{
  "best_metric": 0.011105372570455074,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.4069175991861648,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004069175991861648,
      "grad_norm": 0.18430504202842712,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.4546,
      "step": 1
    },
    {
      "epoch": 0.004069175991861648,
      "eval_loss": 0.2489006370306015,
      "eval_runtime": 12.8231,
      "eval_samples_per_second": 3.899,
      "eval_steps_per_second": 0.546,
      "step": 1
    },
    {
      "epoch": 0.008138351983723296,
      "grad_norm": 0.20032061636447906,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.4626,
      "step": 2
    },
    {
      "epoch": 0.012207527975584944,
      "grad_norm": 0.1911066621541977,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.4799,
      "step": 3
    },
    {
      "epoch": 0.01627670396744659,
      "grad_norm": 0.20888791978359222,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.4716,
      "step": 4
    },
    {
      "epoch": 0.02034587995930824,
      "grad_norm": 0.24220263957977295,
      "learning_rate": 0.00015,
      "loss": 0.4777,
      "step": 5
    },
    {
      "epoch": 0.024415055951169887,
      "grad_norm": 0.25128036737442017,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.3979,
      "step": 6
    },
    {
      "epoch": 0.028484231943031537,
      "grad_norm": 0.1742318868637085,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.3759,
      "step": 7
    },
    {
      "epoch": 0.03255340793489318,
      "grad_norm": 0.17110617458820343,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.3271,
      "step": 8
    },
    {
      "epoch": 0.03662258392675483,
      "grad_norm": 0.19768884778022766,
      "learning_rate": 0.00027,
      "loss": 0.2259,
      "step": 9
    },
    {
      "epoch": 0.04069175991861648,
      "grad_norm": 0.2143348902463913,
      "learning_rate": 0.0003,
      "loss": 0.1569,
      "step": 10
    },
    {
      "epoch": 0.044760935910478125,
      "grad_norm": 0.2793988287448883,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.1393,
      "step": 11
    },
    {
      "epoch": 0.048830111902339775,
      "grad_norm": 0.2352091372013092,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.0939,
      "step": 12
    },
    {
      "epoch": 0.052899287894201424,
      "grad_norm": 0.17386719584465027,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.0802,
      "step": 13
    },
    {
      "epoch": 0.056968463886063074,
      "grad_norm": 0.5942983627319336,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.0948,
      "step": 14
    },
    {
      "epoch": 0.061037639877924724,
      "grad_norm": 0.21323800086975098,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.0423,
      "step": 15
    },
    {
      "epoch": 0.06510681586978637,
      "grad_norm": 0.11683189123868942,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.0327,
      "step": 16
    },
    {
      "epoch": 0.06917599186164802,
      "grad_norm": 0.09624740481376648,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.0322,
      "step": 17
    },
    {
      "epoch": 0.07324516785350967,
      "grad_norm": 0.12023144215345383,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.0437,
      "step": 18
    },
    {
      "epoch": 0.07731434384537131,
      "grad_norm": 0.4698963761329651,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.1443,
      "step": 19
    },
    {
      "epoch": 0.08138351983723296,
      "grad_norm": 1.0405900478363037,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.4887,
      "step": 20
    },
    {
      "epoch": 0.08545269582909461,
      "grad_norm": 0.5793169736862183,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.4255,
      "step": 21
    },
    {
      "epoch": 0.08952187182095625,
      "grad_norm": 0.5396560430526733,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.4089,
      "step": 22
    },
    {
      "epoch": 0.0935910478128179,
      "grad_norm": 0.43461382389068604,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.5076,
      "step": 23
    },
    {
      "epoch": 0.09766022380467955,
      "grad_norm": 0.4178922474384308,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.5139,
      "step": 24
    },
    {
      "epoch": 0.1017293997965412,
      "grad_norm": 0.47736668586730957,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.6272,
      "step": 25
    },
    {
      "epoch": 0.1017293997965412,
      "eval_loss": 0.14711476862430573,
      "eval_runtime": 13.014,
      "eval_samples_per_second": 3.842,
      "eval_steps_per_second": 0.538,
      "step": 25
    },
    {
      "epoch": 0.10579857578840285,
      "grad_norm": 0.5472037196159363,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.6612,
      "step": 26
    },
    {
      "epoch": 0.10986775178026449,
      "grad_norm": 0.4757766127586365,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.5034,
      "step": 27
    },
    {
      "epoch": 0.11393692777212615,
      "grad_norm": 0.43715453147888184,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.4988,
      "step": 28
    },
    {
      "epoch": 0.11800610376398779,
      "grad_norm": 0.4352036416530609,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.54,
      "step": 29
    },
    {
      "epoch": 0.12207527975584945,
      "grad_norm": 0.5779057741165161,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.4994,
      "step": 30
    },
    {
      "epoch": 0.12614445574771108,
      "grad_norm": 0.5189437866210938,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.5054,
      "step": 31
    },
    {
      "epoch": 0.13021363173957273,
      "grad_norm": 0.5969810485839844,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.6,
      "step": 32
    },
    {
      "epoch": 0.1342828077314344,
      "grad_norm": 0.6625540256500244,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.4243,
