{
  "best_metric": 1.8152918815612793,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.019923295313044778,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019923295313044778,
      "grad_norm": 1.2284634113311768,
      "learning_rate": 1e-05,
      "loss": 2.9428,
      "step": 1
    },
    {
      "epoch": 0.00019923295313044778,
      "eval_loss": 4.057371616363525,
      "eval_runtime": 602.6822,
      "eval_samples_per_second": 14.027,
      "eval_steps_per_second": 3.508,
      "step": 1
    },
    {
      "epoch": 0.00039846590626089557,
      "grad_norm": 1.68904447555542,
      "learning_rate": 2e-05,
      "loss": 3.5104,
      "step": 2
    },
    {
      "epoch": 0.0005976988593913434,
      "grad_norm": 1.1529206037521362,
      "learning_rate": 3e-05,
      "loss": 2.5356,
      "step": 3
    },
    {
      "epoch": 0.0007969318125217911,
      "grad_norm": 1.5264250040054321,
      "learning_rate": 4e-05,
      "loss": 3.2004,
      "step": 4
    },
    {
      "epoch": 0.0009961647656522388,
      "grad_norm": 1.771896481513977,
      "learning_rate": 5e-05,
      "loss": 3.2337,
      "step": 5
    },
    {
      "epoch": 0.0011953977187826868,
      "grad_norm": 1.5935925245285034,
      "learning_rate": 6e-05,
      "loss": 3.3152,
      "step": 6
    },
    {
      "epoch": 0.0013946306719131345,
      "grad_norm": 1.6249325275421143,
      "learning_rate": 7e-05,
      "loss": 2.8173,
      "step": 7
    },
    {
      "epoch": 0.0015938636250435823,
      "grad_norm": 1.6689910888671875,
      "learning_rate": 8e-05,
      "loss": 2.8131,
      "step": 8
    },
    {
      "epoch": 0.00179309657817403,
      "grad_norm": 1.5419508218765259,
      "learning_rate": 9e-05,
      "loss": 2.5659,
      "step": 9
    },
    {
      "epoch": 0.0019923295313044776,
      "grad_norm": 1.5755772590637207,
      "learning_rate": 0.0001,
      "loss": 2.3418,
      "step": 10
    },
    {
      "epoch": 0.0021915624844349255,
      "grad_norm": 1.8057647943496704,
      "learning_rate": 9.99983777858264e-05,
      "loss": 2.3202,
      "step": 11
    },
    {
      "epoch": 0.0023907954375653735,
      "grad_norm": 1.9575777053833008,
      "learning_rate": 9.999351124856874e-05,
      "loss": 2.4932,
      "step": 12
    },
    {
      "epoch": 0.002590028390695821,
      "grad_norm": 1.9527984857559204,
      "learning_rate": 9.998540070400966e-05,
      "loss": 1.8685,
      "step": 13
    },
    {
      "epoch": 0.002789261343826269,
      "grad_norm": 1.5637708902359009,
      "learning_rate": 9.997404667843075e-05,
      "loss": 1.831,
      "step": 14
    },
    {
      "epoch": 0.0029884942969567166,
      "grad_norm": 1.2870111465454102,
      "learning_rate": 9.995944990857849e-05,
      "loss": 2.0248,
      "step": 15
    },
    {
      "epoch": 0.0031877272500871645,
      "grad_norm": 1.454819679260254,
      "learning_rate": 9.994161134161634e-05,
      "loss": 1.9433,
      "step": 16
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 1.470567226409912,
      "learning_rate": 9.992053213506334e-05,
      "loss": 1.8326,
      "step": 17
    },
    {
      "epoch": 0.00358619315634806,
      "grad_norm": 1.2251739501953125,
      "learning_rate": 9.989621365671902e-05,
      "loss": 1.9384,
      "step": 18
    },
    {
      "epoch": 0.0037854261094785076,
      "grad_norm": 1.148119568824768,
      "learning_rate": 9.986865748457457e-05,
      "loss": 1.9556,
      "step": 19
    },
    {
      "epoch": 0.003984659062608955,
      "grad_norm": 1.022918939590454,
      "learning_rate": 9.983786540671051e-05,
