{
  "best_metric": 4.3903303146362305,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.08708904855214457,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017417809710428913,
      "grad_norm": 980.28076171875,
      "learning_rate": 5e-05,
      "loss": 52.678,
      "step": 1
    },
    {
      "epoch": 0.0017417809710428913,
      "eval_loss": 95.80888366699219,
      "eval_runtime": 127.5975,
      "eval_samples_per_second": 30.314,
      "eval_steps_per_second": 3.793,
      "step": 1
    },
    {
      "epoch": 0.0034835619420857827,
      "grad_norm": 1256.04638671875,
      "learning_rate": 0.0001,
      "loss": 66.1445,
      "step": 2
    },
    {
      "epoch": 0.005225342913128674,
      "grad_norm": 235.8488311767578,
      "learning_rate": 9.989294616193017e-05,
      "loss": 53.9092,
      "step": 3
    },
    {
      "epoch": 0.006967123884171565,
      "grad_norm": 170.13990783691406,
      "learning_rate": 9.957224306869053e-05,
      "loss": 44.056,
      "step": 4
    },
    {
      "epoch": 0.008708904855214456,
      "grad_norm": 211.44520568847656,
      "learning_rate": 9.903926402016153e-05,
      "loss": 37.6098,
      "step": 5
    },
    {
      "epoch": 0.010450685826257348,
      "grad_norm": 233.2891845703125,
      "learning_rate": 9.829629131445342e-05,
      "loss": 22.5444,
      "step": 6
    },
    {
      "epoch": 0.012192466797300239,
      "grad_norm": 189.3314971923828,
      "learning_rate": 9.73465064747553e-05,
      "loss": 6.8803,
      "step": 7
    },
    {
      "epoch": 0.01393424776834313,
      "grad_norm": 8.66031551361084,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.4224,
      "step": 8
    },
    {
      "epoch": 0.015676028739386023,
      "grad_norm": 8.11958122253418,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.4728,
      "step": 9
    },
    {
      "epoch": 0.017417809710428913,
      "grad_norm": 47.53468322753906,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.6014,
      "step": 10
    },
    {
      "epoch": 0.019159590681471803,
      "grad_norm": 35.7159538269043,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.5073,
      "step": 11
    },
    {
      "epoch": 0.020901371652514697,
      "grad_norm": 10.519912719726562,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.4364,
      "step": 12
    },
    {
      "epoch": 0.022643152623557587,
      "grad_norm": 12.840738296508789,
      "learning_rate": 8.759199037394887e-05,
      "loss": 5.8249,
      "step": 13
    },
    {
      "epoch": 0.024384933594600477,
      "grad_norm": 8.846430778503418,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.4291,
      "step": 14
    },
    {
      "epoch": 0.02612671456564337,
      "grad_norm": 6.8042144775390625,
      "learning_rate": 8.296729075500344e-05,
      "loss": 4.7596,
      "step": 15
    },
    {
      "epoch": 0.02786849553668626,
      "grad_norm": 6.720730304718018,
      "learning_rate": 8.043807145043604e-05,
      "loss": 4.555,
      "step": 16
    },
    {
      "epoch": 0.029610276507729152,
      "grad_norm": 6.846876621246338,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.4903,
      "step": 17
    },
    {
      "epoch": 0.031352057478772045,
      "grad_norm": 5.811584949493408,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.634,
      "step": 18
    },
    {
      "epoch": 0.033093838449814936,
      "grad_norm": 10.352850914001465,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.6729,
      "step": 19
    },
    {
      "epoch": 0.034835619420857826,
      "grad_norm": 14.11441707611084,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.5623,
      "step": 20
    },
    {
      "epoch": 0.036577400391900716,
      "grad_norm": 4.49542236328125,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.4165,
      "step": 21
    },
    {
      "epoch": 0.038319181362943606,
      "grad_norm": 6.2761054039001465,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.4753,
      "step": 22
    },
    {
      "epoch": 0.040060962333986504,
      "grad_norm": 8.291924476623535,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.8606,
      "step": 23
    },
    {
      "epoch": 0.041802743305029394,
      "grad_norm": 4.27721643447876,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.6517,
      "step": 24
    },
    {
      "epoch": 0.043544524276072284,
      "grad_norm": 11.168854713439941,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.8501,
      "step": 25
    },
    {
      "epoch": 0.043544524276072284,
      "eval_loss": 4.6739654541015625,
      "eval_runtime": 127.9187,
