{
  "best_metric": 0.6699920892715454,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.07028641714988579,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007028641714988579,
      "grad_norm": 3.985713005065918,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9101,
      "step": 1
    },
    {
      "epoch": 0.0007028641714988579,
      "eval_loss": 1.2333168983459473,
      "eval_runtime": 329.6451,
      "eval_samples_per_second": 7.271,
      "eval_steps_per_second": 3.637,
      "step": 1
    },
    {
      "epoch": 0.0014057283429977157,
      "grad_norm": 3.467237710952759,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.8645,
      "step": 2
    },
    {
      "epoch": 0.0021085925144965737,
      "grad_norm": 4.0260396003723145,
      "learning_rate": 1e-05,
      "loss": 0.8497,
      "step": 3
    },
    {
      "epoch": 0.0028114566859954314,
      "grad_norm": 3.5175299644470215,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.8297,
      "step": 4
    },
    {
      "epoch": 0.003514320857494289,
      "grad_norm": 3.0513343811035156,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9402,
      "step": 5
    },
    {
      "epoch": 0.004217185028993147,
      "grad_norm": 2.0091588497161865,
      "learning_rate": 2e-05,
      "loss": 0.9226,
      "step": 6
    },
    {
      "epoch": 0.004920049200492005,
      "grad_norm": 1.5375112295150757,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.8269,
      "step": 7
    },
    {
      "epoch": 0.005622913371990863,
      "grad_norm": 1.1322797536849976,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.8076,
      "step": 8
    },
    {
      "epoch": 0.0063257775434897206,
      "grad_norm": 0.6666527390480042,
      "learning_rate": 3e-05,
      "loss": 0.7947,
      "step": 9
    },
    {
      "epoch": 0.007028641714988578,
      "grad_norm": 0.49241289496421814,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.8479,
      "step": 10
    },
    {
      "epoch": 0.007731505886487436,
      "grad_norm": 0.38597196340560913,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.8584,
      "step": 11
    },
    {
      "epoch": 0.008434370057986295,
      "grad_norm": 0.38379645347595215,
      "learning_rate": 4e-05,
      "loss": 0.9209,
      "step": 12
    },
    {
      "epoch": 0.009137234229485152,
      "grad_norm": 0.3469511866569519,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.9364,
      "step": 13
    },
    {
      "epoch": 0.00984009840098401,
      "grad_norm": 0.37990155816078186,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.9295,
      "step": 14
    },
    {
      "epoch": 0.010542962572482868,
      "grad_norm": 0.39598187804222107,
      "learning_rate": 5e-05,
      "loss": 0.98,
      "step": 15
    },
    {
      "epoch": 0.011245826743981726,
      "grad_norm": 0.5101740956306458,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.869,
      "step": 16
    },
    {
      "epoch": 0.011948690915480583,
      "grad_norm": 0.4814358651638031,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.8725,
      "step": 17
    },
    {
      "epoch": 0.012651555086979441,
      "grad_norm": 0.4803312420845032,
      "learning_rate": 6e-05,
      "loss": 0.8974,
      "step": 18
    },
    {
      "epoch": 0.013354419258478299,
      "grad_norm": 0.5351816415786743,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.8547,
      "step": 19
    },
    {
      "epoch": 0.014057283429977157,
      "grad_norm": 0.3521532416343689,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8167,
      "step": 20
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.3495865762233734,
      "learning_rate": 7e-05,
      "loss": 0.8601,
      "step": 21
    },
    {
      "epoch": 0.015463011772974872,
      "grad_norm": 0.32179948687553406,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.9306,
      "step": 22
    },
    {
      "epoch": 0.01616587594447373,
      "grad_norm": 0.31504809856414795,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.9073,
      "step": 23
    },
    {
      "epoch": 0.01686874011597259,
      "grad_norm": 0.29273295402526855,
      "learning_rate": 8e-05,
      "loss": 0.9163,
      "step": 24
    },
    {
      "epoch": 0.017571604287471447,
      "grad_norm": 0.29041165113449097,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.9695,
      "step": 25
    },
    {
      "epoch": 0.018274468458970305,
      "grad_norm": 0.27887824177742004,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.9974,
      "step": 26
    },
    {
      "epoch": 0.018977332630469163,
      "grad_norm": 0.2727268934249878,
      "learning_rate": 9e-05,
      "loss": 0.9174,
      "step": 27
    },
    {
      "epoch": 0.01968019680196802,
      "grad_norm": 0.32749247550964355,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.0012,
      "step": 28
    },
    {
      "epoch": 0.020383060973466878,
      "grad_norm": 0.3218176066875458,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.9661,
      "step": 29
    },
    {
      "epoch": 0.021085925144965736,
      "grad_norm": 0.29646337032318115,
      "learning_rate": 0.0001,
      "loss": 0.9915,
      "step": 30
    },
    {
      "epoch": 0.021788789316464593,
      "grad_norm": 0.34624406695365906,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.8692,
      "step": 31
    },
    {
      "epoch": 0.02249165348796345,
      "grad_norm": 0.768728494644165,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.8271,
      "step": 32
    },
    {
      "epoch": 0.02319451765946231,
      "grad_norm": 0.3600139617919922,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.887,
      "step": 33
    },
    {
      "epoch": 0.023897381830961167,
