{
  "best_metric": 0.8320402503013611,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.23889154323936931,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047778308647873863,
      "eval_loss": 4.255329608917236,
      "eval_runtime": 12.7971,
      "eval_samples_per_second": 68.922,
      "eval_steps_per_second": 17.27,
      "step": 1
    },
    {
      "epoch": 0.004777830864787387,
      "grad_norm": 138.58535766601562,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 6.9317,
      "step": 10
    },
    {
      "epoch": 0.009555661729574774,
      "grad_norm": 131.84646606445312,
      "learning_rate": 8.560000000000001e-05,
      "loss": 4.5285,
      "step": 20
    },
    {
      "epoch": 0.01433349259436216,
      "grad_norm": 46.312652587890625,
      "learning_rate": 0.0001284,
      "loss": 3.299,
      "step": 30
    },
    {
      "epoch": 0.019111323459149548,
      "grad_norm": 38.920799255371094,
      "learning_rate": 0.00017120000000000001,
      "loss": 2.7357,
      "step": 40
    },
    {
      "epoch": 0.023889154323936932,
      "grad_norm": 42.04233169555664,
      "learning_rate": 0.000214,
      "loss": 2.9014,
      "step": 50
    },
    {
      "epoch": 0.023889154323936932,
      "eval_loss": 1.3917949199676514,
      "eval_runtime": 12.3884,
      "eval_samples_per_second": 71.196,
      "eval_steps_per_second": 17.839,
      "step": 50
    },
    {
      "epoch": 0.02866698518872432,
      "grad_norm": 102.38275146484375,
      "learning_rate": 0.00021373935337780118,
      "loss": 2.403,
      "step": 60
    },
    {
      "epoch": 0.033444816053511704,
      "grad_norm": 527.3989868164062,
      "learning_rate": 0.00021295868335534802,
      "loss": 2.5263,
      "step": 70
    },
    {
      "epoch": 0.038222646918299095,
      "grad_norm": 188.73924255371094,
      "learning_rate": 0.0002116617932785172,
      "loss": 3.2151,
      "step": 80
    },
    {
      "epoch": 0.04300047778308648,
      "grad_norm": 119.0323486328125,
      "learning_rate": 0.00020985500146540012,
      "loss": 3.5938,
      "step": 90
    },
    {
      "epoch": 0.047778308647873864,
      "grad_norm": 170.87159729003906,
      "learning_rate": 0.0002075471104240922,
      "loss": 4.0067,
      "step": 100
    },
    {
      "epoch": 0.047778308647873864,
      "eval_loss": 2.311336040496826,
      "eval_runtime": 13.4445,
      "eval_samples_per_second": 65.603,
      "eval_steps_per_second": 16.438,
      "step": 100
    },
    {
      "epoch": 0.05255613951266125,
      "grad_norm": 32.53251647949219,
      "learning_rate": 0.00020474936396775828,
      "loss": 10.3052,
      "step": 110
    },
    {
      "epoch": 0.05733397037744864,
      "grad_norm": 65.40621185302734,
      "learning_rate": 0.00020147539243590517,
      "loss": 7.4235,
      "step": 120
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 20.591093063354492,
      "learning_rate": 0.00019774114628873756,
      "loss": 3.2373,
      "step": 130
    },
    {
      "epoch": 0.06688963210702341,
      "grad_norm": 31.703140258789062,
      "learning_rate": 0.00019356481839811937,
      "loss": 2.8812,
      "step": 140
    },
    {
      "epoch": 0.0716674629718108,
      "grad_norm": 34.521854400634766,
      "learning_rate": 0.00018896675541373064,
      "loss": 3.2874,
      "step": 150
    },
    {
      "epoch": 0.0716674629718108,
      "eval_loss": 1.4771889448165894,
      "eval_runtime": 12.9239,
      "eval_samples_per_second": 68.246,
      "eval_steps_per_second": 17.1,
      "step": 150
    },
    {
      "epoch": 0.07644529383659819,
      "grad_norm": 28.358295440673828,
      "learning_rate": 0.00018396935863623567,
      "loss": 2.4476,
