{
  "best_metric": 2.8458566665649414,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.004827326530021144,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.654653060042287e-06,
      "eval_loss": 3.049283742904663,
      "eval_runtime": 592.2246,
      "eval_samples_per_second": 73.641,
      "eval_steps_per_second": 18.41,
      "step": 1
    },
    {
      "epoch": 9.654653060042287e-05,
      "grad_norm": 9.588415145874023,
      "learning_rate": 4.34e-05,
      "loss": 5.3317,
      "step": 10
    },
    {
      "epoch": 0.00019309306120084574,
      "grad_norm": 12.097651481628418,
      "learning_rate": 8.68e-05,
      "loss": 5.3358,
      "step": 20
    },
    {
      "epoch": 0.00028963959180126864,
      "grad_norm": 16.885087966918945,
      "learning_rate": 0.0001302,
      "loss": 5.4894,
      "step": 30
    },
    {
      "epoch": 0.0003861861224016915,
      "grad_norm": 25.137943267822266,
      "learning_rate": 0.0001736,
      "loss": 6.421,
      "step": 40
    },
    {
      "epoch": 0.0004827326530021144,
      "grad_norm": 32.7490119934082,
      "learning_rate": 0.000217,
      "loss": 8.0108,
      "step": 50
    },
    {
      "epoch": 0.0004827326530021144,
      "eval_loss": 3.020226240158081,
      "eval_runtime": 594.5306,
      "eval_samples_per_second": 73.355,
      "eval_steps_per_second": 18.339,
      "step": 50
    },
    {
      "epoch": 0.0005792791836025373,
      "grad_norm": 11.534395217895508,
      "learning_rate": 0.00021673569945319091,
      "loss": 5.425,
      "step": 60
    },
    {
      "epoch": 0.0006758257142029601,
      "grad_norm": 13.132587432861328,
      "learning_rate": 0.00021594408545846038,
      "loss": 5.2352,
      "step": 70
    },
    {
      "epoch": 0.000772372244803383,
      "grad_norm": 17.452167510986328,
      "learning_rate": 0.0002146290146796179,
      "loss": 5.6235,
      "step": 80
    },
    {
      "epoch": 0.0008689187754038058,
      "grad_norm": 12.21745491027832,
      "learning_rate": 0.0002127968940093076,
      "loss": 6.2937,
      "step": 90
    },
    {
      "epoch": 0.0009654653060042288,
      "grad_norm": 23.016115188598633,
      "learning_rate": 0.00021045664935527106,
      "loss": 7.6852,
      "step": 100
    },
    {
      "epoch": 0.0009654653060042288,
      "eval_loss": 3.0362181663513184,
      "eval_runtime": 593.3315,
      "eval_samples_per_second": 73.504,
      "eval_steps_per_second": 18.376,
      "step": 100
    },
    {
      "epoch": 0.0010620118366046515,
      "grad_norm": 21.253969192504883,
      "learning_rate": 0.00020761968215422217,
      "loss": 5.5279,
      "step": 110
    },
    {
      "epoch": 0.0011585583672050746,
      "grad_norm": 10.032729148864746,
      "learning_rate": 0.00020429981382519356,
      "loss": 5.3829,
      "step": 120
    },
    {
      "epoch": 0.0012551048978054974,
      "grad_norm": 18.771055221557617,
      "learning_rate": 0.00020051321843297219,
      "loss": 5.7132,
      "step": 130
    },
    {
      "epoch": 0.0013516514284059203,
      "grad_norm": 16.89134407043457,
      "learning_rate": 0.0001962783438896818,
      "loss": 6.0961,
      "step": 140
    },
    {
      "epoch": 0.0014481979590063431,
      "grad_norm": 18.406845092773438,
      "learning_rate": 0.0001916158220784091,
      "loss": 7.3874,
      "step": 150
    },
    {
      "epoch": 0.0014481979590063431,
      "eval_loss": 2.9778358936309814,
      "eval_runtime": 608.5301,
      "eval_samples_per_second": 71.668,
      "eval_steps_per_second": 17.917,
      "step": 150
    },
    {
      "epoch": 0.001544744489606766,
      "grad_norm": 12.62802505493164,
      "learning_rate": 0.00018654836833674362,
      "loss": 5.17,
      "step": 160
    },
    {
