{
  "best_metric": 0.12837110459804535,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1182033096926714,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001182033096926714,
      "grad_norm": 0.45257845520973206,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.7527,
      "step": 1
    },
    {
      "epoch": 0.001182033096926714,
      "eval_loss": 0.21998687088489532,
      "eval_runtime": 6.5713,
      "eval_samples_per_second": 7.609,
      "eval_steps_per_second": 1.065,
      "step": 1
    },
    {
      "epoch": 0.002364066193853428,
      "grad_norm": 0.4749073386192322,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.6891,
      "step": 2
    },
    {
      "epoch": 0.0035460992907801418,
      "grad_norm": 0.4979456961154938,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.8038,
      "step": 3
    },
    {
      "epoch": 0.004728132387706856,
      "grad_norm": 0.4834277331829071,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.69,
      "step": 4
    },
    {
      "epoch": 0.00591016548463357,
      "grad_norm": 0.4842442274093628,
      "learning_rate": 0.00015,
      "loss": 0.8362,
      "step": 5
    },
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 0.37017032504081726,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.7844,
      "step": 6
    },
    {
      "epoch": 0.008274231678486997,
      "grad_norm": 0.20203356444835663,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.5235,
      "step": 7
    },
    {
      "epoch": 0.009456264775413711,
      "grad_norm": 0.35705870389938354,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.5528,
      "step": 8
    },
    {
      "epoch": 0.010638297872340425,
      "grad_norm": 0.3792789876461029,
      "learning_rate": 0.00027,
      "loss": 0.5373,
      "step": 9
    },
    {
      "epoch": 0.01182033096926714,
      "grad_norm": 0.3239419460296631,
      "learning_rate": 0.0003,
      "loss": 0.4818,
      "step": 10
    },
    {
      "epoch": 0.013002364066193853,
      "grad_norm": 0.29636237025260925,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.5745,
      "step": 11
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 0.3467446565628052,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.6402,
      "step": 12
    },
    {
      "epoch": 0.015366430260047281,
      "grad_norm": 0.23589834570884705,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.6432,
      "step": 13
    },
    {
      "epoch": 0.016548463356973995,
      "grad_norm": 0.195448100566864,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.5233,
      "step": 14
    },
    {
      "epoch": 0.01773049645390071,
      "grad_norm": 0.2630046010017395,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.5089,
      "step": 15
    },
    {
      "epoch": 0.018912529550827423,
      "grad_norm": 0.18320521712303162,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.3504,
      "step": 16
    },
    {
      "epoch": 0.02009456264775414,
      "grad_norm": 0.16204728186130524,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.3852,
      "step": 17
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.24153684079647064,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.8729,
      "step": 18
    },
    {
      "epoch": 0.022458628841607566,
      "grad_norm": 0.16790688037872314,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.3754,
      "step": 19
    },
    {
      "epoch": 0.02364066193853428,
      "grad_norm": 0.24352045357227325,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.3613,
      "step": 20
    },
    {
      "epoch": 0.024822695035460994,
      "grad_norm": 0.17234143614768982,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.4107,
      "step": 21
    },
    {
      "epoch": 0.026004728132387706,
      "grad_norm": 0.16111795604228973,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.2606,
      "step": 22
    },
    {
      "epoch": 0.027186761229314422,
      "grad_norm": 0.12541893124580383,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.2757,
      "step": 23
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.14481070637702942,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.2086,
      "step": 24
    },
    {
      "epoch": 0.02955082742316785,
      "grad_norm": 0.2305174022912979,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.4623,
      "step": 25
    },
    {
      "epoch": 0.02955082742316785,
      "eval_loss": 0.13037407398223877,
      "eval_runtime": 6.8052,
      "eval_samples_per_second": 7.347,
      "eval_steps_per_second": 1.029,
      "step": 25
    },
    {
      "epoch": 0.030732860520094562,
      "grad_norm": 0.19182905554771423,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.4473,
      "step": 26
    },
    {
      "epoch": 0.031914893617021274,
      "grad_norm": 0.24724812805652618,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.4684,
      "step": 27
    },
    {
      "epoch": 0.03309692671394799,
      "grad_norm": 0.15102490782737732,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.2546,
      "step": 28
    },
    {
      "epoch": 0.034278959810874705,
      "grad_norm": 0.35056641697883606,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.3202,
      "step": 29
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 0.2419431358575821,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.3701,
      "step": 30
    },
    {
      "epoch": 0.03664302600472813,
      "grad_norm": 0.15826299786567688,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.2572,
      "step": 31
    },
    {
      "epoch": 0.037825059101654845,
      "grad_norm": 0.2803819179534912,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.4723,
      "step": 32
    },
    {
      "epoch": 0.03900709219858156,