      "loss": 1.7457,
      "step": 20
    },
    {
      "epoch": 0.0041838920157394035,
      "grad_norm": 1.0495177507400513,
      "learning_rate": 9.980383942118066e-05,
      "loss": 1.7567,
      "step": 21
    },
    {
      "epoch": 0.004383124968869851,
      "grad_norm": 1.1652737855911255,
      "learning_rate": 9.976658173588244e-05,
      "loss": 1.7853,
      "step": 22
    },
    {
      "epoch": 0.004582357922000299,
      "grad_norm": 1.1292279958724976,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.6153,
      "step": 23
    },
    {
      "epoch": 0.004781590875130747,
      "grad_norm": 1.0591461658477783,
      "learning_rate": 9.968238114591566e-05,
      "loss": 2.0229,
      "step": 24
    },
    {
      "epoch": 0.0049808238282611945,
      "grad_norm": 1.0844651460647583,
      "learning_rate": 9.96354437049027e-05,
      "loss": 1.8225,
      "step": 25
    },
    {
      "epoch": 0.005180056781391642,
      "grad_norm": 1.2742100954055786,
      "learning_rate": 9.95852854910781e-05,
      "loss": 2.1446,
      "step": 26
    },
    {
      "epoch": 0.00537928973452209,
      "grad_norm": 1.0586717128753662,
      "learning_rate": 9.953190975913647e-05,
      "loss": 1.8019,
      "step": 27
    },
    {
      "epoch": 0.005578522687652538,
      "grad_norm": 0.8670190572738647,
      "learning_rate": 9.947531997255256e-05,
      "loss": 1.8777,
      "step": 28
    },
    {
      "epoch": 0.005777755640782986,
      "grad_norm": 1.0841562747955322,
      "learning_rate": 9.941551980335652e-05,
      "loss": 1.8035,
      "step": 29
    },
    {
      "epoch": 0.005976988593913433,
      "grad_norm": 1.0292096138000488,
      "learning_rate": 9.935251313189564e-05,
      "loss": 1.8991,
      "step": 30
    },
    {
      "epoch": 0.006176221547043881,
      "grad_norm": 0.9672908782958984,
      "learning_rate": 9.928630404658255e-05,
      "loss": 1.8272,
      "step": 31
    },
    {
      "epoch": 0.006375454500174329,
      "grad_norm": 0.9663026332855225,
      "learning_rate": 9.921689684362989e-05,
      "loss": 1.9222,
      "step": 32
    },
    {
      "epoch": 0.006574687453304777,
      "grad_norm": 0.8640333414077759,
      "learning_rate": 9.914429602677162e-05,
      "loss": 1.9071,
      "step": 33
    },
    {
      "epoch": 0.006773920406435224,
      "grad_norm": 0.9674398303031921,
      "learning_rate": 9.906850630697068e-05,
      "loss": 2.113,
      "step": 34
    },
    {
      "epoch": 0.0069731533595656725,
      "grad_norm": 0.9393993616104126,
      "learning_rate": 9.898953260211338e-05,
      "loss": 1.8711,
      "step": 35
    },
    {
      "epoch": 0.00717238631269612,
      "grad_norm": 0.9489927291870117,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0426,
      "step": 36
    },
    {
      "epoch": 0.007371619265826568,
      "grad_norm": 1.1132601499557495,
      "learning_rate": 9.882205394146361e-05,
      "loss": 2.3052,
      "step": 37
    },
    {
      "epoch": 0.007570852218957015,
      "grad_norm": 1.2090137004852295,
      "learning_rate": 9.87335598531214e-05,
      "loss": 2.0266,
      "step": 38
    },
    {
      "epoch": 0.0077700851720874636,
      "grad_norm": 1.0615320205688477,
      "learning_rate": 9.864190351391822e-05,
      "loss": 2.1822,
      "step": 39
    },
    {
      "epoch": 0.00796931812521791,
      "grad_norm": 0.9923949837684631,
      "learning_rate": 9.85470908713026e-05,
      "loss": 1.9442,
      "step": 40
    },
    {
      "epoch": 0.008168551078348359,
      "grad_norm": 1.0683104991912842,
      "learning_rate": 9.844912807753104e-05,
