{
  "best_metric": 1.9266914129257202,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07399186089530152,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014798372179060304,
      "grad_norm": 2.129586935043335,
      "learning_rate": 2e-05,
      "loss": 8.8458,
      "step": 1
    },
    {
      "epoch": 0.0014798372179060304,
      "eval_loss": 2.549591064453125,
      "eval_runtime": 27.4011,
      "eval_samples_per_second": 41.568,
      "eval_steps_per_second": 5.219,
      "step": 1
    },
    {
      "epoch": 0.0029596744358120607,
      "grad_norm": 2.134746789932251,
      "learning_rate": 4e-05,
      "loss": 9.1871,
      "step": 2
    },
    {
      "epoch": 0.004439511653718091,
      "grad_norm": 2.0432419776916504,
      "learning_rate": 6e-05,
      "loss": 8.7238,
      "step": 3
    },
    {
      "epoch": 0.0059193488716241215,
      "grad_norm": 1.9869104623794556,
      "learning_rate": 8e-05,
      "loss": 9.2447,
      "step": 4
    },
    {
      "epoch": 0.007399186089530152,
      "grad_norm": 1.9248343706130981,
      "learning_rate": 0.0001,
      "loss": 8.9723,
      "step": 5
    },
    {
      "epoch": 0.008879023307436182,
      "grad_norm": 1.9572157859802246,
      "learning_rate": 9.987820251299122e-05,
      "loss": 8.8129,
      "step": 6
    },
    {
      "epoch": 0.010358860525342212,
      "grad_norm": 1.7023802995681763,
      "learning_rate": 9.951340343707852e-05,
      "loss": 8.4475,
      "step": 7
    },
    {
      "epoch": 0.011838697743248243,
      "grad_norm": 1.5187019109725952,
      "learning_rate": 9.890738003669029e-05,
      "loss": 8.0999,
      "step": 8
    },
    {
      "epoch": 0.013318534961154272,
      "grad_norm": 1.5758388042449951,
      "learning_rate": 9.806308479691595e-05,
      "loss": 8.2545,
      "step": 9
    },
    {
      "epoch": 0.014798372179060304,
      "grad_norm": 1.7771358489990234,
      "learning_rate": 9.698463103929542e-05,
      "loss": 8.3517,
      "step": 10
    },
    {
      "epoch": 0.016278209396966333,
      "grad_norm": 1.8085169792175293,
      "learning_rate": 9.567727288213005e-05,
      "loss": 7.7781,
      "step": 11
    },
    {
      "epoch": 0.017758046614872364,
      "grad_norm": 1.7134963274002075,
      "learning_rate": 9.414737964294636e-05,
      "loss": 8.2057,
      "step": 12
    },
    {
      "epoch": 0.019237883832778396,
      "grad_norm": 1.593971610069275,
      "learning_rate": 9.24024048078213e-05,
      "loss": 8.1811,
      "step": 13
    },
    {
      "epoch": 0.020717721050684423,
      "grad_norm": 1.6796249151229858,
      "learning_rate": 9.045084971874738e-05,
      "loss": 8.2568,
      "step": 14
    },
    {
      "epoch": 0.022197558268590455,
      "grad_norm": 2.30429744720459,
      "learning_rate": 8.83022221559489e-05,
      "loss": 8.2857,
      "step": 15
    },
    {
      "epoch": 0.023677395486496486,
      "grad_norm": 1.4573338031768799,
      "learning_rate": 8.596699001693255e-05,
      "loss": 8.1385,
      "step": 16
    },
    {
      "epoch": 0.025157232704402517,
      "grad_norm": 1.3977992534637451,
      "learning_rate": 8.345653031794292e-05,
      "loss": 8.2235,
      "step": 17
    },
    {
      "epoch": 0.026637069922308545,
      "grad_norm": 1.5306203365325928,
      "learning_rate": 8.07830737662829e-05,
      "loss": 8.2804,
      "step": 18
    },
    {
      "epoch": 0.028116907140214576,
      "grad_norm": 1.3745988607406616,
      "learning_rate": 7.795964517353735e-05,
      "loss": 7.831,
      "step": 19
    },
    {
      "epoch": 0.029596744358120607,
      "grad_norm": 1.3429087400436401,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.5392,
      "step": 20
    },
    {
      "epoch": 0.03107658157602664,
      "grad_norm": 1.4494553804397583,
      "learning_rate": 7.191855733945387e-05,
      "loss": 8.4962,
      "step": 21
    },
    {
      "epoch": 0.032556418793932666,
      "grad_norm": 1.5279874801635742,
      "learning_rate": 6.873032967079561e-05,
      "loss": 7.8566,
      "step": 22
    },
    {
      "epoch": 0.0340362560118387,
      "grad_norm": 1.348048448562622,
      "learning_rate": 6.545084971874738e-05,
      "loss": 7.6185,
      "step": 23
    },
    {
      "epoch": 0.03551609322974473,
      "grad_norm": 1.3786513805389404,
      "learning_rate": 6.209609477998338e-05,
      "loss": 8.0027,
      "step": 24
    },
    {
      "epoch": 0.03699593044765076,
      "grad_norm": 1.4435409307479858,
      "learning_rate": 5.868240888334653e-05,
      "loss": 7.9214,
      "step": 25
    },
    {
      "epoch": 0.03699593044765076,
      "eval_loss": 1.9655485153198242,