      "step": 33
    },
    {
      "epoch": 0.13835198372329605,
      "grad_norm": 0.6620368361473083,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.6029,
      "step": 34
    },
    {
      "epoch": 0.14242115971515767,
      "grad_norm": 0.6099522709846497,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.4348,
      "step": 35
    },
    {
      "epoch": 0.14649033570701933,
      "grad_norm": 0.696644127368927,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.5671,
      "step": 36
    },
    {
      "epoch": 0.150559511698881,
      "grad_norm": 0.6944995522499084,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.5403,
      "step": 37
    },
    {
      "epoch": 0.15462868769074262,
      "grad_norm": 0.8135762810707092,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.4017,
      "step": 38
    },
    {
      "epoch": 0.15869786368260427,
      "grad_norm": 0.6780802011489868,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.4815,
      "step": 39
    },
    {
      "epoch": 0.16276703967446593,
      "grad_norm": 0.6904082298278809,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.5513,
      "step": 40
    },
    {
      "epoch": 0.16683621566632756,
      "grad_norm": 0.7780231237411499,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.4496,
      "step": 41
    },
    {
      "epoch": 0.17090539165818922,
      "grad_norm": 0.690417468547821,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.2988,
      "step": 42
    },
    {
      "epoch": 0.17497456765005087,
      "grad_norm": 0.7350278496742249,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.2754,
      "step": 43
    },
    {
      "epoch": 0.1790437436419125,
      "grad_norm": 0.8998621106147766,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.535,
      "step": 44
    },
    {
      "epoch": 0.18311291963377416,
      "grad_norm": 0.5199292898178101,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.2193,
      "step": 45
    },
    {
      "epoch": 0.1871820956256358,
      "grad_norm": 0.7286368012428284,
      "learning_rate": 0.000274201324672203,
      "loss": 0.3971,
      "step": 46
    },
    {
      "epoch": 0.19125127161749747,
      "grad_norm": 0.8066439628601074,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.5201,
      "step": 47
    },
    {
      "epoch": 0.1953204476093591,
      "grad_norm": 0.8500910401344299,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.4594,
      "step": 48
    },
    {
      "epoch": 0.19938962360122076,
      "grad_norm": 0.9414553642272949,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.7813,
      "step": 49
    },
    {
      "epoch": 0.2034587995930824,
      "grad_norm": 2.258089065551758,
      "learning_rate": 0.00026837107640945905,
      "loss": 1.5064,
      "step": 50
    },
    {
      "epoch": 0.2034587995930824,
      "eval_loss": 0.03713131323456764,
      "eval_runtime": 13.0009,
      "eval_samples_per_second": 3.846,
      "eval_steps_per_second": 0.538,
      "step": 50
    },
    {
      "epoch": 0.20752797558494404,
      "grad_norm": 0.7120374441146851,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.096,
      "step": 51
    },
    {
      "epoch": 0.2115971515768057,
      "grad_norm": 0.3248690366744995,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.0389,
      "step": 52
    },
    {
      "epoch": 0.21566632756866735,
      "grad_norm": 0.3197277784347534,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.0302,
      "step": 53
    },
    {
      "epoch": 0.21973550356052898,
      "grad_norm": 0.14361833035945892,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.0137,
      "step": 54
    },
    {
      "epoch": 0.22380467955239064,
      "grad_norm": 0.17876560986042023,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.036,
      "step": 55
    },
    {
      "epoch": 0.2278738555442523,
      "grad_norm": 0.07787288725376129,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.0154,
      "step": 56
    },
    {
      "epoch": 0.23194303153611392,
      "grad_norm": 0.11396508663892746,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.0188,
      "step": 57
    },
    {
      "epoch": 0.23601220752797558,
      "grad_norm": 0.10331092029809952,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.0184,
      "step": 58
    },
    {
      "epoch": 0.24008138351983724,
      "grad_norm": 0.07832586020231247,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.0126,
      "step": 59
    },
    {
      "epoch": 0.2441505595116989,
      "grad_norm": 0.038063760846853256,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.0064,
      "step": 60
    },
    {
      "epoch": 0.24821973550356052,
      "grad_norm": 0.04389215260744095,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.0035,
      "step": 61
    },
    {
      "epoch": 0.25228891149542215,
      "grad_norm": 0.033812519162893295,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.0029,
      "step": 62
    },
    {
      "epoch": 0.25635808748728384,
      "grad_norm": 0.05039115995168686,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.0049,
      "step": 63
    },
    {
      "epoch": 0.26042726347914547,
      "grad_norm": 0.04454028606414795,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.003,
      "step": 64
    },
    {
      "epoch": 0.2644964394710071,
      "grad_norm": 0.03696225956082344,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.0022,
      "step": 65
    },
    {
      "epoch": 0.2685656154628688,
      "grad_norm": 0.05542654171586037,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.0021,
      "step": 66
    },
    {
      "epoch": 0.2726347914547304,
      "grad_norm": 0.013826167210936546,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.0008,
      "step": 67
    },
    {
      "epoch": 0.2767039674465921,
