{
  "best_metric": 0.3960544764995575,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.10398253093480295,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002079650618696059,
      "eval_loss": 0.9533683061599731,
      "eval_runtime": 156.6179,
      "eval_samples_per_second": 3.237,
      "eval_steps_per_second": 0.811,
      "step": 1
    },
    {
      "epoch": 0.002079650618696059,
      "grad_norm": 3.18047833442688,
      "learning_rate": 4.36e-05,
      "loss": 0.8342,
      "step": 10
    },
    {
      "epoch": 0.004159301237392118,
      "grad_norm": 2.9091711044311523,
      "learning_rate": 8.72e-05,
      "loss": 0.5367,
      "step": 20
    },
    {
      "epoch": 0.006238951856088177,
      "grad_norm": 12.142705917358398,
      "learning_rate": 0.0001308,
      "loss": 0.5186,
      "step": 30
    },
    {
      "epoch": 0.008318602474784236,
      "grad_norm": 1.364218831062317,
      "learning_rate": 0.0001744,
      "loss": 0.5148,
      "step": 40
    },
    {
      "epoch": 0.010398253093480296,
      "grad_norm": 2.0976734161376953,
      "learning_rate": 0.000218,
      "loss": 0.5504,
      "step": 50
    },
    {
      "epoch": 0.010398253093480296,
      "eval_loss": 0.5830835103988647,
      "eval_runtime": 80.9255,
      "eval_samples_per_second": 6.265,
      "eval_steps_per_second": 1.569,
      "step": 50
    },
    {
      "epoch": 0.012477903712176355,
      "grad_norm": 1.4801353216171265,
      "learning_rate": 0.00021773448147832086,
      "loss": 0.5768,
      "step": 60
    },
    {
      "epoch": 0.014557554330872413,
      "grad_norm": 1.2638306617736816,
      "learning_rate": 0.0002169392194928312,
      "loss": 0.585,
      "step": 70
    },
    {
      "epoch": 0.01663720494956847,
      "grad_norm": 1.3111450672149658,
      "learning_rate": 0.00021561808847998484,
      "loss": 0.6144,
      "step": 80
    },
    {
      "epoch": 0.01871685556826453,
      "grad_norm": 1.4548810720443726,
      "learning_rate": 0.00021377752485727676,
      "loss": 0.5459,
      "step": 90
    },
    {
      "epoch": 0.020796506186960592,
      "grad_norm": 1.1708745956420898,
      "learning_rate": 0.00021142649566566402,
      "loss": 0.6452,
      "step": 100
    },
    {
      "epoch": 0.020796506186960592,
      "eval_loss": 0.553749680519104,
      "eval_runtime": 80.7517,
      "eval_samples_per_second": 6.279,
      "eval_steps_per_second": 1.573,
      "step": 100
    },
    {
      "epoch": 0.02287615680565665,
      "grad_norm": 1.927892804145813,
      "learning_rate": 0.0002085764548830435,
      "loss": 0.5392,
      "step": 110
    },
    {
      "epoch": 0.02495580742435271,
      "grad_norm": 1.463425636291504,
      "learning_rate": 0.00020524128762162305,
      "loss": 0.5582,
      "step": 120
    },
    {
      "epoch": 0.027035458043048768,
      "grad_norm": 1.3318297863006592,
      "learning_rate": 0.00020143724248105043,
      "loss": 0.549,
      "step": 130
    },
    {
      "epoch": 0.029115108661744826,
      "grad_norm": 2.8513331413269043,
      "learning_rate": 0.0001971828523868693,
      "loss": 0.559,
      "step": 140
    },
    {
      "epoch": 0.031194759280440885,
      "grad_norm": 1.3817558288574219,
      "learning_rate": 0.0001924988442999686,
      "loss": 0.5554,
      "step": 150
    },
    {
      "epoch": 0.031194759280440885,
      "eval_loss": 0.5377894043922424,
      "eval_runtime": 80.77,
      "eval_samples_per_second": 6.277,
      "eval_steps_per_second": 1.572,
      "step": 150
    },
    {
      "epoch": 0.03327440989913694,
      "grad_norm": 1.0492221117019653,
      "learning_rate": 0.00018740803823691298,
      "loss": 0.569,
      "step": 160
    },
    {
