{
  "best_metric": 0.0002786099212244153,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.31695721077654515,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006339144215530904,
      "grad_norm": 19.315614700317383,
      "learning_rate": 5e-05,
      "loss": 6.9727,
      "step": 1
    },
    {
      "epoch": 0.006339144215530904,
      "eval_loss": 13.125102996826172,
      "eval_runtime": 28.4445,
      "eval_samples_per_second": 37.371,
      "eval_steps_per_second": 4.676,
      "step": 1
    },
    {
      "epoch": 0.012678288431061807,
      "grad_norm": 21.581457138061523,
      "learning_rate": 0.0001,
      "loss": 9.3109,
      "step": 2
    },
    {
      "epoch": 0.01901743264659271,
      "grad_norm": 27.578533172607422,
      "learning_rate": 9.989294616193017e-05,
      "loss": 9.7303,
      "step": 3
    },
    {
      "epoch": 0.025356576862123614,
      "grad_norm": 22.673236846923828,
      "learning_rate": 9.957224306869053e-05,
      "loss": 5.0265,
      "step": 4
    },
    {
      "epoch": 0.03169572107765452,
      "grad_norm": 32.24650192260742,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.9491,
      "step": 5
    },
    {
      "epoch": 0.03803486529318542,
      "grad_norm": 17.17237663269043,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9572,
      "step": 6
    },
    {
      "epoch": 0.044374009508716325,
      "grad_norm": 3.5517826080322266,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.1242,
      "step": 7
    },
    {
      "epoch": 0.05071315372424723,
      "grad_norm": 0.2518044114112854,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0136,
      "step": 8
    },
    {
      "epoch": 0.05705229793977813,
      "grad_norm": 0.05993271246552467,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0035,
      "step": 9
    },
    {
      "epoch": 0.06339144215530904,
      "grad_norm": 0.02625989355146885,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0016,
      "step": 10
    },
    {
      "epoch": 0.06973058637083994,
      "grad_norm": 0.018867602571845055,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.001,
      "step": 11
    },
    {
      "epoch": 0.07606973058637084,
      "grad_norm": 0.015163183212280273,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0008,
      "step": 12
    },
    {
      "epoch": 0.08240887480190175,
      "grad_norm": 41.5079345703125,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.2589,
      "step": 13
    },
    {
      "epoch": 0.08874801901743265,
      "grad_norm": 1.5474677085876465,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.004,
      "step": 14
    },
    {
      "epoch": 0.09508716323296355,
      "grad_norm": 0.010092128068208694,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0004,
      "step": 15
    },
    {
      "epoch": 0.10142630744849446,
      "grad_norm": 0.0076212394051253796,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0004,
      "step": 16
    },
    {
      "epoch": 0.10776545166402536,
      "grad_norm": 0.007200384046882391,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0004,
      "step": 17
    },
    {
      "epoch": 0.11410459587955626,
      "grad_norm": 0.0074212574400007725,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0004,
      "step": 18
    },
    {
      "epoch": 0.12044374009508717,
      "grad_norm": 0.008471443317830563,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0005,
      "step": 19
    },
    {
      "epoch": 0.12678288431061807,
      "grad_norm": 0.00895465537905693,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0005,
      "step": 20
    },
    {
      "epoch": 0.13312202852614896,
      "grad_norm": 0.009696467779576778,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0005,
      "step": 21
    },
    {
      "epoch": 0.13946117274167988,
      "grad_norm": 0.00839303620159626,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0005,
      "step": 22
    },
    {
      "epoch": 0.14580031695721077,
      "grad_norm": 0.010750889778137207,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0005,
      "step": 23
    },
    {
      "epoch": 0.15213946117274169,
      "grad_norm": 0.01001252606511116,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0005,
      "step": 24
    },
    {
      "epoch": 0.15847860538827258,
      "grad_norm": 0.008487698622047901,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0005,
      "step": 25
    },
    {
      "epoch": 0.15847860538827258,