      "grad_norm": 0.023703791201114655,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.0022,
      "step": 68
    },
    {
      "epoch": 0.2807731434384537,
      "grad_norm": 0.08458836376667023,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.0164,
      "step": 69
    },
    {
      "epoch": 0.28484231943031535,
      "grad_norm": 0.7300925850868225,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.0927,
      "step": 70
    },
    {
      "epoch": 0.28891149542217703,
      "grad_norm": 0.5981572270393372,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.1194,
      "step": 71
    },
    {
      "epoch": 0.29298067141403866,
      "grad_norm": 0.5619075298309326,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.0957,
      "step": 72
    },
    {
      "epoch": 0.2970498474059003,
      "grad_norm": 0.33565792441368103,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.0656,
      "step": 73
    },
    {
      "epoch": 0.301119023397762,
      "grad_norm": 0.46171268820762634,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.0598,
      "step": 74
    },
    {
      "epoch": 0.3051881993896236,
      "grad_norm": 0.45766952633857727,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.0685,
      "step": 75
    },
    {
      "epoch": 0.3051881993896236,
      "eval_loss": 0.025676894932985306,
      "eval_runtime": 13.0016,
      "eval_samples_per_second": 3.846,
      "eval_steps_per_second": 0.538,
      "step": 75
    },
    {
      "epoch": 0.30925737538148523,
      "grad_norm": 0.5149214863777161,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.0755,
      "step": 76
    },
    {
      "epoch": 0.3133265513733469,
      "grad_norm": 0.3870311975479126,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.0534,
      "step": 77
    },
    {
      "epoch": 0.31739572736520855,
      "grad_norm": 0.33499646186828613,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.0599,
      "step": 78
    },
    {
      "epoch": 0.3214649033570702,
      "grad_norm": 0.29793283343315125,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.0375,
      "step": 79
    },
    {
      "epoch": 0.32553407934893186,
      "grad_norm": 0.2961036264896393,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.0398,
      "step": 80
    },
    {
      "epoch": 0.3296032553407935,
      "grad_norm": 0.3199717104434967,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.0375,
      "step": 81
    },
    {
      "epoch": 0.3336724313326551,
      "grad_norm": 0.30673283338546753,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.0474,
      "step": 82
    },
    {
      "epoch": 0.3377416073245168,
      "grad_norm": 0.35638052225112915,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.0364,
      "step": 83
    },
    {
      "epoch": 0.34181078331637843,
      "grad_norm": 0.541354775428772,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.0596,
      "step": 84
    },
    {
      "epoch": 0.34587995930824006,
      "grad_norm": 0.23636458814144135,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.0285,
      "step": 85
    },
    {
      "epoch": 0.34994913530010174,
      "grad_norm": 0.25946715474128723,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.0334,
      "step": 86
    },
    {
      "epoch": 0.3540183112919634,
      "grad_norm": 0.3717379868030548,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.0823,
      "step": 87
    },
    {
      "epoch": 0.358087487283825,
      "grad_norm": 0.6748691201210022,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.072,
      "step": 88
    },
    {
      "epoch": 0.3621566632756867,
      "grad_norm": 0.42658162117004395,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.0462,
      "step": 89
    },
    {
      "epoch": 0.3662258392675483,
      "grad_norm": 0.42387211322784424,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.1011,
      "step": 90
    },
    {
      "epoch": 0.37029501525940994,
      "grad_norm": 0.29736894369125366,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.0411,
      "step": 91
    },
    {
      "epoch": 0.3743641912512716,
      "grad_norm": 0.2868631184101105,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.0671,
      "step": 92
    },
    {
      "epoch": 0.37843336724313326,
      "grad_norm": 0.4251483082771301,
      "learning_rate": 0.000179567554117722,
      "loss": 0.1333,
      "step": 93
    },
    {
      "epoch": 0.38250254323499494,
      "grad_norm": 0.3550730049610138,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.0863,
      "step": 94
    },
    {
      "epoch": 0.38657171922685657,
      "grad_norm": 0.28326889872550964,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.0795,
      "step": 95
    },
    {
      "epoch": 0.3906408952187182,
      "grad_norm": 0.3059619963169098,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.1373,
      "step": 96
    },
    {
      "epoch": 0.3947100712105799,
      "grad_norm": 0.3868827819824219,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.1411,
      "step": 97
    },
    {
      "epoch": 0.3987792472024415,
      "grad_norm": 0.35499969124794006,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.1811,
      "step": 98
    },
    {
      "epoch": 0.40284842319430314,
      "grad_norm": 0.793555736541748,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.4984,
      "step": 99
    },
    {
      "epoch": 0.4069175991861648,
      "grad_norm": 1.1363798379898071,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.742,
      "step": 100
    },
    {
      "epoch": 0.4069175991861648,
      "eval_loss": 0.011105372570455074,
      "eval_runtime": 12.9997,
      "eval_samples_per_second": 3.846,
      "eval_steps_per_second": 0.538,
      "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": 1,
        "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": 2.7563955529659187e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}