{
  "best_metric": 0.526287853717804,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.6143790849673203,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05228758169934641,
      "grad_norm": 6.460526943206787,
      "learning_rate": 5e-05,
      "loss": 3.8396,
      "step": 1
    },
    {
      "epoch": 0.05228758169934641,
      "eval_loss": 3.95047926902771,
      "eval_runtime": 0.9341,
      "eval_samples_per_second": 138.108,
      "eval_steps_per_second": 18.2,
      "step": 1
    },
    {
      "epoch": 0.10457516339869281,
      "grad_norm": 6.698931694030762,
      "learning_rate": 0.0001,
      "loss": 3.8934,
      "step": 2
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 6.0289130210876465,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.6689,
      "step": 3
    },
    {
      "epoch": 0.20915032679738563,
      "grad_norm": 4.654027938842773,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.1382,
      "step": 4
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 5.704774856567383,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.7575,
      "step": 5
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 5.513850212097168,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.3247,
      "step": 6
    },
    {
      "epoch": 0.3660130718954248,
      "grad_norm": 4.727966785430908,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0788,
      "step": 7
    },
    {
      "epoch": 0.41830065359477125,
      "grad_norm": 4.920650959014893,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7544,
      "step": 8
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 4.469264507293701,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.5345,
      "step": 9
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 3.867827892303467,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.414,
      "step": 10
    },
    {
      "epoch": 0.5751633986928104,
      "grad_norm": 3.5533699989318848,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.1654,
      "step": 11
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 3.0781290531158447,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1687,
      "step": 12
    },
    {
      "epoch": 0.6797385620915033,
      "grad_norm": 4.141233444213867,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.0384,
      "step": 13
    },
    {
      "epoch": 0.7320261437908496,
      "grad_norm": 3.7738871574401855,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.012,
      "step": 14
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 2.6970467567443848,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.9884,
      "step": 15
    },
    {
      "epoch": 0.8366013071895425,
      "grad_norm": 2.233119010925293,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8815,
      "step": 16
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.7174006700515747,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.7866,
      "step": 17
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 2.046114921569824,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7722,
      "step": 18
    },
    {
      "epoch": 0.9934640522875817,
      "grad_norm": 2.273921489715576,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7433,
      "step": 19
    },
    {
      "epoch": 1.0457516339869282,
      "grad_norm": 3.623931646347046,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3464,
      "step": 20
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 2.1640617847442627,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6948,
      "step": 21
    },
    {
      "epoch": 1.1503267973856208,
      "grad_norm": 2.020327091217041,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6669,
      "step": 22
    },
    {
      "epoch": 1.2026143790849673,
      "grad_norm": 1.8963872194290161,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.6226,
      "step": 23
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 2.513511896133423,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6172,
      "step": 24
    },
    {
      "epoch": 1.3071895424836601,
      "grad_norm": 2.398629903793335,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.6283,
      "step": 25
    },
    {
      "epoch": 1.3071895424836601,
      "eval_loss": 0.648818850517273,
      "eval_runtime": 0.9306,
      "eval_samples_per_second": 138.623,
      "eval_steps_per_second": 18.268,
      "step": 25
    },
    {
      "epoch": 1.3594771241830066,
      "grad_norm": 1.6588599681854248,
      "learning_rate": 5e-05,
      "loss": 0.5987,
      "step": 26
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.7340439558029175,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.5583,
      "step": 27
    },
    {
      "epoch": 1.4640522875816995,
      "grad_norm": 1.5749491453170776,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.602,
      "step": 28
    },
    {
      "epoch": 1.5163398692810457,
      "grad_norm": 1.7133127450942993,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.6292,
      "step": 29
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 2.0184829235076904,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.6021,
      "step": 30
    },
    {
      "epoch": 1.6209150326797386,
      "grad_norm": 1.7977181673049927,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.5567,
      "step": 31
    },
    {
      "epoch": 1.673202614379085,
      "grad_norm": 1.6275135278701782,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5543,
      "step": 32
    },
    {
      "epoch": 1.7254901960784315,
      "grad_norm": 1.8324847221374512,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.5745,
      "step": 33
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.6420360803604126,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.52,
      "step": 34
    },
    {
      "epoch": 1.8300653594771243,
      "grad_norm": 1.4819954633712769,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.4934,
      "step": 35
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 1.4158824682235718,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.5388,
      "step": 36
    },
    {
      "epoch": 1.934640522875817,
      "grad_norm": 1.7841893434524536,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.4938,
      "step": 37
    },
    {
      "epoch": 1.9869281045751634,
      "grad_norm": 1.9757091999053955,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5301,
      "step": 38
    },
    {
      "epoch": 2.0392156862745097,
      "grad_norm": 3.0482711791992188,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.9327,
      "step": 39
    },
    {
      "epoch": 2.0915032679738563,
      "grad_norm": 1.5659737586975098,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.4755,
      "step": 40
    },
    {
      "epoch": 2.1437908496732025,
      "grad_norm": 1.4230481386184692,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.5159,
      "step": 41
    },
    {
      "epoch": 2.196078431372549,
      "grad_norm": 1.5947973728179932,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4792,
      "step": 42
    },
    {
      "epoch": 2.2483660130718954,
      "grad_norm": 1.546298623085022,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.4841,
      "step": 43
    },
    {
      "epoch": 2.3006535947712417,
      "grad_norm": 1.5563234090805054,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5057,
      "step": 44
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 1.8946163654327393,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.4677,
      "step": 45
    },
    {
      "epoch": 2.4052287581699345,
      "grad_norm": 1.349687933921814,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.4777,
      "step": 46
    },
    {
      "epoch": 2.457516339869281,
      "grad_norm": 1.4442392587661743,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.4766,
      "step": 47
    },
    {
      "epoch": 2.5098039215686274,
      "grad_norm": 1.3940331935882568,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.5297,
      "step": 48
    },
    {
      "epoch": 2.5620915032679736,
      "grad_norm": 1.1987098455429077,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.5222,
      "step": 49
    },
    {
      "epoch": 2.6143790849673203,
      "grad_norm": 1.7109036445617676,
      "learning_rate": 0.0,
      "loss": 0.4988,
      "step": 50
    },
    {
      "epoch": 2.6143790849673203,
      "eval_loss": 0.526287853717804,
      "eval_runtime": 0.9308,
      "eval_samples_per_second": 138.584,
      "eval_steps_per_second": 18.263,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}