      "step": 160
    },
    {
      "epoch": 0.08122312470138557,
      "grad_norm": 21.966550827026367,
      "learning_rate": 0.00017859697488039784,
      "loss": 2.4135,
      "step": 170
    },
    {
      "epoch": 0.08600095556617296,
      "grad_norm": 32.07853317260742,
      "learning_rate": 0.00017287577785984542,
      "loss": 2.2956,
      "step": 180
    },
    {
      "epoch": 0.09077878643096035,
      "grad_norm": 17.3485107421875,
      "learning_rate": 0.0001668336406713699,
      "loss": 2.2849,
      "step": 190
    },
    {
      "epoch": 0.09555661729574773,
      "grad_norm": 14.762402534484863,
      "learning_rate": 0.0001605,
      "loss": 2.4335,
      "step": 200
    },
    {
      "epoch": 0.09555661729574773,
      "eval_loss": 1.0888148546218872,
      "eval_runtime": 12.7061,
      "eval_samples_per_second": 69.415,
      "eval_steps_per_second": 17.393,
      "step": 200
    },
    {
      "epoch": 0.10033444816053512,
      "grad_norm": 140.28663635253906,
      "learning_rate": 0.00015390571270643128,
      "loss": 1.7442,
      "step": 210
    },
    {
      "epoch": 0.1051122790253225,
      "grad_norm": 134.5390167236328,
      "learning_rate": 0.0001470829054955026,
      "loss": 1.9716,
      "step": 220
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 25.001611709594727,
      "learning_rate": 0.00014006481839811937,
      "loss": 2.0693,
      "step": 230
    },
    {
      "epoch": 0.11466794075489728,
      "grad_norm": 33.87446594238281,
      "learning_rate": 0.00013288564282916442,
      "loss": 2.4731,
      "step": 240
    },
    {
      "epoch": 0.11944577161968466,
      "grad_norm": 56.331687927246094,
      "learning_rate": 0.00012558035501036158,
      "loss": 2.7371,
      "step": 250
    },
    {
      "epoch": 0.11944577161968466,
      "eval_loss": 1.124778389930725,
      "eval_runtime": 12.2143,
      "eval_samples_per_second": 72.21,
      "eval_steps_per_second": 18.094,
      "step": 250
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 20.330785751342773,
      "learning_rate": 0.00011818454556963892,
      "loss": 1.6651,
      "step": 260
    },
    {
      "epoch": 0.12900143334925943,
      "grad_norm": 14.653603553771973,
      "learning_rate": 0.00011073424614716762,
      "loss": 1.6375,
      "step": 270
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 9.812971115112305,
      "learning_rate": 0.00010326575385283242,
      "loss": 2.0153,
      "step": 280
    },
    {
      "epoch": 0.1385570950788342,
      "grad_norm": 15.295802116394043,
      "learning_rate": 9.58154544303611e-05,
      "loss": 2.2795,
      "step": 290
    },
    {
      "epoch": 0.1433349259436216,
      "grad_norm": 12.265714645385742,
      "learning_rate": 8.841964498963846e-05,
      "loss": 2.2539,
      "step": 300
    },
    {
      "epoch": 0.1433349259436216,
      "eval_loss": 0.9771943092346191,
      "eval_runtime": 12.2008,
      "eval_samples_per_second": 72.291,
      "eval_steps_per_second": 18.114,
      "step": 300
    },
    {
      "epoch": 0.148112756808409,
      "grad_norm": 14.376371383666992,
      "learning_rate": 8.111435717083556e-05,
      "loss": 1.5526,
      "step": 310
    },
    {
      "epoch": 0.15289058767319638,
      "grad_norm": 9.20234203338623,
      "learning_rate": 7.393518160188063e-05,
      "loss": 1.572,
      "step": 320
    },
    {
      "epoch": 0.15766841853798375,
      "grad_norm": 11.955562591552734,
      "learning_rate": 6.69170945044974e-05,
      "loss": 1.8717,
      "step": 330
    },
    {
      "epoch": 0.16244624940277114,
      "grad_norm": 8.291068077087402,
      "learning_rate": 6.009428729356871e-05,
      "loss": 1.9432,
      "step": 340
