{
  "best_metric": 10.371416091918945,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06811409110259685,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001362281822051937,
      "grad_norm": 0.026211107149720192,
      "learning_rate": 5e-05,
      "loss": 10.377,
      "step": 1
    },
    {
      "epoch": 0.001362281822051937,
      "eval_loss": 10.375895500183105,
      "eval_runtime": 4.8059,
      "eval_samples_per_second": 1029.156,
      "eval_steps_per_second": 128.801,
      "step": 1
    },
    {
      "epoch": 0.002724563644103874,
      "grad_norm": 0.026691626757383347,
      "learning_rate": 0.0001,
      "loss": 10.377,
      "step": 2
    },
    {
      "epoch": 0.004086845466155811,
      "grad_norm": 0.025942042469978333,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3761,
      "step": 3
    },
    {
      "epoch": 0.005449127288207748,
      "grad_norm": 0.025576652958989143,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.377,
      "step": 4
    },
    {
      "epoch": 0.006811409110259685,
      "grad_norm": 0.025234706699848175,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3773,
      "step": 5
    },
    {
      "epoch": 0.008173690932311623,
      "grad_norm": 0.029249094426631927,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.3771,
      "step": 6
    },
    {
      "epoch": 0.00953597275436356,
      "grad_norm": 0.02763037569820881,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3758,
      "step": 7
    },
    {
      "epoch": 0.010898254576415497,
      "grad_norm": 0.029007017612457275,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3764,
      "step": 8
    },
    {
      "epoch": 0.012260536398467433,
      "grad_norm": 0.027018466964364052,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3753,
      "step": 9
    },
    {
      "epoch": 0.01362281822051937,
      "grad_norm": 0.030888764187693596,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3739,
      "step": 10
    },
    {
      "epoch": 0.014985100042571307,
      "grad_norm": 0.03369227796792984,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.3744,
      "step": 11
    },
    {
      "epoch": 0.016347381864623246,
      "grad_norm": 0.03383956849575043,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3725,
      "step": 12
    },
    {
      "epoch": 0.017709663686675182,
      "grad_norm": 0.031551700085401535,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3754,
      "step": 13
    },
    {
      "epoch": 0.01907194550872712,
      "grad_norm": 0.034269507974386215,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3754,
      "step": 14
    },
    {
      "epoch": 0.020434227330779056,
      "grad_norm": 0.03306145220994949,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3745,
      "step": 15
    },
    {
      "epoch": 0.021796509152830993,
      "grad_norm": 0.03238727152347565,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3747,
      "step": 16
    },
    {
      "epoch": 0.02315879097488293,
      "grad_norm": 0.03371455892920494,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.3749,
      "step": 17
    },
    {
      "epoch": 0.024521072796934867,
      "grad_norm": 0.035507142543792725,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3749,
      "step": 18
    },
    {
      "epoch": 0.025883354618986804,
      "grad_norm": 0.03634075075387955,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.3745,
      "step": 19
    },
    {
      "epoch": 0.02724563644103874,
      "grad_norm": 0.037323951721191406,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3745,
      "step": 20
    },
    {
      "epoch": 0.028607918263090677,
      "grad_norm": 0.038444288074970245,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.3761,
      "step": 21
    },
    {
      "epoch": 0.029970200085142614,
      "grad_norm": 0.038676731288433075,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.3727,
      "step": 22
    },
    {
      "epoch": 0.03133248190719455,
      "grad_norm": 0.046296995133161545,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.3717,
      "step": 23
    },
    {
      "epoch": 0.03269476372924649,
      "grad_norm": 0.046376023441553116,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3702,
      "step": 24
    },
    {
      "epoch": 0.034057045551298425,
      "grad_norm": 0.058545101433992386,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.3673,
      "step": 25
    },
    {
      "epoch": 0.034057045551298425,
      "eval_loss": 10.37269401550293,
      "eval_runtime": 4.8093,
      "eval_samples_per_second": 1028.426,