      "grad_norm": 0.4439491033554077,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.8287,
      "step": 34
    },
    {
      "epoch": 0.024600246002460024,
      "grad_norm": 0.5002362132072449,
      "learning_rate": 9.978670881475172e-05,
      "loss": 1.0547,
      "step": 35
    },
    {
      "epoch": 0.025303110173958882,
      "grad_norm": 0.36719855666160583,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.9393,
      "step": 36
    },
    {
      "epoch": 0.02600597434545774,
      "grad_norm": 0.4160923659801483,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.985,
      "step": 37
    },
    {
      "epoch": 0.026708838516956598,
      "grad_norm": 0.48960939049720764,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.9871,
      "step": 38
    },
    {
      "epoch": 0.027411702688455455,
      "grad_norm": 0.406502366065979,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.9413,
      "step": 39
    },
    {
      "epoch": 0.028114566859954313,
      "grad_norm": 0.3597155511379242,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.9638,
      "step": 40
    },
    {
      "epoch": 0.02881743103145317,
      "grad_norm": 0.3127121925354004,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.962,
      "step": 41
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 0.3300633430480957,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.9166,
      "step": 42
    },
    {
      "epoch": 0.030223159374450886,
      "grad_norm": 0.3021150827407837,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.8592,
      "step": 43
    },
    {
      "epoch": 0.030926023545949744,
      "grad_norm": 0.33230969309806824,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.8466,
      "step": 44
    },
    {
      "epoch": 0.0316288877174486,
      "grad_norm": 0.3447709381580353,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.8761,
      "step": 45
    },
    {
      "epoch": 0.03233175188894746,
      "grad_norm": 0.3439708948135376,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.8295,
      "step": 46
    },
    {
      "epoch": 0.03303461606044632,
      "grad_norm": 0.3578321933746338,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8659,
      "step": 47
    },
    {
      "epoch": 0.03373748023194518,
      "grad_norm": 0.4063121974468231,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.9674,
      "step": 48
    },
    {
      "epoch": 0.03444034440344403,
      "grad_norm": 0.41490623354911804,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.9979,
      "step": 49
    },
    {
      "epoch": 0.035143208574942894,
      "grad_norm": 0.6388435959815979,
      "learning_rate": 9.662361147021779e-05,
      "loss": 1.0037,
      "step": 50
    },
    {
      "epoch": 0.035143208574942894,
      "eval_loss": 0.7931326031684875,
      "eval_runtime": 332.4888,
      "eval_samples_per_second": 7.209,
      "eval_steps_per_second": 3.606,
      "step": 50
    },
    {
      "epoch": 0.03584607274644175,
      "grad_norm": 5.554098606109619,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.7428,
      "step": 51
    },
    {
      "epoch": 0.03654893691794061,
      "grad_norm": 0.6978570222854614,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.4409,
      "step": 52
    },
    {
      "epoch": 0.037251801089439464,
      "grad_norm": 0.28626111149787903,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.3601,
      "step": 53
    },
    {
      "epoch": 0.037954665260938325,
      "grad_norm": 0.1934920996427536,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.3868,
      "step": 54
    },
    {
      "epoch": 0.03865752943243718,
      "grad_norm": 0.18251414597034454,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.3611,
      "step": 55
    },
    {
      "epoch": 0.03936039360393604,
      "grad_norm": 0.2201131284236908,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.4773,
      "step": 56
    },
    {
      "epoch": 0.040063257775434895,
      "grad_norm": 0.21173296868801117,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.486,
      "step": 57
    },
    {
      "epoch": 0.040766121946933756,
      "grad_norm": 0.2153291255235672,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.4396,
      "step": 58
    },
    {
      "epoch": 0.04146898611843261,
      "grad_norm": 0.20555301010608673,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.5213,
      "step": 59
    },
    {
      "epoch": 0.04217185028993147,
      "grad_norm": 0.19719314575195312,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.5652,
      "step": 60
    },
    {
      "epoch": 0.042874714461430326,
      "grad_norm": 0.18588709831237793,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.5582,
      "step": 61
    },
    {
      "epoch": 0.04357757863292919,
      "grad_norm": 0.22327612340450287,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.7321,
      "step": 62
    },
    {
      "epoch": 0.04428044280442804,
      "grad_norm": 0.21731068193912506,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.7298,
      "step": 63
    },
    {
      "epoch": 0.0449833069759269,
      "grad_norm": 0.21543888747692108,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6652,
      "step": 64
    },
    {
      "epoch": 0.04568617114742576,
      "grad_norm": 0.23041720688343048,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.7261,
      "step": 65
    },
    {
      "epoch": 0.04638903531892462,
      "grad_norm": 0.20984987914562225,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.6916,
      "step": 66
    },
    {
      "epoch": 0.04709189949042347,
      "grad_norm": 0.22370988130569458,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.6645,