      "grad_norm": 0.22237618267536163,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.3599,
      "step": 33
    },
    {
      "epoch": 0.04018912529550828,
      "grad_norm": 0.2598985731601715,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.501,
      "step": 34
    },
    {
      "epoch": 0.041371158392434985,
      "grad_norm": 0.4324254095554352,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.4615,
      "step": 35
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.16531601548194885,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.1464,
      "step": 36
    },
    {
      "epoch": 0.04373522458628842,
      "grad_norm": 0.16330963373184204,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.2302,
      "step": 37
    },
    {
      "epoch": 0.04491725768321513,
      "grad_norm": 0.16654549539089203,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.2296,
      "step": 38
    },
    {
      "epoch": 0.04609929078014184,
      "grad_norm": 0.5145742893218994,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.2124,
      "step": 39
    },
    {
      "epoch": 0.04728132387706856,
      "grad_norm": 0.19344383478164673,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.2257,
      "step": 40
    },
    {
      "epoch": 0.04846335697399527,
      "grad_norm": 0.20284941792488098,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.3324,
      "step": 41
    },
    {
      "epoch": 0.04964539007092199,
      "grad_norm": 0.09100235253572464,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0292,
      "step": 42
    },
    {
      "epoch": 0.0508274231678487,
      "grad_norm": 0.3754136562347412,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.2822,
      "step": 43
    },
    {
      "epoch": 0.05200945626477541,
      "grad_norm": 0.03608919680118561,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0019,
      "step": 44
    },
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 0.2937483787536621,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.2582,
      "step": 45
    },
    {
      "epoch": 0.054373522458628844,
      "grad_norm": 0.1442236453294754,
      "learning_rate": 0.000274201324672203,
      "loss": 0.0591,
      "step": 46
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.19208501279354095,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.0851,
      "step": 47
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.02040451020002365,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.0009,
      "step": 48
    },
    {
      "epoch": 0.057919621749408984,
      "grad_norm": 0.36763325333595276,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.1239,
      "step": 49
    },
    {
      "epoch": 0.0591016548463357,
      "grad_norm": 0.5783975124359131,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.0694,
      "step": 50
    },
    {
      "epoch": 0.0591016548463357,
      "eval_loss": 0.12837110459804535,
      "eval_runtime": 6.8069,
      "eval_samples_per_second": 7.346,
      "eval_steps_per_second": 1.028,
      "step": 50
    },
    {
      "epoch": 0.06028368794326241,
      "grad_norm": 0.23129263520240784,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.4675,
      "step": 51
    },
    {
      "epoch": 0.061465721040189124,
      "grad_norm": 0.3005974590778351,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.5101,
      "step": 52
    },
    {
      "epoch": 0.06264775413711583,
      "grad_norm": 0.15042176842689514,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.3429,
      "step": 53
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 0.1577768176794052,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.5794,
      "step": 54
    },
    {
      "epoch": 0.06501182033096926,
      "grad_norm": 0.19460776448249817,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.6019,
      "step": 55
    },
    {
      "epoch": 0.06619385342789598,
      "grad_norm": 0.18861106038093567,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.7549,
      "step": 56
    },
    {
      "epoch": 0.0673758865248227,
      "grad_norm": 0.14117053151130676,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.459,
      "step": 57
    },
    {
      "epoch": 0.06855791962174941,
      "grad_norm": 0.22173011302947998,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.5504,
      "step": 58
    },
    {
      "epoch": 0.06973995271867613,
      "grad_norm": 0.25081151723861694,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.524,
      "step": 59
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 0.13126404583454132,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.3677,
      "step": 60
    },
    {
      "epoch": 0.07210401891252956,
      "grad_norm": 0.13712657988071442,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.4722,
      "step": 61
    },
    {
      "epoch": 0.07328605200945626,
      "grad_norm": 0.2549358904361725,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.8239,
      "step": 62
    },
    {
      "epoch": 0.07446808510638298,
      "grad_norm": 0.14273299276828766,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.3742,
      "step": 63
    },
    {
      "epoch": 0.07565011820330969,
      "grad_norm": 0.19160489737987518,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.6387,
      "step": 64
    },
    {
      "epoch": 0.0768321513002364,
      "grad_norm": 0.15993249416351318,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.5228,
      "step": 65
    },
    {
      "epoch": 0.07801418439716312,
      "grad_norm": 0.15967561304569244,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.4422,
      "step": 66
    },
    {
      "epoch": 0.07919621749408984,
      "grad_norm": 0.1872466653585434,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.4686,
      "step": 67
    },
    {
      "epoch": 0.08037825059101655,
