{
  "best_metric": 0.0006782332202419639,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06756756756756757,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013513513513513514,
      "grad_norm": 0.45085078477859497,
      "learning_rate": 5e-05,
      "loss": 0.2322,
      "step": 1
    },
    {
      "epoch": 0.0013513513513513514,
      "eval_loss": 0.5629749894142151,
      "eval_runtime": 150.6076,
      "eval_samples_per_second": 33.099,
      "eval_steps_per_second": 4.143,
      "step": 1
    },
    {
      "epoch": 0.002702702702702703,
      "grad_norm": 0.5798161625862122,
      "learning_rate": 0.0001,
      "loss": 0.2991,
      "step": 2
    },
    {
      "epoch": 0.004054054054054054,
      "grad_norm": 0.6623466610908508,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.2862,
      "step": 3
    },
    {
      "epoch": 0.005405405405405406,
      "grad_norm": 0.5939732789993286,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.1894,
      "step": 4
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 0.6891723275184631,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0948,
      "step": 5
    },
    {
      "epoch": 0.008108108108108109,
      "grad_norm": 0.38345640897750854,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.035,
      "step": 6
    },
    {
      "epoch": 0.00945945945945946,
      "grad_norm": 0.11537162214517593,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0128,
      "step": 7
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 0.1635945439338684,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0091,
      "step": 8
    },
    {
      "epoch": 0.012162162162162163,
      "grad_norm": 0.1792706996202469,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0055,
      "step": 9
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 0.11829370260238647,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0027,
      "step": 10
    },
    {
      "epoch": 0.014864864864864866,
      "grad_norm": 0.40137365460395813,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0089,
      "step": 11
    },
    {
      "epoch": 0.016216216216216217,
      "grad_norm": 0.13307957351207733,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0041,
      "step": 12
    },
    {
      "epoch": 0.01756756756756757,
      "grad_norm": 0.28080302476882935,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0132,
      "step": 13
    },
    {
      "epoch": 0.01891891891891892,
      "grad_norm": 0.09083463996648788,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0032,
      "step": 14
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 0.03497685119509697,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0026,
      "step": 15
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 0.0257202610373497,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.001,
      "step": 16
    },
    {
      "epoch": 0.022972972972972974,
      "grad_norm": 0.05532519146800041,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0011,
      "step": 17
    },
    {
      "epoch": 0.024324324324324326,
      "grad_norm": 0.03546787053346634,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0011,
      "step": 18
    },
    {
      "epoch": 0.025675675675675677,
      "grad_norm": 0.05323174595832825,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0006,
      "step": 19
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 0.04640858247876167,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0021,
      "step": 20
    },
    {
      "epoch": 0.02837837837837838,
      "grad_norm": 0.037614379078149796,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0006,
      "step": 21
    },
    {
      "epoch": 0.02972972972972973,
      "grad_norm": 0.020708007737994194,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0006,
      "step": 22
    },
    {
      "epoch": 0.031081081081081083,
      "grad_norm": 0.03838440403342247,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0003,
      "step": 23
    },
    {
      "epoch": 0.032432432432432434,
      "grad_norm": 0.1440870463848114,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0012,
      "step": 24
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 0.07391831278800964,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0024,
      "step": 25
    },
    {
      "epoch": 0.033783783783783786,
      "eval_loss": 0.0011842730455100536,
      "eval_runtime": 150.7684,
      "eval_samples_per_second": 33.064,
      "eval_steps_per_second": 4.139,
      "step": 25
    },
    {
      "epoch": 0.03513513513513514,
      "grad_norm": 0.14307132363319397,
      "learning_rate": 5e-05,
      "loss": 0.0022,
      "step": 26
    },
    {
      "epoch": 0.03648648648648649,
      "grad_norm": 0.045208968222141266,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0005,
      "step": 27
    },
    {
      "epoch": 0.03783783783783784,
      "grad_norm": 0.04789796844124794,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0009,
      "step": 28
    },
    {
      "epoch": 0.03918918918918919,
      "grad_norm": 0.023802442476153374,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0005,
      "step": 29
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 0.0236771609634161,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0005,
      "step": 30
    },
    {
      "epoch": 0.041891891891891894,
      "grad_norm": 0.004636330995708704,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0002,
      "step": 31
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 0.04701589047908783,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0006,
      "step": 32
    },
    {
      "epoch": 0.0445945945945946,
      "grad_norm": 0.009117241948843002,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0002,
      "step": 33
    },
    {
      "epoch": 0.04594594594594595,
      "grad_norm": 0.07297568768262863,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0007,
      "step": 34
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 0.011586630716919899,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0002,
      "step": 35
    },
    {
      "epoch": 0.04864864864864865,
      "grad_norm": 0.026419680565595627,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0005,
      "step": 36
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.021272508427500725,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0006,
      "step": 37
    },
    {
      "epoch": 0.051351351351351354,
      "grad_norm": 0.10119505971670151,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0047,
      "step": 38
    },
    {
      "epoch": 0.052702702702702706,
      "grad_norm": 0.04138147085905075,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.001,
      "step": 39
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.010599342174828053,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0004,
      "step": 40
    },
    {
      "epoch": 0.05540540540540541,
      "grad_norm": 0.043806999921798706,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0008,
      "step": 41
    },
    {
      "epoch": 0.05675675675675676,
      "grad_norm": 0.00391389848664403,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.05810810810810811,
      "grad_norm": 0.11111900955438614,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0007,
      "step": 43
    },
    {
      "epoch": 0.05945945945945946,
      "grad_norm": 0.017778916284441948,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0003,
      "step": 44
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 0.03460654616355896,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0011,
      "step": 45
    },
    {
      "epoch": 0.062162162162162166,
      "grad_norm": 0.011294426396489143,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.06351351351351352,
      "grad_norm": 0.008213512599468231,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0002,
      "step": 47
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 0.03531975671648979,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0004,
      "step": 48
    },
    {
      "epoch": 0.06621621621621622,
      "grad_norm": 0.0346805676817894,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0004,
      "step": 49
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 0.31902623176574707,
      "learning_rate": 0.0,
      "loss": 0.0028,
      "step": 50
    },
    {
      "epoch": 0.06756756756756757,
      "eval_loss": 0.0006782332202419639,
      "eval_runtime": 152.5444,
      "eval_samples_per_second": 32.679,
      "eval_steps_per_second": 4.091,
      "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": 5.969948642440643e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}