{
  "best_metric": 0.0015694969333708286,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12726694241170855,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002545338848234171,
      "grad_norm": 129.92514038085938,
      "learning_rate": 5e-05,
      "loss": 114.627,
      "step": 1
    },
    {
      "epoch": 0.002545338848234171,
      "eval_loss": 7.0684075355529785,
      "eval_runtime": 133.3179,
      "eval_samples_per_second": 19.855,
      "eval_steps_per_second": 2.483,
      "step": 1
    },
    {
      "epoch": 0.005090677696468342,
      "grad_norm": 122.67146301269531,
      "learning_rate": 0.0001,
      "loss": 109.1541,
      "step": 2
    },
    {
      "epoch": 0.007636016544702514,
      "grad_norm": 125.86717987060547,
      "learning_rate": 9.989294616193017e-05,
      "loss": 108.6269,
      "step": 3
    },
    {
      "epoch": 0.010181355392936684,
      "grad_norm": 115.33885192871094,
      "learning_rate": 9.957224306869053e-05,
      "loss": 86.9907,
      "step": 4
    },
    {
      "epoch": 0.012726694241170856,
      "grad_norm": 120.60005950927734,
      "learning_rate": 9.903926402016153e-05,
      "loss": 60.2449,
      "step": 5
    },
    {
      "epoch": 0.015272033089405028,
      "grad_norm": 103.03462982177734,
      "learning_rate": 9.829629131445342e-05,
      "loss": 39.516,
      "step": 6
    },
    {
      "epoch": 0.017817371937639197,
      "grad_norm": 95.61904907226562,
      "learning_rate": 9.73465064747553e-05,
      "loss": 24.1843,
      "step": 7
    },
    {
      "epoch": 0.02036271078587337,
      "grad_norm": 54.237098693847656,
      "learning_rate": 9.619397662556435e-05,
      "loss": 12.2665,
      "step": 8
    },
    {
      "epoch": 0.02290804963410754,
      "grad_norm": 34.288536071777344,
      "learning_rate": 9.484363707663442e-05,
      "loss": 6.7009,
      "step": 9
    },
    {
      "epoch": 0.025453388482341712,
      "grad_norm": 25.363252639770508,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.4084,
      "step": 10
    },
    {
      "epoch": 0.027998727330575884,
      "grad_norm": 9.300350189208984,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.017,
      "step": 11
    },
    {
      "epoch": 0.030544066178810055,
      "grad_norm": 10.918034553527832,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.6565,
      "step": 12
    },
    {
      "epoch": 0.03308940502704422,
      "grad_norm": 3.387279510498047,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.1737,
      "step": 13
    },
    {
      "epoch": 0.035634743875278395,
      "grad_norm": 0.526419997215271,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0245,
      "step": 14
    },
    {
      "epoch": 0.038180082723512566,
      "grad_norm": 0.08817209303379059,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0048,
      "step": 15
    },
    {
      "epoch": 0.04072542157174674,
      "grad_norm": 0.03126617893576622,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0017,
      "step": 16
    },
    {
      "epoch": 0.04327076041998091,
      "grad_norm": 0.015730440616607666,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0007,
      "step": 17
    },
    {
      "epoch": 0.04581609926821508,
      "grad_norm": 2.4320287704467773,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0248,
      "step": 18
    },
    {
      "epoch": 0.04836143811644925,
      "grad_norm": 0.009516693651676178,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0004,
      "step": 19
    },
    {
      "epoch": 0.050906776964683424,
      "grad_norm": 0.009594852104783058,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0004,
      "step": 20
    },
    {
      "epoch": 0.053452115812917596,
      "grad_norm": 0.009399442002177238,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0004,
      "step": 21
    },
    {
      "epoch": 0.05599745466115177,
      "grad_norm": 0.009702535346150398,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0003,
      "step": 22
    },
    {
      "epoch": 0.05854279350938594,
      "grad_norm": 0.010525376535952091,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0004,
      "step": 23
    },
    {
      "epoch": 0.06108813235762011,
      "grad_norm": 12.577119827270508,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.2616,
      "step": 24
    },
    {
      "epoch": 0.06363347120585428,
      "grad_norm": 0.0849747359752655,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0013,
      "step": 25
