0390498638153076,
      "eval_runtime": 1155.0488,
      "eval_samples_per_second": 24.29,
      "eval_steps_per_second": 3.036,
      "step": 1
    },
    {
      "epoch": 0.0004802569374615419,
      "grad_norm": 0.23116692900657654,
      "learning_rate": 0.0001,
      "loss": 1.5498,
      "step": 2
    },
    {
      "epoch": 0.0007203854061923129,
      "grad_norm": 0.24923942983150482,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6402,
      "step": 3
    },
    {
      "epoch": 0.0009605138749230838,
      "grad_norm": 0.33614450693130493,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.7196,
      "step": 4
    },
    {
      "epoch": 0.0012006423436538548,
      "grad_norm": 0.36924055218696594,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7367,
      "step": 5
    },
    {
      "epoch": 0.0014407708123846258,
      "grad_norm": 0.371552973985672,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7168,
      "step": 6
    },
    {
      "epoch": 0.0016808992811153968,
      "grad_norm": 0.34694090485572815,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.8259,
      "step": 7
    },
    {
      "epoch": 0.0019210277498461676,
      "grad_norm": 0.3056355118751526,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7686,
      "step": 8
    },
    {
      "epoch": 0.0021611562185769387,
      "grad_norm": 0.29312482476234436,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.787,
      "step": 9
    },
    {
      "epoch": 0.0024012846873077095,
      "grad_norm": 0.320833683013916,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8585,
      "step": 10
    },
    {
      "epoch": 0.0026414131560384808,
      "grad_norm": 0.402270644903183,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8626,
      "step": 11
    },
    {
      "epoch": 0.0028815416247692516,
      "grad_norm": 0.4543990194797516,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9568,
      "step": 12
    },
    {
      "epoch": 0.0031216700935000224,
      "grad_norm": 0.3918941020965576,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3646,
      "step": 13
    },
    {
      "epoch": 0.0033617985622307936,
      "grad_norm": 0.40506842732429504,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3939,
      "step": 14
    },
    {
      "epoch": 0.0036019270309615645,
      "grad_norm": 0.3427084982395172,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.4416,
      "step": 15
    },
    {
      "epoch": 0.0038420554996923353,
      "grad_norm": 0.2760331630706787,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.4962,
      "step": 16
    },
    {
      "epoch": 0.004082183968423106,
      "grad_norm": 0.257813036441803,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.4571,
      "step": 17
    },
    {
      "epoch": 0.004322312437153877,
      "grad_norm": 0.18276511132717133,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5071,
      "step": 18
    },
    {
      "epoch": 0.004562440905884649,
      "grad_norm": 0.1987859308719635,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.5773,
      "step": 19
    },
    {
      "epoch": 0.004802569374615419,
      "grad_norm": 0.24936237931251526,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6188,
      "step": 20
    },
    {
      "epoch": 0.00504269784334619,
      "grad_norm": 0.24859172105789185,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6216,
      "step": 21
    },
    {
      "epoch": 0.0052828263120769615,
      "grad_norm": 0.281144380569458,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6582,
      "step": 22
    },
    {
      "epoch": 0.005522954780807732,
      "grad_norm": 0.3248162567615509,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.7176,
      "step": 23
    },
    {
      "epoch": 0.005763083249538503,
      "grad_norm": 0.34245750308036804,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.758,
      "step": 24
    },
    {
      "epoch": 0.006003211718269274,
      "grad_norm": 0.5346644520759583,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.8896,
      "step": 25
    },
    {
      "epoch": 0.006003211718269274,
      "eval_loss": 1.55069100856781,
      "eval_runtime": 1158.5198,
      "eval_samples_per_second": 24.217,
      "eval_steps_per_second": 3.027,
      "step": 25
    },
    {
      "epoch": 0.006243340187000045,
      "grad_norm": 0.08969517797231674,
      "learning_rate": 5e-05,
      "loss": 1.2936,
      "step": 26
    },
    {
      "epoch": 0.006483468655730816,
      "grad_norm": 0.11303842067718506,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.3628,
      "step": 27
    },
    {
      "epoch": 0.006723597124461587,
      "grad_norm": 0.12476766109466553,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.451,
      "step": 28
    },
    {
      "epoch": 0.006963725593192358,
      "grad_norm": 0.15192772448062897,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.4926,
      "step": 29
    },
    {
      "epoch": 0.007203854061923129,
      "grad_norm": 0.1468016803264618,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.428,
      "step": 30
    },
    {
      "epoch": 0.0074439825306539,
      "grad_norm": 0.16281750798225403,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.5421,
      "step": 31
    },
    {
      "epoch": 0.007684110999384671,
      "grad_norm": 0.17703953385353088,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5468,
      "step": 32
    },
    {
      "epoch": 0.007924239468115442,
      "grad_norm": 0.1892644166946411,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.5334,
      "step": 33
    },
    {
      "epoch": 0.008164367936846212,
      "grad_norm": 0.2066446989774704,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5535,
      "step": 34
    },
    {
      "epoch": 0.008404496405576984,
      "grad_norm": 0.22278033196926117,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.6071,
      "step": 35
    },
    {
      "epoch": 0.008644624874307755,
      "grad_norm": 0.31610944867134094,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.7292,
      "step": 36
    },
    {
      "epoch": 0.008884753343038525,
      "grad_norm": 0.3492298722267151,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.822,
      "step": 37
    },
    {
      "epoch": 0.009124881811769297,
      "grad_norm": 0.11775483191013336,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.3414,
      "step": 38
    },
    {
      "epoch": 0.009365010280500068,
      "grad_norm": 0.11511360853910446,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.3609,
      "step": 39
    },
    {
      "epoch": 0.009605138749230838,
      "grad_norm": 0.14886504411697388,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.3542,
      "step": 40
    },
    {
      "epoch": 0.00984526721796161,
      "grad_norm": 0.12947678565979004,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.3978,
      "step": 41
    },
    {
      "epoch": 0.01008539568669238,
      "grad_norm": 0.14663155376911163,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4352,
      "step": 42
    },
    {
      "epoch": 0.010325524155423151,
      "grad_norm": 0.151982843875885,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.5166,
      "step": 43
    },
    {
      "epoch": 0.010565652624153923,
      "grad_norm": 0.1591339111328125,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.528,
      "step": 44
    },
    {
      "epoch": 0.010805781092884693,
      "grad_norm": 0.17459267377853394,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.589,
      "step": 45
    },
    {
      "epoch": 0.011045909561615464,
      "grad_norm": 0.1837066113948822,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.5155,
      "step": 46
    },
    {
      "epoch": 0.011286038030346236,
      "grad_norm": 0.19872833788394928,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.5935,
      "step": 47
    },
    {
      "epoch": 0.011526166499077006,
      "grad_norm": 0.23636873066425323,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.6234,
      "step": 48
    },
    {
      "epoch": 0.011766294967807777,
      "grad_norm": 0.260368287563324,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.7284,
      "step": 49
    },
    {
      "epoch": 0.012006423436538549,
      "grad_norm": 0.39386460185050964,
      "learning_rate": 0.0,
      "loss": 1.8102,
      "step": 50
    },
    {
      "epoch": 0.012006423436538549,
      "eval_loss": 1.5269875526428223,
      "eval_runtime": 1156.4327,
      "eval_samples_per_second": 24.261,
      "eval_steps_per_second": 3.033,
      "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": 1.0234754251431608e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}