      "epoch": 0.0016412910202071888,
      "grad_norm": 12.671950340270996,
      "learning_rate": 0.0001811006707899361,
      "loss": 5.1057,
      "step": 170
    },
    {
      "epoch": 0.0017378375508076116,
      "grad_norm": 9.260117530822754,
      "learning_rate": 0.0001752992700728339,
      "loss": 5.3075,
      "step": 180
    },
    {
      "epoch": 0.0018343840814080345,
      "grad_norm": 13.710508346557617,
      "learning_rate": 0.00016917243002657602,
      "loss": 6.106,
      "step": 190
    },
    {
      "epoch": 0.0019309306120084576,
      "grad_norm": 15.460708618164062,
      "learning_rate": 0.00016275,
      "loss": 7.2009,
      "step": 200
    },
    {
      "epoch": 0.0019309306120084576,
      "eval_loss": 2.9488205909729004,
      "eval_runtime": 600.8577,
      "eval_samples_per_second": 72.583,
      "eval_steps_per_second": 18.146,
      "step": 200
    },
    {
      "epoch": 0.00202747714260888,
      "grad_norm": 12.144033432006836,
      "learning_rate": 0.0001560632694266149,
      "loss": 5.208,
      "step": 210
    },
    {
      "epoch": 0.002124023673209303,
      "grad_norm": 12.754302978515625,
      "learning_rate": 0.00014914481538562646,
      "loss": 5.3033,
      "step": 220
    },
    {
      "epoch": 0.0022205702038097263,
      "grad_norm": 10.792929649353027,
      "learning_rate": 0.0001420283438896818,
      "loss": 5.5286,
      "step": 230
    },
    {
      "epoch": 0.002317116734410149,
      "grad_norm": 13.988052368164062,
      "learning_rate": 0.00013474852567256393,
      "loss": 6.0218,
      "step": 240
    },
    {
      "epoch": 0.002413663265010572,
      "grad_norm": 26.327573776245117,
      "learning_rate": 0.00012734082727686196,
      "loss": 6.9626,
      "step": 250
    },
    {
      "epoch": 0.002413663265010572,
      "eval_loss": 2.8977274894714355,
      "eval_runtime": 605.0961,
      "eval_samples_per_second": 72.075,
      "eval_steps_per_second": 18.019,
      "step": 250
    },
    {
      "epoch": 0.002510209795610995,
      "grad_norm": 11.27015209197998,
      "learning_rate": 0.0001198413382645404,
      "loss": 5.2217,
      "step": 260
    },
    {
      "epoch": 0.0026067563262114177,
      "grad_norm": 20.627559661865234,
      "learning_rate": 0.00011228659539222137,
      "loss": 5.4243,
      "step": 270
    },
    {
      "epoch": 0.0027033028568118405,
      "grad_norm": 23.235761642456055,
      "learning_rate": 0.00010471340460777866,
      "loss": 5.634,
      "step": 280
    },
    {
      "epoch": 0.0027998493874122634,
      "grad_norm": 26.621187210083008,
      "learning_rate": 9.715866173545961e-05,
      "loss": 5.9205,
      "step": 290
    },
    {
      "epoch": 0.0028963959180126862,
      "grad_norm": 38.239044189453125,
      "learning_rate": 8.965917272313806e-05,
      "loss": 7.0007,
      "step": 300
    },
    {
      "epoch": 0.0028963959180126862,
      "eval_loss": 2.8962948322296143,
      "eval_runtime": 602.2623,
      "eval_samples_per_second": 72.414,
      "eval_steps_per_second": 18.103,
      "step": 300
    },
    {
      "epoch": 0.002992942448613109,
      "grad_norm": 25.593109130859375,
      "learning_rate": 8.225147432743606e-05,
      "loss": 5.3537,
      "step": 310
    },
    {
      "epoch": 0.003089488979213532,
      "grad_norm": 20.555158615112305,
      "learning_rate": 7.497165611031821e-05,
      "loss": 5.2222,
      "step": 320
    },
    {
      "epoch": 0.0031860355098139548,
      "grad_norm": 17.040815353393555,
      "learning_rate": 6.785518461437353e-05,
      "loss": 5.4117,
      "step": 330
    },
    {
      "epoch": 0.0032825820404143776,
      "grad_norm": 44.51173400878906,
      "learning_rate": 6.093673057338509e-05,
      "loss": 5.9886,
      "step": 340