    },
    {
      "epoch": 0.06363347120585428,
      "eval_loss": 0.0022325909230858088,
      "eval_runtime": 131.4816,
      "eval_samples_per_second": 20.132,
      "eval_steps_per_second": 2.517,
      "step": 25
    },
    {
      "epoch": 0.06617881005408845,
      "grad_norm": 0.02771487459540367,
      "learning_rate": 5e-05,
      "loss": 0.0006,
      "step": 26
    },
    {
      "epoch": 0.06872414890232262,
      "grad_norm": 0.3581013083457947,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0026,
      "step": 27
    },
    {
      "epoch": 0.07126948775055679,
      "grad_norm": 0.17332956194877625,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0013,
      "step": 28
    },
    {
      "epoch": 0.07381482659879096,
      "grad_norm": 0.04999712109565735,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0006,
      "step": 29
    },
    {
      "epoch": 0.07636016544702513,
      "grad_norm": 0.01677992381155491,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0003,
      "step": 30
    },
    {
      "epoch": 0.0789055042952593,
      "grad_norm": 0.008356700651347637,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0003,
      "step": 31
    },
    {
      "epoch": 0.08145084314349348,
      "grad_norm": 0.011792369186878204,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0003,
      "step": 32
    },
    {
      "epoch": 0.08399618199172765,
      "grad_norm": 0.03631852939724922,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0003,
      "step": 33
    },
    {
      "epoch": 0.08654152083996182,
      "grad_norm": 0.004105123691260815,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0002,
      "step": 34
    },
    {
      "epoch": 0.08908685968819599,
      "grad_norm": 0.007662076968699694,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0003,
      "step": 35
    },
    {
      "epoch": 0.09163219853643016,
      "grad_norm": 0.005889294669032097,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0002,
      "step": 36
    },
    {
      "epoch": 0.09417753738466433,
      "grad_norm": 1.1749862432479858,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0066,
      "step": 37
    },
    {
      "epoch": 0.0967228762328985,
      "grad_norm": 0.03878513351082802,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0003,
      "step": 38
    },
    {
      "epoch": 0.09926821508113268,
      "grad_norm": 0.00471383985131979,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0002,
      "step": 39
    },
    {
      "epoch": 0.10181355392936685,
      "grad_norm": 0.004265178926289082,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0002,
      "step": 40
    },
    {
      "epoch": 0.10435889277760102,
      "grad_norm": 0.004452875815331936,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0002,
      "step": 41
    },
    {
      "epoch": 0.10690423162583519,
      "grad_norm": 0.0047661480493843555,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0002,
      "step": 42
    },
    {
      "epoch": 0.10944957047406936,
      "grad_norm": 0.004124505445361137,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0002,
      "step": 43
    },
    {
      "epoch": 0.11199490932230353,
      "grad_norm": 0.0037059446331113577,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0001,
      "step": 44
    },
    {
      "epoch": 0.1145402481705377,
      "grad_norm": 0.003210233524441719,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.11708558701877188,
      "grad_norm": 0.003240456571802497,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.11963092586700605,
      "grad_norm": 0.004116287920624018,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.12217626471524022,
      "grad_norm": 0.006474327761679888,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0002,
      "step": 48
    },
    {
      "epoch": 0.12472160356347439,
      "grad_norm": 0.007355257868766785,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0003,
      "step": 49
    },
    {
      "epoch": 0.12726694241170855,
      "grad_norm": 10.613334655761719,
      "learning_rate": 0.0,
      "loss": 1.0866,
      "step": 50
    },
    {
      "epoch": 0.12726694241170855,
      "eval_loss": 0.0015694969333708286,
      "eval_runtime": 133.4738,
      "eval_samples_per_second": 19.832,
      "eval_steps_per_second": 2.48,
      "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": 5.260799806149755e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}