      "loss": 2.1782,
      "step": 41
    },
    {
      "epoch": 0.008367784031478807,
      "grad_norm": 1.1865333318710327,
      "learning_rate": 9.834802148926882e-05,
      "loss": 2.1076,
      "step": 42
    },
    {
      "epoch": 0.008567016984609254,
      "grad_norm": 0.9799418449401855,
      "learning_rate": 9.824377766717759e-05,
      "loss": 2.0544,
      "step": 43
    },
    {
      "epoch": 0.008766249937739702,
      "grad_norm": 1.0477815866470337,
      "learning_rate": 9.813640337548954e-05,
      "loss": 1.9788,
      "step": 44
    },
    {
      "epoch": 0.00896548289087015,
      "grad_norm": 0.9999564290046692,
      "learning_rate": 9.802590558156862e-05,
      "loss": 2.12,
      "step": 45
    },
    {
      "epoch": 0.009164715844000597,
      "grad_norm": 0.998177170753479,
      "learning_rate": 9.791229145545831e-05,
      "loss": 2.039,
      "step": 46
    },
    {
      "epoch": 0.009363948797131046,
      "grad_norm": 1.1539019346237183,
      "learning_rate": 9.779556836941645e-05,
      "loss": 2.3537,
      "step": 47
    },
    {
      "epoch": 0.009563181750261494,
      "grad_norm": 1.0150654315948486,
      "learning_rate": 9.767574389743682e-05,
      "loss": 2.0415,
      "step": 48
    },
    {
      "epoch": 0.00976241470339194,
      "grad_norm": 1.0183194875717163,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0481,
      "step": 49
    },
    {
      "epoch": 0.009961647656522389,
      "grad_norm": 0.9892953038215637,
      "learning_rate": 9.742682209735727e-05,
      "loss": 2.1764,
      "step": 50
    },
    {
      "epoch": 0.009961647656522389,
      "eval_loss": 1.82403564453125,
      "eval_runtime": 607.5197,
      "eval_samples_per_second": 13.916,
      "eval_steps_per_second": 3.48,
      "step": 50
    },
    {
      "epoch": 0.010160880609652836,
      "grad_norm": 0.8542794585227966,
      "learning_rate": 9.729774092143627e-05,
      "loss": 1.6775,
      "step": 51
    },
    {
      "epoch": 0.010360113562783284,
      "grad_norm": 0.8750085234642029,
      "learning_rate": 9.716559066288715e-05,
      "loss": 1.4926,
      "step": 52
    },
    {
      "epoch": 0.010559346515913733,
      "grad_norm": 0.875607430934906,
      "learning_rate": 9.703037989675087e-05,
      "loss": 1.8167,
      "step": 53
    },
    {
      "epoch": 0.01075857946904418,
      "grad_norm": 0.7322773933410645,
      "learning_rate": 9.689211739666023e-05,
      "loss": 1.4753,
      "step": 54
    },
    {
      "epoch": 0.010957812422174628,
      "grad_norm": 0.648223876953125,
      "learning_rate": 9.675081213427076e-05,
      "loss": 1.3975,
      "step": 55
    },
    {
      "epoch": 0.011157045375305076,
      "grad_norm": 0.6270776391029358,
      "learning_rate": 9.66064732786784e-05,
      "loss": 1.1602,
      "step": 56
    },
    {
      "epoch": 0.011356278328435523,
      "grad_norm": 0.6656715273857117,
      "learning_rate": 9.645911019582467e-05,
      "loss": 1.3633,
      "step": 57
    },
    {
      "epoch": 0.011555511281565971,
      "grad_norm": 0.7466765642166138,
      "learning_rate": 9.630873244788883e-05,
      "loss": 1.4871,
      "step": 58
    },
    {
      "epoch": 0.01175474423469642,
      "grad_norm": 0.8152953386306763,
      "learning_rate": 9.615534979266745e-05,
      "loss": 1.4701,
      "step": 59
    },
    {
      "epoch": 0.011953977187826866,
      "grad_norm": 0.8492268919944763,
      "learning_rate": 9.599897218294122e-05,
      "loss": 1.688,
      "step": 60
    },
    {
      "epoch": 0.012153210140957315,
