{
  "best_metric": 1.125113606452942,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.22701475595913734,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004540295119182747,
      "grad_norm": 0.5608993172645569,
      "learning_rate": 2e-05,
      "loss": 1.2604,
      "step": 1
    },
    {
      "epoch": 0.004540295119182747,
      "eval_loss": 1.4539767503738403,
      "eval_runtime": 10.0855,
      "eval_samples_per_second": 36.785,
      "eval_steps_per_second": 4.66,
      "step": 1
    },
    {
      "epoch": 0.009080590238365494,
      "grad_norm": 0.5262722373008728,
      "learning_rate": 4e-05,
      "loss": 1.2812,
      "step": 2
    },
    {
      "epoch": 0.01362088535754824,
      "grad_norm": 0.45176419615745544,
      "learning_rate": 6e-05,
      "loss": 1.1693,
      "step": 3
    },
    {
      "epoch": 0.018161180476730987,
      "grad_norm": 0.4379451870918274,
      "learning_rate": 8e-05,
      "loss": 1.1982,
      "step": 4
    },
    {
      "epoch": 0.022701475595913734,
      "grad_norm": 0.38019585609436035,
      "learning_rate": 0.0001,
      "loss": 1.1727,
      "step": 5
    },
    {
      "epoch": 0.02724177071509648,
      "grad_norm": 0.3477766513824463,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.2451,
      "step": 6
    },
    {
      "epoch": 0.03178206583427923,
      "grad_norm": 0.35698744654655457,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2523,
      "step": 7
    },
    {
      "epoch": 0.036322360953461974,
      "grad_norm": 0.3647920787334442,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3273,
      "step": 8
    },
    {
      "epoch": 0.04086265607264472,
      "grad_norm": 0.3550705015659332,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.2223,
      "step": 9
    },
    {
      "epoch": 0.04540295119182747,
      "grad_norm": 0.43464210629463196,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.3025,
      "step": 10
    },
    {
      "epoch": 0.049943246311010214,
      "grad_norm": 0.37873485684394836,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2259,
      "step": 11
    },
    {
      "epoch": 0.05448354143019296,
      "grad_norm": 0.37317633628845215,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.2298,
      "step": 12
    },
    {
      "epoch": 0.05902383654937571,
      "grad_norm": 0.40012049674987793,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.215,
      "step": 13
    },
    {
      "epoch": 0.06356413166855845,
      "grad_norm": 0.3849846422672272,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2012,
      "step": 14
    },
    {
      "epoch": 0.0681044267877412,
      "grad_norm": 0.37194129824638367,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1632,
      "step": 15
    },
    {
      "epoch": 0.07264472190692395,
      "grad_norm": 0.38879069685935974,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1127,
      "step": 16
    },
    {
      "epoch": 0.0771850170261067,
      "grad_norm": 0.3786041736602783,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1716,
      "step": 17
    },
    {
      "epoch": 0.08172531214528944,
      "grad_norm": 0.3922478258609772,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.2044,
      "step": 18
    },
    {
      "epoch": 0.08626560726447219,
      "grad_norm": 0.38386255502700806,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.151,
      "step": 19
    },
    {
      "epoch": 0.09080590238365494,
      "grad_norm": 0.42602765560150146,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1694,
      "step": 20
    },
    {
      "epoch": 0.09534619750283768,
      "grad_norm": 0.39171090722084045,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.175,
      "step": 21
    },
    {
      "epoch": 0.09988649262202043,
      "grad_norm": 0.3942036032676697,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.1999,
      "step": 22
    },
    {
      "epoch": 0.10442678774120318,
      "grad_norm": 0.4129440188407898,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1767,
      "step": 23
    },
    {
      "epoch": 0.10896708286038592,
      "grad_norm": 0.4210982620716095,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.2759,
      "step": 24
    },
    {
      "epoch": 0.11350737797956867,
      "grad_norm": 0.4219196140766144,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.1998,
      "step": 25
    },
    {
      "epoch": 0.11350737797956867,
      "eval_loss": 1.125113606452942,
      "eval_runtime": 10.0342,