      "epoch": 0.035354060517833005,
      "grad_norm": 1.0622763633728027,
      "learning_rate": 0.00018193523609311556,
      "loss": 0.5299,
      "step": 170
    },
    {
      "epoch": 0.03743371113652906,
      "grad_norm": 1.661616325378418,
      "learning_rate": 0.00017610710081049675,
      "loss": 0.5821,
      "step": 180
    },
    {
      "epoch": 0.03951336175522512,
      "grad_norm": 1.344832420349121,
      "learning_rate": 0.00016995202647831142,
      "loss": 0.5302,
      "step": 190
    },
    {
      "epoch": 0.041593012373921184,
      "grad_norm": 1.5419880151748657,
      "learning_rate": 0.00016350000000000002,
      "loss": 0.566,
      "step": 200
    },
    {
      "epoch": 0.041593012373921184,
      "eval_loss": 0.5337647199630737,
      "eval_runtime": 80.6952,
      "eval_samples_per_second": 6.283,
      "eval_steps_per_second": 1.574,
      "step": 200
    },
    {
      "epoch": 0.04367266299261724,
      "grad_norm": 1.1745060682296753,
      "learning_rate": 0.00015678245500000943,
      "loss": 0.5042,
      "step": 210
    },
    {
      "epoch": 0.0457523136113133,
      "grad_norm": 1.176100492477417,
      "learning_rate": 0.00014983211868233444,
      "loss": 0.5065,
      "step": 220
    },
    {
      "epoch": 0.047831964230009356,
      "grad_norm": 1.4111114740371704,
      "learning_rate": 0.00014268285238686927,
      "loss": 0.4751,
      "step": 230
    },
    {
      "epoch": 0.04991161484870542,
      "grad_norm": 1.2417322397232056,
      "learning_rate": 0.00013536948662036378,
      "loss": 0.5278,
      "step": 240
    },
    {
      "epoch": 0.051991265467401473,
      "grad_norm": 1.5264148712158203,
      "learning_rate": 0.00012792765136569544,
      "loss": 0.4541,
      "step": 250
    },
    {
      "epoch": 0.051991265467401473,
      "eval_loss": 0.5013260841369629,
      "eval_runtime": 80.7104,
      "eval_samples_per_second": 6.282,
      "eval_steps_per_second": 1.574,
      "step": 250
    },
    {
      "epoch": 0.054070916086097535,
      "grad_norm": 1.2806155681610107,
      "learning_rate": 0.00012039360249617425,
      "loss": 0.4848,
      "step": 260
    },
    {
      "epoch": 0.0561505667047936,
      "grad_norm": 0.8744197487831116,
      "learning_rate": 0.00011280404514057264,
      "loss": 0.4888,
      "step": 270
    },
    {
      "epoch": 0.05823021732348965,
      "grad_norm": 1.0379194021224976,
      "learning_rate": 0.00010519595485942743,
      "loss": 0.4923,
      "step": 280
    },
    {
      "epoch": 0.060309867942185715,
      "grad_norm": 1.0062249898910522,
      "learning_rate": 9.76063975038258e-05,
      "loss": 0.4953,
      "step": 290
    },
    {
      "epoch": 0.06238951856088177,
      "grad_norm": 1.2005985975265503,
      "learning_rate": 9.00723486343046e-05,
      "loss": 0.4437,
      "step": 300
    },
    {
      "epoch": 0.06238951856088177,
      "eval_loss": 0.4650544822216034,
      "eval_runtime": 80.7039,
      "eval_samples_per_second": 6.282,
      "eval_steps_per_second": 1.574,
      "step": 300
    },
    {
      "epoch": 0.06446916917957783,
      "grad_norm": 1.3032387495040894,
      "learning_rate": 8.263051337963623e-05,
      "loss": 0.4818,
      "step": 310
    },
    {
      "epoch": 0.06654881979827389,
      "grad_norm": 1.2554705142974854,
      "learning_rate": 7.531714761313074e-05,
      "loss": 0.469,
      "step": 320
    },
    {
      "epoch": 0.06862847041696996,
      "grad_norm": 1.2291592359542847,
      "learning_rate": 6.816788131766559e-05,
      "loss": 0.4692,
      "step": 330
    },
    {
      "epoch": 0.07070812103566601,
      "grad_norm": 0.8150742650032043,
      "learning_rate": 6.121754499999055e-05,
      "loss": 0.4679,