      "eval_loss": 0.0004992838366888463,
      "eval_runtime": 28.4204,
      "eval_samples_per_second": 37.403,
      "eval_steps_per_second": 4.68,
      "step": 25
    },
    {
      "epoch": 0.1648177496038035,
      "grad_norm": 0.2868141531944275,
      "learning_rate": 5e-05,
      "loss": 0.0011,
      "step": 26
    },
    {
      "epoch": 0.17115689381933438,
      "grad_norm": 0.03185323625802994,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0005,
      "step": 27
    },
    {
      "epoch": 0.1774960380348653,
      "grad_norm": 0.03331844136118889,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0005,
      "step": 28
    },
    {
      "epoch": 0.1838351822503962,
      "grad_norm": 0.010569626465439796,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0004,
      "step": 29
    },
    {
      "epoch": 0.1901743264659271,
      "grad_norm": 0.008686893619596958,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0003,
      "step": 30
    },
    {
      "epoch": 0.196513470681458,
      "grad_norm": 0.004377232864499092,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0003,
      "step": 31
    },
    {
      "epoch": 0.20285261489698891,
      "grad_norm": 0.005554168950766325,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0003,
      "step": 32
    },
    {
      "epoch": 0.2091917591125198,
      "grad_norm": 0.004525969736278057,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0003,
      "step": 33
    },
    {
      "epoch": 0.21553090332805072,
      "grad_norm": 0.005449299700558186,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0003,
      "step": 34
    },
    {
      "epoch": 0.2218700475435816,
      "grad_norm": 0.0035808521788567305,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0003,
      "step": 35
    },
    {
      "epoch": 0.22820919175911253,
      "grad_norm": 0.0033939117565751076,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0003,
      "step": 36
    },
    {
      "epoch": 0.23454833597464342,
      "grad_norm": 0.003639708273112774,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0004,
      "step": 37
    },
    {
      "epoch": 0.24088748019017434,
      "grad_norm": 0.002626145724207163,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0002,
      "step": 38
    },
    {
      "epoch": 0.24722662440570523,
      "grad_norm": 0.002726343460381031,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0002,
      "step": 39
    },
    {
      "epoch": 0.25356576862123614,
      "grad_norm": 0.002509567653760314,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0002,
      "step": 40
    },
    {
      "epoch": 0.25990491283676703,
      "grad_norm": 0.002883738139644265,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0003,
      "step": 41
    },
    {
      "epoch": 0.2662440570522979,
      "grad_norm": 0.0029756142757833004,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0003,
      "step": 42
    },
    {
      "epoch": 0.27258320126782887,
      "grad_norm": 0.0024971175007522106,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0003,
      "step": 43
    },
    {
      "epoch": 0.27892234548335976,
      "grad_norm": 0.003839804558083415,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0003,
      "step": 44
    },
    {
      "epoch": 0.28526148969889065,
      "grad_norm": 0.002964878687635064,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0003,
      "step": 45
    },
    {
      "epoch": 0.29160063391442154,
      "grad_norm": 0.0027413098141551018,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0003,
      "step": 46
    },
    {
      "epoch": 0.2979397781299525,
      "grad_norm": 0.002740249503403902,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0003,
      "step": 47
    },
    {
      "epoch": 0.30427892234548337,
      "grad_norm": 0.0029246630147099495,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0003,
      "step": 48
    },
    {
      "epoch": 0.31061806656101426,
      "grad_norm": 0.003166801994666457,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0003,
      "step": 49
    },
    {
      "epoch": 0.31695721077654515,
      "grad_norm": 0.0033695553429424763,
      "learning_rate": 0.0,
      "loss": 0.0003,
      "step": 50
    },
    {
      "epoch": 0.31695721077654515,
      "eval_loss": 0.0002786099212244153,
      "eval_runtime": 28.3691,
      "eval_samples_per_second": 37.47,
      "eval_steps_per_second": 4.688,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}