      "eval_samples_per_second": 36.974,
      "eval_steps_per_second": 4.684,
      "step": 25
    },
    {
      "epoch": 0.11804767309875142,
      "grad_norm": 0.45543304085731506,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2383,
      "step": 26
    },
    {
      "epoch": 0.12258796821793416,
      "grad_norm": 0.5423667430877686,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1882,
      "step": 27
    },
    {
      "epoch": 0.1271282633371169,
      "grad_norm": 0.45114219188690186,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.1249,
      "step": 28
    },
    {
      "epoch": 0.13166855845629966,
      "grad_norm": 0.4604540467262268,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.1833,
      "step": 29
    },
    {
      "epoch": 0.1362088535754824,
      "grad_norm": 0.49046003818511963,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.1793,
      "step": 30
    },
    {
      "epoch": 0.14074914869466515,
      "grad_norm": 0.5115222334861755,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.1548,
      "step": 31
    },
    {
      "epoch": 0.1452894438138479,
      "grad_norm": 0.48150011897087097,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0399,
      "step": 32
    },
    {
      "epoch": 0.14982973893303064,
      "grad_norm": 0.5298136472702026,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.1891,
      "step": 33
    },
    {
      "epoch": 0.1543700340522134,
      "grad_norm": 0.4817681908607483,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0856,
      "step": 34
    },
    {
      "epoch": 0.15891032917139614,
      "grad_norm": 0.5052300095558167,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0734,
      "step": 35
    },
    {
      "epoch": 0.16345062429057888,
      "grad_norm": 0.5191230177879333,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0951,
      "step": 36
    },
    {
      "epoch": 0.16799091940976163,
      "grad_norm": 0.49014902114868164,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0811,
      "step": 37
    },
    {
      "epoch": 0.17253121452894438,
      "grad_norm": 0.558128297328949,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.1841,
      "step": 38
    },
    {
      "epoch": 0.17707150964812712,
      "grad_norm": 0.5571663975715637,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0598,
      "step": 39
    },
    {
      "epoch": 0.18161180476730987,
      "grad_norm": 0.5573685765266418,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.013,
      "step": 40
    },
    {
      "epoch": 0.18615209988649262,
      "grad_norm": 0.5625842213630676,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0995,
      "step": 41
    },
    {
      "epoch": 0.19069239500567536,
      "grad_norm": 0.6718692183494568,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.0627,
      "step": 42
    },
    {
      "epoch": 0.1952326901248581,
      "grad_norm": 0.6249908208847046,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0266,
      "step": 43
    },
    {
      "epoch": 0.19977298524404086,
      "grad_norm": 0.6505060791969299,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.0113,
      "step": 44
    },
    {
      "epoch": 0.2043132803632236,
      "grad_norm": 0.7362877130508423,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0885,
      "step": 45
    },
    {
      "epoch": 0.20885357548240635,
      "grad_norm": 0.7237470746040344,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.9956,
      "step": 46
    },
    {
      "epoch": 0.2133938706015891,
      "grad_norm": 0.8162877559661865,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.0847,
      "step": 47
    },
    {
      "epoch": 0.21793416572077184,
      "grad_norm": 0.8599759340286255,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.0561,
      "step": 48
    },
    {
      "epoch": 0.2224744608399546,
      "grad_norm": 1.2603548765182495,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.0098,
      "step": 49
    },
    {
      "epoch": 0.22701475595913734,
      "grad_norm": 1.499512791633606,
      "learning_rate": 0.0,
      "loss": 1.2965,
      "step": 50
    },
    {
      "epoch": 0.22701475595913734,
      "eval_loss": 1.127669095993042,
      "eval_runtime": 10.241,
      "eval_samples_per_second": 36.227,
      "eval_steps_per_second": 4.589,
      "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": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5934336184352768e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}