      "step": 67
    },
    {
      "epoch": 0.04779476366192233,
      "grad_norm": 0.2238708734512329,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.6684,
      "step": 68
    },
    {
      "epoch": 0.048497627833421195,
      "grad_norm": 0.2282782942056656,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.6836,
      "step": 69
    },
    {
      "epoch": 0.04920049200492005,
      "grad_norm": 0.22426971793174744,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.6277,
      "step": 70
    },
    {
      "epoch": 0.04990335617641891,
      "grad_norm": 0.24329598248004913,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.7216,
      "step": 71
    },
    {
      "epoch": 0.050606220347917764,
      "grad_norm": 0.23810680210590363,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.6573,
      "step": 72
    },
    {
      "epoch": 0.051309084519416626,
      "grad_norm": 0.2418031245470047,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.7383,
      "step": 73
    },
    {
      "epoch": 0.05201194869091548,
      "grad_norm": 0.23166213929653168,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.7561,
      "step": 74
    },
    {
      "epoch": 0.05271481286241434,
      "grad_norm": 0.24179698526859283,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.6931,
      "step": 75
    },
    {
      "epoch": 0.053417677033913195,
      "grad_norm": 0.25874027609825134,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.8606,
      "step": 76
    },
    {
      "epoch": 0.05412054120541206,
      "grad_norm": 0.2505108118057251,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.8458,
      "step": 77
    },
    {
      "epoch": 0.05482340537691091,
      "grad_norm": 0.2619728446006775,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.857,
      "step": 78
    },
    {
      "epoch": 0.05552626954840977,
      "grad_norm": 0.2551406919956207,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.8475,
      "step": 79
    },
    {
      "epoch": 0.056229133719908626,
      "grad_norm": 0.26327502727508545,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.7916,
      "step": 80
    },
    {
      "epoch": 0.05693199789140749,
      "grad_norm": 0.28274351358413696,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8075,
      "step": 81
    },
    {
      "epoch": 0.05763486206290634,
      "grad_norm": 0.2752515971660614,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.8331,
      "step": 82
    },
    {
      "epoch": 0.0583377262344052,
      "grad_norm": 0.4340633451938629,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.7778,
      "step": 83
    },
    {
      "epoch": 0.05904059040590406,
      "grad_norm": 0.362873911857605,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.863,
      "step": 84
    },
    {
      "epoch": 0.05974345457740292,
      "grad_norm": 0.3778440058231354,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.7936,
      "step": 85
    },
    {
      "epoch": 0.06044631874890177,
      "grad_norm": 0.3569698929786682,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.8301,
      "step": 86
    },
    {
      "epoch": 0.061149182920400634,
      "grad_norm": 0.3684358596801758,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.8868,
      "step": 87
    },
    {
      "epoch": 0.06185204709189949,
      "grad_norm": 0.3750736117362976,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.9028,
      "step": 88
    },
    {
      "epoch": 0.06255491126339835,
      "grad_norm": 0.3491847813129425,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.8992,
      "step": 89
    },
    {
      "epoch": 0.0632577754348972,
      "grad_norm": 0.30583202838897705,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.881,
      "step": 90
    },
    {
      "epoch": 0.06396063960639606,
      "grad_norm": 0.25735631585121155,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.8979,
      "step": 91
    },
    {
      "epoch": 0.06466350377789493,
      "grad_norm": 0.2660073935985565,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.8359,
      "step": 92
    },
    {
      "epoch": 0.06536636794939378,
      "grad_norm": 0.3032679557800293,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.8739,
      "step": 93
    },
    {
      "epoch": 0.06606923212089263,
      "grad_norm": 0.334891140460968,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.85,
      "step": 94
    },
    {
      "epoch": 0.06677209629239149,
      "grad_norm": 0.3186686933040619,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.874,
      "step": 95
    },
    {
      "epoch": 0.06747496046389036,
      "grad_norm": 0.32608991861343384,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.9199,
      "step": 96
    },
    {
      "epoch": 0.06817782463538921,
      "grad_norm": 0.3285480737686157,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.8406,
      "step": 97
    },
    {
      "epoch": 0.06888068880688807,
      "grad_norm": 0.35589680075645447,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8486,
      "step": 98
    },
    {
      "epoch": 0.06958355297838692,
      "grad_norm": 0.3586467206478119,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.9165,
      "step": 99
    },
    {
      "epoch": 0.07028641714988579,
      "grad_norm": 0.49421557784080505,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.9244,
      "step": 100
    },
    {
      "epoch": 0.07028641714988579,
      "eval_loss": 0.6699920892715454,
      "eval_runtime": 332.5314,
      "eval_samples_per_second": 7.208,
      "eval_steps_per_second": 3.606,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.43583936364544e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}