{
  "best_metric": 2.1088995933532715,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6980802792321117,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013961605584642234,
      "grad_norm": 2.3544766902923584,
      "learning_rate": 5e-05,
      "loss": 3.0767,
      "step": 1
    },
    {
      "epoch": 0.013961605584642234,
      "eval_loss": 3.6313090324401855,
      "eval_runtime": 14.5941,
      "eval_samples_per_second": 33.095,
      "eval_steps_per_second": 4.18,
      "step": 1
    },
    {
      "epoch": 0.027923211169284468,
      "grad_norm": 2.693396806716919,
      "learning_rate": 0.0001,
      "loss": 3.2593,
      "step": 2
    },
    {
      "epoch": 0.041884816753926704,
      "grad_norm": 2.7242043018341064,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.304,
      "step": 3
    },
    {
      "epoch": 0.055846422338568937,
      "grad_norm": 1.9358065128326416,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.9138,
      "step": 4
    },
    {
      "epoch": 0.06980802792321117,
      "grad_norm": 1.808017611503601,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.8791,
      "step": 5
    },
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 2.140544891357422,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.7218,
      "step": 6
    },
    {
      "epoch": 0.09773123909249563,
      "grad_norm": 1.8418841361999512,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.6181,
      "step": 7
    },
    {
      "epoch": 0.11169284467713787,
      "grad_norm": 1.6990655660629272,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3669,
      "step": 8
    },
    {
      "epoch": 0.1256544502617801,
      "grad_norm": 1.6916632652282715,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.5283,
      "step": 9
    },
    {
      "epoch": 0.13961605584642234,
      "grad_norm": 1.864851474761963,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.5263,
      "step": 10
    },
    {
      "epoch": 0.15357766143106458,
      "grad_norm": 2.088778257369995,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.3329,
      "step": 11
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 2.2531039714813232,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.2406,
      "step": 12
    },
    {
      "epoch": 0.18150087260034903,
      "grad_norm": 2.6214418411254883,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.3912,
      "step": 13
    },
    {
      "epoch": 0.19546247818499127,
      "grad_norm": 2.1405601501464844,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.445,
      "step": 14
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 1.3295773267745972,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.4146,
      "step": 15
    },
    {
      "epoch": 0.22338568935427575,
      "grad_norm": 1.4058939218521118,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.3657,
      "step": 16
    },
    {
      "epoch": 0.23734729493891799,
      "grad_norm": 1.4520275592803955,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.3578,
      "step": 17
    },
    {
      "epoch": 0.2513089005235602,
      "grad_norm": 1.3432828187942505,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3258,
      "step": 18
    },
    {
      "epoch": 0.26527050610820246,
      "grad_norm": 1.297534465789795,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.2328,
      "step": 19
    },
    {
      "epoch": 0.2792321116928447,
      "grad_norm": 1.3611699342727661,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2543,
      "step": 20
    },
    {
      "epoch": 0.2931937172774869,
      "grad_norm": 1.3455018997192383,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.0886,
      "step": 21
    },
    {
      "epoch": 0.30715532286212915,
      "grad_norm": 1.5149480104446411,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.2083,
      "step": 22
    },
    {
      "epoch": 0.32111692844677137,
      "grad_norm": 1.5376019477844238,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 2.0752,
      "step": 23
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 1.6265954971313477,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.1121,
      "step": 24
    },
    {
      "epoch": 0.34904013961605584,
      "grad_norm": 2.5437185764312744,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.1333,
      "step": 25
    },
    {
      "epoch": 0.34904013961605584,
      "eval_loss": 2.18756365776062,
      "eval_runtime": 14.5747,
      "eval_samples_per_second": 33.14,
      "eval_steps_per_second": 4.185,
      "step": 25
    },
    {
      "epoch": 0.36300174520069806,
      "grad_norm": 1.2121622562408447,
      "learning_rate": 5e-05,
      "loss": 2.3337,
      "step": 26
    },
    {
      "epoch": 0.3769633507853403,
      "grad_norm": 1.252693772315979,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.3411,
      "step": 27
    },
    {
      "epoch": 0.39092495636998253,
      "grad_norm": 1.2453138828277588,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.1837,
      "step": 28
    },
    {
      "epoch": 0.4048865619546248,
      "grad_norm": 1.2619675397872925,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.4556,
      "step": 29
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 1.2121081352233887,
      "learning_rate": 3.705904774487396e-05,
      "loss": 2.2601,
      "step": 30
    },
    {
      "epoch": 0.4328097731239092,
      "grad_norm": 1.2065447568893433,
      "learning_rate": 3.392802673484193e-05,
      "loss": 2.1049,
      "step": 31
    },
    {
      "epoch": 0.4467713787085515,
      "grad_norm": 1.3605051040649414,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.3307,
      "step": 32
    },
    {
      "epoch": 0.4607329842931937,
      "grad_norm": 1.3275235891342163,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.9696,
      "step": 33
    },
    {
      "epoch": 0.47469458987783597,
      "grad_norm": 1.4929739236831665,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1102,
      "step": 34
    },
    {
      "epoch": 0.4886561954624782,
      "grad_norm": 1.5965300798416138,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.9822,
      "step": 35
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 1.6006946563720703,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 2.0504,
      "step": 36
    },
    {
      "epoch": 0.5165794066317626,
      "grad_norm": 1.8246269226074219,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.9678,
      "step": 37
    },
    {
      "epoch": 0.5305410122164049,
      "grad_norm": 1.0196877717971802,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3278,
      "step": 38
    },
    {
      "epoch": 0.5445026178010471,
      "grad_norm": 0.9331263303756714,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.2347,
      "step": 39
    },
    {
      "epoch": 0.5584642233856894,
      "grad_norm": 1.1264294385910034,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.1915,
      "step": 40
    },
    {
      "epoch": 0.5724258289703316,
      "grad_norm": 1.0697758197784424,
      "learning_rate": 8.426519384872733e-06,
      "loss": 2.1187,
      "step": 41
    },
    {
      "epoch": 0.5863874345549738,
      "grad_norm": 1.1378289461135864,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.1259,
      "step": 42
    },
    {
      "epoch": 0.6003490401396161,
      "grad_norm": 1.2001599073410034,
      "learning_rate": 5.156362923365588e-06,
      "loss": 2.1106,
      "step": 43
    },
    {
      "epoch": 0.6143106457242583,
      "grad_norm": 1.2745617628097534,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0472,
      "step": 44
    },
    {
      "epoch": 0.6282722513089005,
      "grad_norm": 1.2752476930618286,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.8658,
      "step": 45
    },
    {
      "epoch": 0.6422338568935427,
      "grad_norm": 1.4296314716339111,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.0441,
      "step": 46
    },
    {
      "epoch": 0.6561954624781849,
      "grad_norm": 1.4413177967071533,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.946,
      "step": 47
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 1.5997071266174316,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.982,
      "step": 48
    },
    {
      "epoch": 0.6841186736474695,
      "grad_norm": 1.6253526210784912,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.965,
      "step": 49
    },
    {
      "epoch": 0.6980802792321117,
      "grad_norm": 2.0481815338134766,
      "learning_rate": 0.0,
      "loss": 1.9041,
      "step": 50
    },
    {
      "epoch": 0.6980802792321117,
      "eval_loss": 2.1088995933532715,
      "eval_runtime": 14.5721,
      "eval_samples_per_second": 33.146,
      "eval_steps_per_second": 4.186,
      "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
}