      "eval_runtime": 27.7998,
      "eval_samples_per_second": 40.972,
      "eval_steps_per_second": 5.144,
      "step": 25
    },
    {
      "epoch": 0.03847576766555679,
      "grad_norm": 1.4376296997070312,
      "learning_rate": 5.522642316338268e-05,
      "loss": 7.7903,
      "step": 26
    },
    {
      "epoch": 0.03995560488346282,
      "grad_norm": 1.3910493850708008,
      "learning_rate": 5.174497483512506e-05,
      "loss": 7.8588,
      "step": 27
    },
    {
      "epoch": 0.04143544210136885,
      "grad_norm": 1.4668195247650146,
      "learning_rate": 4.825502516487497e-05,
      "loss": 7.3172,
      "step": 28
    },
    {
      "epoch": 0.04291527931927488,
      "grad_norm": 1.402090072631836,
      "learning_rate": 4.477357683661734e-05,
      "loss": 7.7589,
      "step": 29
    },
    {
      "epoch": 0.04439511653718091,
      "grad_norm": 1.4813686609268188,
      "learning_rate": 4.131759111665349e-05,
      "loss": 7.8017,
      "step": 30
    },
    {
      "epoch": 0.04587495375508694,
      "grad_norm": 2.463548421859741,
      "learning_rate": 3.790390522001662e-05,
      "loss": 7.6135,
      "step": 31
    },
    {
      "epoch": 0.04735479097299297,
      "grad_norm": 1.5885082483291626,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 8.5428,
      "step": 32
    },
    {
      "epoch": 0.048834628190899,
      "grad_norm": 1.560816764831543,
      "learning_rate": 3.12696703292044e-05,
      "loss": 7.8812,
      "step": 33
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": 1.5413081645965576,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 7.6855,
      "step": 34
    },
    {
      "epoch": 0.05179430262671106,
      "grad_norm": 1.4592106342315674,
      "learning_rate": 2.500000000000001e-05,
      "loss": 7.7255,
      "step": 35
    },
    {
      "epoch": 0.05327413984461709,
      "grad_norm": 1.670977234840393,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 8.4883,
      "step": 36
    },
    {
      "epoch": 0.05475397706252312,
      "grad_norm": 1.8226683139801025,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 8.7609,
      "step": 37
    },
    {
      "epoch": 0.05623381428042915,
      "grad_norm": 1.6706664562225342,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 8.6615,
      "step": 38
    },
    {
      "epoch": 0.05771365149833518,
      "grad_norm": 1.6275519132614136,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 8.1914,
      "step": 39
    },
    {
      "epoch": 0.059193488716241215,
      "grad_norm": 1.7154792547225952,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 7.8306,
      "step": 40
    },
    {
      "epoch": 0.060673325934147246,
      "grad_norm": 1.9715549945831299,
      "learning_rate": 9.549150281252633e-06,
      "loss": 7.6668,
      "step": 41
    },
    {
      "epoch": 0.06215316315205328,
      "grad_norm": 1.7641280889511108,
      "learning_rate": 7.597595192178702e-06,
      "loss": 8.4745,
      "step": 42
    },
    {
      "epoch": 0.06363300036995931,
      "grad_norm": 1.7766765356063843,
      "learning_rate": 5.852620357053651e-06,
      "loss": 8.406,
      "step": 43
    },
    {
      "epoch": 0.06511283758786533,
      "grad_norm": 1.8936883211135864,
      "learning_rate": 4.322727117869951e-06,
      "loss": 8.5094,
      "step": 44
    },
    {
      "epoch": 0.06659267480577137,
      "grad_norm": 1.8665753602981567,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 8.6963,
      "step": 45
    },
    {
      "epoch": 0.0680725120236774,
      "grad_norm": 2.0399463176727295,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 8.3318,
      "step": 46
    },
    {
      "epoch": 0.06955234924158342,
      "grad_norm": 1.9355149269104004,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 7.987,
      "step": 47
    },
    {
      "epoch": 0.07103218645948946,
      "grad_norm": 2.051863670349121,
      "learning_rate": 4.865965629214819e-07,
      "loss": 8.1395,
      "step": 48
    },
    {
      "epoch": 0.07251202367739548,
      "grad_norm": 2.5829217433929443,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 8.7321,
      "step": 49
    },
    {
      "epoch": 0.07399186089530152,
      "grad_norm": 2.865070343017578,
      "learning_rate": 0.0,
      "loss": 7.8764,
      "step": 50
    },
    {
      "epoch": 0.07399186089530152,
      "eval_loss": 1.9266914129257202,
      "eval_runtime": 27.9034,
      "eval_samples_per_second": 40.819,
      "eval_steps_per_second": 5.125,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.888596025933824e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}