{
  "best_metric": 0.217138409614563,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2828854314002829,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011315417256011316,
      "grad_norm": 9.686368942260742,
      "learning_rate": 5e-05,
      "loss": 12.4512,
      "step": 1
    },
    {
      "epoch": 0.011315417256011316,
      "eval_loss": 12.496306419372559,
      "eval_runtime": 15.6369,
      "eval_samples_per_second": 38.051,
      "eval_steps_per_second": 4.796,
      "step": 1
    },
    {
      "epoch": 0.02263083451202263,
      "grad_norm": 9.485298156738281,
      "learning_rate": 0.0001,
      "loss": 12.5365,
      "step": 2
    },
    {
      "epoch": 0.033946251768033946,
      "grad_norm": 10.219993591308594,
      "learning_rate": 9.989294616193017e-05,
      "loss": 12.1397,
      "step": 3
    },
    {
      "epoch": 0.04526166902404526,
      "grad_norm": 12.514872550964355,
      "learning_rate": 9.957224306869053e-05,
      "loss": 9.1671,
      "step": 4
    },
    {
      "epoch": 0.056577086280056574,
      "grad_norm": 12.2258939743042,
      "learning_rate": 9.903926402016153e-05,
      "loss": 6.2113,
      "step": 5
    },
    {
      "epoch": 0.06789250353606789,
      "grad_norm": 14.635221481323242,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.7714,
      "step": 6
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 11.704349517822266,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.5518,
      "step": 7
    },
    {
      "epoch": 0.09052333804809053,
      "grad_norm": 4.874855041503906,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4791,
      "step": 8
    },
    {
      "epoch": 0.10183875530410184,
      "grad_norm": 10.435992240905762,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.8347,
      "step": 9
    },
    {
      "epoch": 0.11315417256011315,
      "grad_norm": 21.458200454711914,
      "learning_rate": 9.330127018922194e-05,
      "loss": 7.7088,
      "step": 10
    },
    {
      "epoch": 0.12446958981612447,
      "grad_norm": 19.289995193481445,
      "learning_rate": 9.157348061512727e-05,
      "loss": 4.7447,
      "step": 11
    },
    {
      "epoch": 0.13578500707213578,
      "grad_norm": 11.059289932250977,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.0373,
      "step": 12
    },
    {
      "epoch": 0.1471004243281471,
      "grad_norm": 6.678143501281738,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.1645,
      "step": 13
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 8.943098068237305,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2441,
      "step": 14
    },
    {
      "epoch": 0.16973125884016974,
      "grad_norm": 7.194612979888916,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.1196,
      "step": 15
    },
    {
      "epoch": 0.18104667609618105,
      "grad_norm": 2.812526226043701,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0578,
      "step": 16
    },
    {
      "epoch": 0.19236209335219237,
      "grad_norm": 3.1021275520324707,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1586,
      "step": 17
    },
    {
      "epoch": 0.2036775106082037,
      "grad_norm": 14.355679512023926,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4559,
      "step": 18
    },
    {
      "epoch": 0.214992927864215,
      "grad_norm": 3.471893310546875,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.1112,
      "step": 19
    },
    {
      "epoch": 0.2263083451202263,
      "grad_norm": 4.7540154457092285,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1393,
      "step": 20
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 1.5422192811965942,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0799,
      "step": 21
    },
    {
      "epoch": 0.24893917963224893,
      "grad_norm": 5.010796546936035,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.4152,
      "step": 22
    },
    {
      "epoch": 0.26025459688826025,
      "grad_norm": 1.886130452156067,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.3529,
      "step": 23
    },
    {
      "epoch": 0.27157001414427157,
      "grad_norm": 7.487283706665039,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.5008,
      "step": 24
    },
    {
      "epoch": 0.2828854314002829,
      "grad_norm": 10.072656631469727,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.6203,
      "step": 25
    },
    {
      "epoch": 0.2828854314002829,
      "eval_loss": 0.217138409614563,
      "eval_runtime": 15.0374,
      "eval_samples_per_second": 39.568,
      "eval_steps_per_second": 4.988,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.812028905324544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}