      "eval_steps_per_second": 128.709,
      "step": 25
    },
    {
      "epoch": 0.035419327373350365,
      "grad_norm": 0.04315102472901344,
      "learning_rate": 5e-05,
      "loss": 10.373,
      "step": 26
    },
    {
      "epoch": 0.0367816091954023,
      "grad_norm": 0.04431917518377304,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 10.3733,
      "step": 27
    },
    {
      "epoch": 0.03814389101745424,
      "grad_norm": 0.04504556581377983,
      "learning_rate": 4.347369038899744e-05,
      "loss": 10.372,
      "step": 28
    },
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.046898357570171356,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 10.3735,
      "step": 29
    },
    {
      "epoch": 0.04086845466155811,
      "grad_norm": 0.04973635450005531,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.3728,
      "step": 30
    },
    {
      "epoch": 0.042230736483610046,
      "grad_norm": 0.04653334617614746,
      "learning_rate": 3.392802673484193e-05,
      "loss": 10.373,
      "step": 31
    },
    {
      "epoch": 0.043593018305661986,
      "grad_norm": 0.0456802062690258,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.373,
      "step": 32
    },
    {
      "epoch": 0.04495530012771392,
      "grad_norm": 0.04771285504102707,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 10.3738,
      "step": 33
    },
    {
      "epoch": 0.04631758194976586,
      "grad_norm": 0.046772122383117676,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3717,
      "step": 34
    },
    {
      "epoch": 0.04767986377181779,
      "grad_norm": 0.05056193843483925,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 10.3702,
      "step": 35
    },
    {
      "epoch": 0.04904214559386973,
      "grad_norm": 0.06328132003545761,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 10.3704,
      "step": 36
    },
    {
      "epoch": 0.05040442741592167,
      "grad_norm": 0.05825236067175865,
      "learning_rate": 1.703270924499656e-05,
      "loss": 10.3657,
      "step": 37
    },
    {
      "epoch": 0.05176670923797361,
      "grad_norm": 0.05023612454533577,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3716,
      "step": 38
    },
    {
      "epoch": 0.05312899106002554,
      "grad_norm": 0.05372828617691994,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 10.3717,
      "step": 39
    },
    {
      "epoch": 0.05449127288207748,
      "grad_norm": 0.05338004603981972,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 10.3725,
      "step": 40
    },
    {
      "epoch": 0.055853554704129414,
      "grad_norm": 0.053346700966358185,
      "learning_rate": 8.426519384872733e-06,
      "loss": 10.3726,
      "step": 41
    },
    {
      "epoch": 0.057215836526181355,
      "grad_norm": 0.05252009630203247,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3734,
      "step": 42
    },
    {
      "epoch": 0.05857811834823329,
      "grad_norm": 0.05296671763062477,
      "learning_rate": 5.156362923365588e-06,
      "loss": 10.3725,
      "step": 43
    },
    {
      "epoch": 0.05994040017028523,
      "grad_norm": 0.05633159726858139,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3726,
      "step": 44
    },
    {
      "epoch": 0.06130268199233716,
      "grad_norm": 0.05360110104084015,
      "learning_rate": 2.653493525244721e-06,
      "loss": 10.3728,
      "step": 45
    },
    {
      "epoch": 0.0626649638143891,
      "grad_norm": 0.050015050917863846,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.3726,
      "step": 46
    },
    {
      "epoch": 0.06402724563644104,
      "grad_norm": 0.054285526275634766,
      "learning_rate": 9.607359798384785e-07,
      "loss": 10.3705,
      "step": 47
    },
    {
      "epoch": 0.06538952745849298,
      "grad_norm": 0.058426082134246826,
      "learning_rate": 4.277569313094809e-07,
      "loss": 10.3718,
      "step": 48
    },
    {
      "epoch": 0.06675180928054492,
      "grad_norm": 0.05342816188931465,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 10.3699,
      "step": 49
    },
    {
      "epoch": 0.06811409110259685,
      "grad_norm": 0.0683768019080162,
      "learning_rate": 0.0,
      "loss": 10.3662,
      "step": 50
    },
    {
      "epoch": 0.06811409110259685,
      "eval_loss": 10.371416091918945,
      "eval_runtime": 4.8187,
      "eval_samples_per_second": 1026.428,
      "eval_steps_per_second": 128.459,
      "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": 42768059596800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}