      "grad_norm": 0.7441631555557251,
      "learning_rate": 9.583960976582913e-05,
      "loss": 1.5078,
      "step": 61
    },
    {
      "epoch": 0.012352443094087761,
      "grad_norm": 0.8003615736961365,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.86,
      "step": 62
    },
    {
      "epoch": 0.01255167604721821,
      "grad_norm": 0.7498038411140442,
      "learning_rate": 9.551197206565173e-05,
      "loss": 1.4841,
      "step": 63
    },
    {
      "epoch": 0.012750909000348658,
      "grad_norm": 0.7930290699005127,
      "learning_rate": 9.534371804252728e-05,
      "loss": 1.6008,
      "step": 64
    },
    {
      "epoch": 0.012950141953479105,
      "grad_norm": 0.7177601456642151,
      "learning_rate": 9.517252173051911e-05,
      "loss": 1.4822,
      "step": 65
    },
    {
      "epoch": 0.013149374906609553,
      "grad_norm": 0.7637808918952942,
      "learning_rate": 9.49983942383106e-05,
      "loss": 1.6999,
      "step": 66
    },
    {
      "epoch": 0.013348607859740002,
      "grad_norm": 0.6996709108352661,
      "learning_rate": 9.482134686478519e-05,
      "loss": 1.5346,
      "step": 67
    },
    {
      "epoch": 0.013547840812870448,
      "grad_norm": 0.8542125821113586,
      "learning_rate": 9.464139109829321e-05,
      "loss": 1.8176,
      "step": 68
    },
    {
      "epoch": 0.013747073766000897,
      "grad_norm": 0.8093202710151672,
      "learning_rate": 9.445853861590647e-05,
      "loss": 1.5795,
      "step": 69
    },
    {
      "epoch": 0.013946306719131345,
      "grad_norm": 0.8053815960884094,
      "learning_rate": 9.42728012826605e-05,
      "loss": 1.7278,
      "step": 70
    },
    {
      "epoch": 0.014145539672261792,
      "grad_norm": 0.823073148727417,
      "learning_rate": 9.408419115078471e-05,
      "loss": 1.6882,
      "step": 71
    },
    {
      "epoch": 0.01434477262539224,
      "grad_norm": 0.9014071822166443,
      "learning_rate": 9.389272045892024e-05,
      "loss": 1.7093,
      "step": 72
    },
    {
      "epoch": 0.014544005578522687,
      "grad_norm": 0.9905192852020264,
      "learning_rate": 9.36984016313259e-05,
      "loss": 1.8529,
      "step": 73
    },
    {
      "epoch": 0.014743238531653135,
      "grad_norm": 0.8374629020690918,
      "learning_rate": 9.350124727707197e-05,
      "loss": 1.7811,
      "step": 74
    },
    {
      "epoch": 0.014942471484783584,
      "grad_norm": 1.0269732475280762,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8239,
      "step": 75
    },
    {
      "epoch": 0.01514170443791403,
      "grad_norm": 0.7490584254264832,
      "learning_rate": 9.309848334400246e-05,
      "loss": 1.5871,
      "step": 76
    },
    {
      "epoch": 0.015340937391044479,
      "grad_norm": 0.8312053680419922,
      "learning_rate": 9.289289989996133e-05,
      "loss": 1.6725,
      "step": 77
    },
    {
      "epoch": 0.015540170344174927,
      "grad_norm": 0.7715761661529541,
      "learning_rate": 9.268453319711363e-05,
      "loss": 1.6291,
      "step": 78
    },
    {
      "epoch": 0.015739403297305374,
      "grad_norm": 0.8476051688194275,
      "learning_rate": 9.247339675607605e-05,
      "loss": 1.8967,
      "step": 79
    },
    {
      "epoch": 0.01593863625043582,
      "grad_norm": 0.7571315765380859,
      "learning_rate": 9.225950427718975e-05,
      "loss": 1.6547,
      "step": 80
    },
    {
      "epoch": 0.01613786920356627,
      "grad_norm": 0.831329882144928,
      "learning_rate": 9.204286963963111e-05,
      "loss": 1.9368,
      "step": 81
    },
    {
      "epoch": 0.016337102156696717,