      "eval_samples_per_second": 30.238,
      "eval_steps_per_second": 3.784,
      "step": 25
    },
    {
      "epoch": 0.045286305247115174,
      "grad_norm": 13.083211898803711,
      "learning_rate": 5e-05,
      "loss": 5.3126,
      "step": 26
    },
    {
      "epoch": 0.047028086218158065,
      "grad_norm": 12.418418884277344,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 5.1456,
      "step": 27
    },
    {
      "epoch": 0.048769867189200955,
      "grad_norm": 10.2151460647583,
      "learning_rate": 4.347369038899744e-05,
      "loss": 4.7801,
      "step": 28
    },
    {
      "epoch": 0.05051164816024385,
      "grad_norm": 8.041688919067383,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 4.5228,
      "step": 29
    },
    {
      "epoch": 0.05225342913128674,
      "grad_norm": 6.638741493225098,
      "learning_rate": 3.705904774487396e-05,
      "loss": 4.687,
      "step": 30
    },
    {
      "epoch": 0.05399521010232963,
      "grad_norm": 4.822203159332275,
      "learning_rate": 3.392802673484193e-05,
      "loss": 4.2664,
      "step": 31
    },
    {
      "epoch": 0.05573699107337252,
      "grad_norm": 4.175324440002441,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.3138,
      "step": 32
    },
    {
      "epoch": 0.05747877204441541,
      "grad_norm": 4.204291820526123,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 4.3258,
      "step": 33
    },
    {
      "epoch": 0.059220553015458303,
      "grad_norm": 5.981131553649902,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.3003,
      "step": 34
    },
    {
      "epoch": 0.0609623339865012,
      "grad_norm": 8.311537742614746,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 4.5814,
      "step": 35
    },
    {
      "epoch": 0.06270411495754409,
      "grad_norm": 9.094008445739746,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 4.59,
      "step": 36
    },
    {
      "epoch": 0.06444589592858697,
      "grad_norm": 9.825113296508789,
      "learning_rate": 1.703270924499656e-05,
      "loss": 4.5756,
      "step": 37
    },
    {
      "epoch": 0.06618767689962987,
      "grad_norm": 4.1204705238342285,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 4.5113,
      "step": 38
    },
    {
      "epoch": 0.06792945787067277,
      "grad_norm": 4.433558940887451,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 4.4955,
      "step": 39
    },
    {
      "epoch": 0.06967123884171565,
      "grad_norm": 4.3605570793151855,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 4.3585,
      "step": 40
    },
    {
      "epoch": 0.07141301981275855,
      "grad_norm": 4.073428630828857,
      "learning_rate": 8.426519384872733e-06,
      "loss": 4.1968,
      "step": 41
    },
    {
      "epoch": 0.07315480078380143,
      "grad_norm": 3.791999340057373,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.4238,
      "step": 42
    },
    {
      "epoch": 0.07489658175484433,
      "grad_norm": 3.7935125827789307,
      "learning_rate": 5.156362923365588e-06,
      "loss": 4.2672,
      "step": 43
    },
    {
      "epoch": 0.07663836272588721,
      "grad_norm": 3.286874771118164,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.0396,
      "step": 44
    },
    {
      "epoch": 0.07838014369693011,
      "grad_norm": 3.8434550762176514,
      "learning_rate": 2.653493525244721e-06,
      "loss": 4.0224,
      "step": 45
    },
    {
      "epoch": 0.08012192466797301,
      "grad_norm": 4.013460159301758,
      "learning_rate": 1.70370868554659e-06,
      "loss": 4.2881,
      "step": 46
    },
    {
      "epoch": 0.08186370563901589,
      "grad_norm": 5.182753086090088,
      "learning_rate": 9.607359798384785e-07,
      "loss": 4.4167,
      "step": 47
    },
    {
      "epoch": 0.08360548661005879,
      "grad_norm": 8.090438842773438,
      "learning_rate": 4.277569313094809e-07,
      "loss": 4.5582,
      "step": 48
    },
    {
      "epoch": 0.08534726758110167,
      "grad_norm": 6.627746105194092,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 4.5952,
      "step": 49
    },
    {
      "epoch": 0.08708904855214457,
      "grad_norm": 9.383976936340332,
      "learning_rate": 0.0,
      "loss": 4.6895,
      "step": 50
    },
    {
      "epoch": 0.08708904855214457,
      "eval_loss": 4.3903303146362305,
      "eval_runtime": 127.9549,
      "eval_samples_per_second": 30.229,
      "eval_steps_per_second": 3.783,
      "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": 6.174479344467968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}