    },
    {
      "epoch": 0.0033791285710148005,
      "grad_norm": 21.535146713256836,
      "learning_rate": 5.4250000000000024e-05,
      "loss": 6.8052,
      "step": 350
    },
    {
      "epoch": 0.0033791285710148005,
      "eval_loss": 2.8616268634796143,
      "eval_runtime": 594.2182,
      "eval_samples_per_second": 73.394,
      "eval_steps_per_second": 18.348,
      "step": 350
    },
    {
      "epoch": 0.0034756751016152233,
      "grad_norm": 15.48707389831543,
      "learning_rate": 4.782756997342398e-05,
      "loss": 5.2369,
      "step": 360
    },
    {
      "epoch": 0.003572221632215646,
      "grad_norm": 12.415227890014648,
      "learning_rate": 4.170072992716607e-05,
      "loss": 5.0543,
      "step": 370
    },
    {
      "epoch": 0.003668768162816069,
      "grad_norm": 25.784727096557617,
      "learning_rate": 3.5899329210063916e-05,
      "loss": 5.3615,
      "step": 380
    },
    {
      "epoch": 0.0037653146934164923,
      "grad_norm": 17.225284576416016,
      "learning_rate": 3.045163166325637e-05,
      "loss": 6.0156,
      "step": 390
    },
    {
      "epoch": 0.003861861224016915,
      "grad_norm": 25.5921573638916,
      "learning_rate": 2.5384177921590895e-05,
      "loss": 7.0295,
      "step": 400
    },
    {
      "epoch": 0.003861861224016915,
      "eval_loss": 2.8515334129333496,
      "eval_runtime": 594.2913,
      "eval_samples_per_second": 73.385,
      "eval_steps_per_second": 18.346,
      "step": 400
    },
    {
      "epoch": 0.003958407754617338,
      "grad_norm": 17.807329177856445,
      "learning_rate": 2.0721656110318213e-05,
      "loss": 4.9179,
      "step": 410
    },
    {
      "epoch": 0.00405495428521776,
      "grad_norm": 14.401619911193848,
      "learning_rate": 1.6486781567027783e-05,
      "loss": 5.0845,
      "step": 420
    },
    {
      "epoch": 0.004151500815818184,
      "grad_norm": 12.0913667678833,
      "learning_rate": 1.2700186174806422e-05,
      "loss": 5.4731,
      "step": 430
    },
    {
      "epoch": 0.004248047346418606,
      "grad_norm": 20.124168395996094,
      "learning_rate": 9.380317845777794e-06,
      "loss": 5.8493,
      "step": 440
    },
    {
      "epoch": 0.004344593877019029,
      "grad_norm": 19.486072540283203,
      "learning_rate": 6.543350644728947e-06,
      "loss": 7.0532,
      "step": 450
    },
    {
      "epoch": 0.004344593877019029,
      "eval_loss": 2.8470160961151123,
      "eval_runtime": 631.7626,
      "eval_samples_per_second": 69.032,
      "eval_steps_per_second": 17.258,
      "step": 450
    },
    {
      "epoch": 0.004441140407619453,
      "grad_norm": 12.585321426391602,
      "learning_rate": 4.2031059906924e-06,
      "loss": 5.103,
      "step": 460
    },
    {
      "epoch": 0.004537686938219875,
      "grad_norm": 12.552547454833984,
      "learning_rate": 2.3709853203820825e-06,
      "loss": 5.1533,
      "step": 470
    },
    {
      "epoch": 0.004634233468820298,
      "grad_norm": 13.851476669311523,
      "learning_rate": 1.0559145415396157e-06,
      "loss": 5.6343,
      "step": 480
    },
    {
      "epoch": 0.004730779999420721,
      "grad_norm": 20.92866325378418,
      "learning_rate": 2.643005468090745e-07,
      "loss": 6.2419,
      "step": 490
    },
    {
      "epoch": 0.004827326530021144,
      "grad_norm": 93.0564956665039,
      "learning_rate": 0.0,
      "loss": 6.9058,
      "step": 500
    },
    {
      "epoch": 0.004827326530021144,
      "eval_loss": 2.8458566665649414,
      "eval_runtime": 599.551,
      "eval_samples_per_second": 72.741,
      "eval_steps_per_second": 18.185,
      "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": 5203897601753088.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}