      "grad_norm": 0.7381522059440613,
      "learning_rate": 9.182350690051133e-05,
      "loss": 1.8917,
      "step": 82
    },
    {
      "epoch": 0.016536335109827164,
      "grad_norm": 0.9195905923843384,
      "learning_rate": 9.160143029396422e-05,
      "loss": 1.907,
      "step": 83
    },
    {
      "epoch": 0.016735568062957614,
      "grad_norm": 0.7933158874511719,
      "learning_rate": 9.13766542302225e-05,
      "loss": 1.7316,
      "step": 84
    },
    {
      "epoch": 0.01693480101608806,
      "grad_norm": 0.8460677266120911,
      "learning_rate": 9.114919329468282e-05,
      "loss": 2.0394,
      "step": 85
    },
    {
      "epoch": 0.017134033969218507,
      "grad_norm": 0.8626026511192322,
      "learning_rate": 9.091906224695935e-05,
      "loss": 1.7807,
      "step": 86
    },
    {
      "epoch": 0.017333266922348958,
      "grad_norm": 1.0532417297363281,
      "learning_rate": 9.068627601992598e-05,
      "loss": 1.9692,
      "step": 87
    },
    {
      "epoch": 0.017532499875479404,
      "grad_norm": 0.9541111588478088,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.1123,
      "step": 88
    },
    {
      "epoch": 0.01773173282860985,
      "grad_norm": 0.8808003067970276,
      "learning_rate": 9.021279861989885e-05,
      "loss": 2.1134,
      "step": 89
    },
    {
      "epoch": 0.0179309657817403,
      "grad_norm": 0.9053674936294556,
      "learning_rate": 8.997213817017507e-05,
      "loss": 1.8627,
      "step": 90
    },
    {
      "epoch": 0.018130198734870748,
      "grad_norm": 0.9115805625915527,
      "learning_rate": 8.972888398568772e-05,
      "loss": 1.8644,
      "step": 91
    },
    {
      "epoch": 0.018329431688001194,
      "grad_norm": 1.0219849348068237,
      "learning_rate": 8.948305185085225e-05,
      "loss": 2.2721,
      "step": 92
    },
    {
      "epoch": 0.018528664641131645,
      "grad_norm": 0.9994537234306335,
      "learning_rate": 8.92346577173636e-05,
      "loss": 2.1956,
      "step": 93
    },
    {
      "epoch": 0.01872789759426209,
      "grad_norm": 0.881737470626831,
      "learning_rate": 8.898371770316111e-05,
      "loss": 1.9247,
      "step": 94
    },
    {
      "epoch": 0.018927130547392538,
      "grad_norm": 1.0032176971435547,
      "learning_rate": 8.873024809138272e-05,
      "loss": 2.1392,
      "step": 95
    },
    {
      "epoch": 0.019126363500522988,
      "grad_norm": 1.0586591958999634,
      "learning_rate": 8.847426532930831e-05,
      "loss": 2.0194,
      "step": 96
    },
    {
      "epoch": 0.019325596453653435,
      "grad_norm": 1.0651748180389404,
      "learning_rate": 8.821578602729242e-05,
      "loss": 2.0458,
      "step": 97
    },
    {
      "epoch": 0.01952482940678388,
      "grad_norm": 1.0627988576889038,
      "learning_rate": 8.795482695768658e-05,
      "loss": 1.9618,
      "step": 98
    },
    {
      "epoch": 0.01972406235991433,
      "grad_norm": 0.9913427233695984,
      "learning_rate": 8.769140505375085e-05,
      "loss": 1.8278,
      "step": 99
    },
    {
      "epoch": 0.019923295313044778,
      "grad_norm": 1.2119276523590088,
      "learning_rate": 8.742553740855506e-05,
      "loss": 2.1889,
      "step": 100
    },
    {
      "epoch": 0.019923295313044778,
      "eval_loss": 1.8152918815612793,
      "eval_runtime": 607.3335,
      "eval_samples_per_second": 13.92,
      "eval_steps_per_second": 3.481,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "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": 1.42188868534272e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}