      "step": 340
    },
    {
      "epoch": 0.07278777165436207,
      "grad_norm": 0.9758222699165344,
      "learning_rate": 5.450000000000003e-05,
      "loss": 0.4195,
      "step": 350
    },
    {
      "epoch": 0.07278777165436207,
      "eval_loss": 0.4387960731983185,
      "eval_runtime": 80.8477,
      "eval_samples_per_second": 6.271,
      "eval_steps_per_second": 1.571,
      "step": 350
    },
    {
      "epoch": 0.07486742227305812,
      "grad_norm": 0.8487042188644409,
      "learning_rate": 4.804797352168861e-05,
      "loss": 0.4459,
      "step": 360
    },
    {
      "epoch": 0.07694707289175419,
      "grad_norm": 1.076621413230896,
      "learning_rate": 4.189289918950325e-05,
      "loss": 0.4533,
      "step": 370
    },
    {
      "epoch": 0.07902672351045024,
      "grad_norm": 0.8744729161262512,
      "learning_rate": 3.606476390688449e-05,
      "loss": 0.4404,
      "step": 380
    },
    {
      "epoch": 0.0811063741291463,
      "grad_norm": 0.8504107594490051,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 0.4176,
      "step": 390
    },
    {
      "epoch": 0.08318602474784237,
      "grad_norm": 0.8338978290557861,
      "learning_rate": 2.550115570003141e-05,
      "loss": 0.4642,
      "step": 400
    },
    {
      "epoch": 0.08318602474784237,
      "eval_loss": 0.4155665934085846,
      "eval_runtime": 80.7198,
      "eval_samples_per_second": 6.281,
      "eval_steps_per_second": 1.573,
      "step": 400
    },
    {
      "epoch": 0.08526567536653842,
      "grad_norm": 0.9245039820671082,
      "learning_rate": 2.081714761313074e-05,
      "loss": 0.4084,
      "step": 410
    },
    {
      "epoch": 0.08734532598523448,
      "grad_norm": 0.9160316586494446,
      "learning_rate": 1.656275751894957e-05,
      "loss": 0.4022,
      "step": 420
    },
    {
      "epoch": 0.08942497660393053,
      "grad_norm": 0.9029657244682312,
      "learning_rate": 1.275871237837696e-05,
      "loss": 0.3921,
      "step": 430
    },
    {
      "epoch": 0.0915046272226266,
      "grad_norm": 0.8298301696777344,
      "learning_rate": 9.423545116956494e-06,
      "loss": 0.3997,
      "step": 440
    },
    {
      "epoch": 0.09358427784132266,
      "grad_norm": 0.8411400318145752,
      "learning_rate": 6.573504334335994e-06,
      "loss": 0.3864,
      "step": 450
    },
    {
      "epoch": 0.09358427784132266,
      "eval_loss": 0.39971646666526794,
      "eval_runtime": 80.8995,
      "eval_samples_per_second": 6.267,
      "eval_steps_per_second": 1.57,
      "step": 450
    },
    {
      "epoch": 0.09566392846001871,
      "grad_norm": 1.0529413223266602,
      "learning_rate": 4.22247514272324e-06,
      "loss": 0.3989,
      "step": 460
    },
    {
      "epoch": 0.09774357907871478,
      "grad_norm": 1.2673580646514893,
      "learning_rate": 2.38191152001518e-06,
      "loss": 0.4017,
      "step": 470
    },
    {
      "epoch": 0.09982322969741084,
      "grad_norm": 0.7570623755455017,
      "learning_rate": 1.0607805071688306e-06,
      "loss": 0.4142,
      "step": 480
    },
    {
      "epoch": 0.10190288031610689,
      "grad_norm": 0.9010934829711914,
      "learning_rate": 2.655185216791625e-07,
      "loss": 0.3869,
      "step": 490
    },
    {
      "epoch": 0.10398253093480295,
      "grad_norm": 1.2820464372634888,
      "learning_rate": 0.0,
      "loss": 0.4153,
      "step": 500
    },
    {
      "epoch": 0.10398253093480295,
      "eval_loss": 0.3960544764995575,
      "eval_runtime": 80.8174,
      "eval_samples_per_second": 6.273,
      "eval_steps_per_second": 1.571,
      "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": 6.694211790097613e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}