      "grad_norm": 0.1232978031039238,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.3756,
      "step": 68
    },
    {
      "epoch": 0.08156028368794327,
      "grad_norm": 0.15848113596439362,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.4773,
      "step": 69
    },
    {
      "epoch": 0.08274231678486997,
      "grad_norm": 0.1522669494152069,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.433,
      "step": 70
    },
    {
      "epoch": 0.08392434988179669,
      "grad_norm": 0.37246736884117126,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.3253,
      "step": 71
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.18676169216632843,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.3645,
      "step": 72
    },
    {
      "epoch": 0.08628841607565012,
      "grad_norm": 0.1256495714187622,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.25,
      "step": 73
    },
    {
      "epoch": 0.08747044917257683,
      "grad_norm": 0.128931924700737,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.2731,
      "step": 74
    },
    {
      "epoch": 0.08865248226950355,
      "grad_norm": 0.13608215749263763,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.3361,
      "step": 75
    },
    {
      "epoch": 0.08865248226950355,
      "eval_loss": 0.11915016919374466,
      "eval_runtime": 6.6761,
      "eval_samples_per_second": 7.489,
      "eval_steps_per_second": 1.049,
      "step": 75
    },
    {
      "epoch": 0.08983451536643026,
      "grad_norm": 0.1711040437221527,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.4544,
      "step": 76
    },
    {
      "epoch": 0.09101654846335698,
      "grad_norm": 0.24072404205799103,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.2764,
      "step": 77
    },
    {
      "epoch": 0.09219858156028368,
      "grad_norm": 0.15333881974220276,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.3369,
      "step": 78
    },
    {
      "epoch": 0.0933806146572104,
      "grad_norm": 0.14597493410110474,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.2058,
      "step": 79
    },
    {
      "epoch": 0.09456264775413711,
      "grad_norm": 0.15312355756759644,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.278,
      "step": 80
    },
    {
      "epoch": 0.09574468085106383,
      "grad_norm": 0.1510908156633377,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.2616,
      "step": 81
    },
    {
      "epoch": 0.09692671394799054,
      "grad_norm": 0.1632828563451767,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.2734,
      "step": 82
    },
    {
      "epoch": 0.09810874704491726,
      "grad_norm": 0.21976338326931,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.3517,
      "step": 83
    },
    {
      "epoch": 0.09929078014184398,
      "grad_norm": 0.18902301788330078,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.3057,
      "step": 84
    },
    {
      "epoch": 0.10047281323877069,
      "grad_norm": 0.17857129871845245,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.2618,
      "step": 85
    },
    {
      "epoch": 0.1016548463356974,
      "grad_norm": 0.14383412897586823,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.1557,
      "step": 86
    },
    {
      "epoch": 0.10283687943262411,
      "grad_norm": 0.18979600071907043,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.2969,
      "step": 87
    },
    {
      "epoch": 0.10401891252955082,
      "grad_norm": 0.23204195499420166,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.3901,
      "step": 88
    },
    {
      "epoch": 0.10520094562647754,
      "grad_norm": 0.23629039525985718,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.3413,
      "step": 89
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 0.12269175052642822,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.0636,
      "step": 90
    },
    {
      "epoch": 0.10756501182033097,
      "grad_norm": 1.75273597240448,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.2072,
      "step": 91
    },
    {
      "epoch": 0.10874704491725769,
      "grad_norm": 0.07240819931030273,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.0383,
      "step": 92
    },
    {
      "epoch": 0.1099290780141844,
      "grad_norm": 0.1977987140417099,
      "learning_rate": 0.000179567554117722,
      "loss": 0.1972,
      "step": 93
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.15330693125724792,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.1202,
      "step": 94
    },
    {
      "epoch": 0.11229314420803782,
      "grad_norm": 0.2938881516456604,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.2919,
      "step": 95
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 0.19431200623512268,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.1018,
      "step": 96
    },
    {
      "epoch": 0.11465721040189125,
      "grad_norm": 0.27025851607322693,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.243,
      "step": 97
    },
    {
      "epoch": 0.11583924349881797,
      "grad_norm": 0.12175106257200241,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.08,
      "step": 98
    },
    {
      "epoch": 0.11702127659574468,
      "grad_norm": 0.18022122979164124,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.0626,
      "step": 99
    },
    {
      "epoch": 0.1182033096926714,
      "grad_norm": 0.3214963674545288,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.1805,
      "step": 100
    },
    {
      "epoch": 0.1182033096926714,
      "eval_loss": 0.1298762410879135,
      "eval_runtime": 6.7923,
      "eval_samples_per_second": 7.361,
      "eval_steps_per_second": 1.031,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.923209170476073e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}