{
  "best_metric": 0.6133490204811096,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.26622296173044924,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005324459234608985,
      "grad_norm": 18.178590774536133,
      "learning_rate": 5e-05,
      "loss": 8.5952,
      "step": 1
    },
    {
      "epoch": 0.005324459234608985,
      "eval_loss": 9.400318145751953,
      "eval_runtime": 18.5977,
      "eval_samples_per_second": 68.019,
      "eval_steps_per_second": 8.549,
      "step": 1
    },
    {
      "epoch": 0.01064891846921797,
      "grad_norm": 18.524410247802734,
      "learning_rate": 0.0001,
      "loss": 9.3788,
      "step": 2
    },
    {
      "epoch": 0.015973377703826955,
      "grad_norm": 19.018756866455078,
      "learning_rate": 9.989294616193017e-05,
      "loss": 8.7897,
      "step": 3
    },
    {
      "epoch": 0.02129783693843594,
      "grad_norm": 20.549850463867188,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.7922,
      "step": 4
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 16.51919174194336,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.5688,
      "step": 5
    },
    {
      "epoch": 0.03194675540765391,
      "grad_norm": 17.26973533630371,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.8683,
      "step": 6
    },
    {
      "epoch": 0.03727121464226289,
      "grad_norm": 17.099246978759766,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.3049,
      "step": 7
    },
    {
      "epoch": 0.04259567387687188,
      "grad_norm": 15.791613578796387,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.7113,
      "step": 8
    },
    {
      "epoch": 0.04792013311148086,
      "grad_norm": 13.631885528564453,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.1921,
      "step": 9
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 10.722579956054688,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.9171,
      "step": 10
    },
    {
      "epoch": 0.05856905158069883,
      "grad_norm": 8.825370788574219,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.6998,
      "step": 11
    },
    {
      "epoch": 0.06389351081530782,
      "grad_norm": 9.83297348022461,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.6349,
      "step": 12
    },
    {
      "epoch": 0.06921797004991681,
      "grad_norm": 8.454965591430664,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.4389,
      "step": 13
    },
    {
      "epoch": 0.07454242928452579,
      "grad_norm": 7.133016586303711,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.068,
      "step": 14
    },
    {
      "epoch": 0.07986688851913477,
      "grad_norm": 5.394034385681152,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.1103,
      "step": 15
    },
    {
      "epoch": 0.08519134775374376,
      "grad_norm": 4.61173677444458,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.7236,
      "step": 16
    },
    {
      "epoch": 0.09051580698835275,
      "grad_norm": 5.1000494956970215,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6841,
      "step": 17
    },
    {
      "epoch": 0.09584026622296173,
      "grad_norm": 4.409814834594727,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5031,
      "step": 18
    },
    {
      "epoch": 0.10116472545757071,
      "grad_norm": 4.465449810028076,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.6356,
      "step": 19
    },
    {
      "epoch": 0.1064891846921797,
      "grad_norm": 3.6205997467041016,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2527,
      "step": 20
    },
    {
      "epoch": 0.11181364392678869,
      "grad_norm": 3.848710775375366,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.0677,
      "step": 21
    },
    {
      "epoch": 0.11713810316139767,
      "grad_norm": 4.458807468414307,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.1782,
      "step": 22
    },
    {
      "epoch": 0.12246256239600666,
      "grad_norm": 5.331320762634277,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.1036,
      "step": 23
    },
    {
      "epoch": 0.12778702163061564,
      "grad_norm": 6.583466529846191,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.1917,
      "step": 24
    },
    {
      "epoch": 0.13311148086522462,
      "grad_norm": 8.270636558532715,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5809,
      "step": 25
    },
    {
      "epoch": 0.13311148086522462,
      "eval_loss": 1.025231957435608,
      "eval_runtime": 18.5274,
      "eval_samples_per_second": 68.277,
      "eval_steps_per_second": 8.582,
      "step": 25
    },
    {
      "epoch": 0.13843594009983362,
      "grad_norm": 6.450296878814697,
      "learning_rate": 5e-05,
      "loss": 1.0312,
      "step": 26
    },
    {
      "epoch": 0.1437603993344426,
      "grad_norm": 5.499378681182861,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.0271,
      "step": 27
    },
    {
      "epoch": 0.14908485856905157,
      "grad_norm": 4.80499267578125,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.8741,
      "step": 28
    },
    {
      "epoch": 0.15440931780366057,
      "grad_norm": 4.07858943939209,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.8599,
      "step": 29
    },
    {
      "epoch": 0.15973377703826955,
      "grad_norm": 3.2893877029418945,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8015,
      "step": 30
    },
    {
      "epoch": 0.16505823627287852,
      "grad_norm": 3.4834606647491455,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7614,
      "step": 31
    },
    {
      "epoch": 0.17038269550748752,
      "grad_norm": 3.2497472763061523,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7866,
      "step": 32
    },
    {
      "epoch": 0.1757071547420965,
      "grad_norm": 4.107487201690674,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.7755,
      "step": 33
    },
    {
      "epoch": 0.1810316139767055,
      "grad_norm": 3.7900607585906982,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6497,
      "step": 34
    },
    {
      "epoch": 0.18635607321131448,
      "grad_norm": 4.495862007141113,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.776,
      "step": 35
    },
    {
      "epoch": 0.19168053244592345,
      "grad_norm": 4.210362434387207,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8306,
      "step": 36
    },
    {
      "epoch": 0.19700499168053245,
      "grad_norm": 5.1397175788879395,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.859,
      "step": 37
    },
    {
      "epoch": 0.20232945091514143,
      "grad_norm": 5.5402936935424805,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8157,
      "step": 38
    },
    {
      "epoch": 0.2076539101497504,
      "grad_norm": 3.070615530014038,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.5884,
      "step": 39
    },
    {
      "epoch": 0.2129783693843594,
      "grad_norm": 3.0448577404022217,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.6112,
      "step": 40
    },
    {
      "epoch": 0.21830282861896838,
      "grad_norm": 3.166132926940918,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.6329,
      "step": 41
    },
    {
      "epoch": 0.22362728785357738,
      "grad_norm": 2.86126971244812,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4517,
      "step": 42
    },
    {
      "epoch": 0.22895174708818636,
      "grad_norm": 3.097123384475708,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.5897,
      "step": 43
    },
    {
      "epoch": 0.23427620632279533,
      "grad_norm": 2.668059825897217,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.4817,
      "step": 44
    },
    {
      "epoch": 0.23960066555740434,
      "grad_norm": 2.4491469860076904,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.4798,
      "step": 45
    },
    {
      "epoch": 0.2449251247920133,
      "grad_norm": 4.0405778884887695,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.5788,
      "step": 46
    },
    {
      "epoch": 0.2502495840266223,
      "grad_norm": 2.962510108947754,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.4239,
      "step": 47
    },
    {
      "epoch": 0.2555740432612313,
      "grad_norm": 3.4761126041412354,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.5796,
      "step": 48
    },
    {
      "epoch": 0.2608985024958403,
      "grad_norm": 3.6893534660339355,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.6451,
      "step": 49
    },
    {
      "epoch": 0.26622296173044924,
      "grad_norm": 6.921513080596924,
      "learning_rate": 0.0,
      "loss": 1.1654,
      "step": 50
    },
    {
      "epoch": 0.26622296173044924,
      "eval_loss": 0.6133490204811096,
      "eval_runtime": 18.5142,
      "eval_samples_per_second": 68.326,
      "eval_steps_per_second": 8.588,
      "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": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}