    },
    {
      "epoch": 0.16722408026755853,
      "grad_norm": 21.525508880615234,
      "learning_rate": 5.3500000000000026e-05,
      "loss": 2.3061,
      "step": 350
    },
    {
      "epoch": 0.16722408026755853,
      "eval_loss": 0.9378606677055359,
      "eval_runtime": 12.1993,
      "eval_samples_per_second": 72.3,
      "eval_steps_per_second": 18.116,
      "step": 350
    },
    {
      "epoch": 0.17200191113234592,
      "grad_norm": 11.051887512207031,
      "learning_rate": 4.7166359328630106e-05,
      "loss": 1.5252,
      "step": 360
    },
    {
      "epoch": 0.1767797419971333,
      "grad_norm": 16.316925048828125,
      "learning_rate": 4.112422214015456e-05,
      "loss": 1.4291,
      "step": 370
    },
    {
      "epoch": 0.1815575728619207,
      "grad_norm": 34.651214599609375,
      "learning_rate": 3.5403025119602206e-05,
      "loss": 1.7447,
      "step": 380
    },
    {
      "epoch": 0.18633540372670807,
      "grad_norm": 15.149808883666992,
      "learning_rate": 3.0030641363764346e-05,
      "loss": 1.9199,
      "step": 390
    },
    {
      "epoch": 0.19111323459149546,
      "grad_norm": 13.764430046081543,
      "learning_rate": 2.5033244586269365e-05,
      "loss": 2.0217,
      "step": 400
    },
    {
      "epoch": 0.19111323459149546,
      "eval_loss": 0.8595229387283325,
      "eval_runtime": 12.2031,
      "eval_samples_per_second": 72.277,
      "eval_steps_per_second": 18.11,
      "step": 400
    },
    {
      "epoch": 0.19589106545628285,
      "grad_norm": 24.64581871032715,
      "learning_rate": 2.0435181601880635e-05,
      "loss": 1.1874,
      "step": 410
    },
    {
      "epoch": 0.20066889632107024,
      "grad_norm": 17.642654418945312,
      "learning_rate": 1.625885371126242e-05,
      "loss": 1.5195,
      "step": 420
    },
    {
      "epoch": 0.20544672718585763,
      "grad_norm": 17.003334045410156,
      "learning_rate": 1.2524607564094813e-05,
      "loss": 1.8292,
      "step": 430
    },
    {
      "epoch": 0.210224558050645,
      "grad_norm": 13.311195373535156,
      "learning_rate": 9.250636032241695e-06,
      "loss": 1.8517,
      "step": 440
    },
    {
      "epoch": 0.21500238891543239,
      "grad_norm": 12.355936050415039,
      "learning_rate": 6.45288957590781e-06,
      "loss": 2.2005,
      "step": 450
    },
    {
      "epoch": 0.21500238891543239,
      "eval_loss": 0.837338387966156,
      "eval_runtime": 12.301,
      "eval_samples_per_second": 71.701,
      "eval_steps_per_second": 17.966,
      "step": 450
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 11.863606452941895,
      "learning_rate": 4.144998534599878e-06,
      "loss": 1.1789,
      "step": 460
    },
    {
      "epoch": 0.22455805064500717,
      "grad_norm": 20.274431228637695,
      "learning_rate": 2.3382067214827915e-06,
      "loss": 1.3979,
      "step": 470
    },
    {
      "epoch": 0.22933588150979456,
      "grad_norm": 10.406599998474121,
      "learning_rate": 1.0413166446519713e-06,
      "loss": 1.7026,
      "step": 480
    },
    {
      "epoch": 0.23411371237458195,
      "grad_norm": 9.674276351928711,
      "learning_rate": 2.6064662219881083e-07,
      "loss": 1.941,
      "step": 490
    },
    {
      "epoch": 0.23889154323936931,
      "grad_norm": 12.152741432189941,
      "learning_rate": 0.0,
      "loss": 2.1046,
      "step": 500
    },
    {
      "epoch": 0.23889154323936931,
      "eval_loss": 0.8320402503013611,
      "eval_runtime": 12.1319,
      "eval_samples_per_second": 72.701,
      "eval_steps_per_second": 18.216,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 4657011228672000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}