{
  "best_metric": 0.6152855753898621,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.7682587819054839,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008086934546373515,
      "grad_norm": 1.5315700769424438,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7462,
      "step": 1
    },
    {
      "epoch": 0.008086934546373515,
      "eval_loss": 2.1085262298583984,
      "eval_runtime": 3.426,
      "eval_samples_per_second": 14.594,
      "eval_steps_per_second": 3.795,
      "step": 1
    },
    {
      "epoch": 0.01617386909274703,
      "grad_norm": 1.7186044454574585,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.9119,
      "step": 2
    },
    {
      "epoch": 0.024260803639120546,
      "grad_norm": 1.9918476343154907,
      "learning_rate": 0.0001,
      "loss": 1.9158,
      "step": 3
    },
    {
      "epoch": 0.03234773818549406,
      "grad_norm": 2.2980024814605713,
      "learning_rate": 9.997376600647783e-05,
      "loss": 1.8927,
      "step": 4
    },
    {
      "epoch": 0.04043467273186758,
      "grad_norm": 3.0650627613067627,
      "learning_rate": 9.989509461357426e-05,
      "loss": 1.3474,
      "step": 5
    },
    {
      "epoch": 0.04852160727824109,
      "grad_norm": 1.560479998588562,
      "learning_rate": 9.976407754861426e-05,
      "loss": 1.1936,
      "step": 6
    },
    {
      "epoch": 0.056608541824614604,
      "grad_norm": 2.4149370193481445,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.0949,
      "step": 7
    },
    {
      "epoch": 0.06469547637098812,
      "grad_norm": 1.5469962358474731,
      "learning_rate": 9.934567829727386e-05,
      "loss": 0.9459,
      "step": 8
    },
    {
      "epoch": 0.07278241091736164,
      "grad_norm": 0.9416520595550537,
      "learning_rate": 9.905878394570453e-05,
      "loss": 0.8887,
      "step": 9
    },
    {
      "epoch": 0.08086934546373516,
      "grad_norm": 0.7777389883995056,
      "learning_rate": 9.872051902290737e-05,
      "loss": 0.8094,
      "step": 10
    },
    {
      "epoch": 0.08895628001010866,
      "grad_norm": 0.6452591419219971,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.7,
      "step": 11
    },
    {
      "epoch": 0.09704321455648218,
      "grad_norm": 0.6828857660293579,
      "learning_rate": 9.789151450663723e-05,
      "loss": 0.5981,
      "step": 12
    },
    {
      "epoch": 0.1051301491028557,
      "grad_norm": 0.6075629591941833,
      "learning_rate": 9.740174149534693e-05,
      "loss": 0.7365,
      "step": 13
    },
    {
      "epoch": 0.11321708364922921,
      "grad_norm": 0.4803518056869507,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.6859,
      "step": 14
    },
    {
      "epoch": 0.12130401819560273,
      "grad_norm": 0.5006831288337708,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.7054,
      "step": 15
    },
    {
      "epoch": 0.12939095274197623,
      "grad_norm": 0.5048025846481323,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.8301,
      "step": 16
    },
    {
      "epoch": 0.13747788728834975,
      "grad_norm": 0.5192086696624756,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.8157,
      "step": 17
    },
    {
      "epoch": 0.14556482183472327,
      "grad_norm": 0.5117838978767395,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.7733,
      "step": 18
    },
    {
      "epoch": 0.1536517563810968,
      "grad_norm": 0.4643174111843109,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.7385,
      "step": 19
    },
    {
      "epoch": 0.1617386909274703,
      "grad_norm": 0.44568756222724915,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.7317,
      "step": 20
    },
    {
      "epoch": 0.16982562547384383,
      "grad_norm": 0.4924642741680145,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.708,
      "step": 21
    },
    {
      "epoch": 0.17791256002021733,
      "grad_norm": 0.48531684279441833,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.7477,
      "step": 22
    },
    {
      "epoch": 0.18599949456659085,
      "grad_norm": 0.4396596848964691,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.6783,
      "step": 23
    },
    {
      "epoch": 0.19408642911296436,
      "grad_norm": 0.40898025035858154,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.6408,
      "step": 24
    },
    {
      "epoch": 0.20217336365933788,
      "grad_norm": 0.48895806074142456,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.6364,
      "step": 25
    },
    {
      "epoch": 0.20217336365933788,
      "eval_loss": 0.6505181193351746,
      "eval_runtime": 3.4916,
      "eval_samples_per_second": 14.32,
      "eval_steps_per_second": 3.723,
      "step": 25
    },
    {
      "epoch": 0.2102602982057114,
      "grad_norm": 0.5990607142448425,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.7604,
      "step": 26
    },
    {
      "epoch": 0.21834723275208492,
      "grad_norm": 0.5680568218231201,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.7052,
      "step": 27
    },
    {
      "epoch": 0.22643416729845842,
      "grad_norm": 0.4318358302116394,
      "learning_rate": 8.457416554680877e-05,
      "loss": 0.7392,
      "step": 28
    },
    {
      "epoch": 0.23452110184483194,
      "grad_norm": 0.4534890353679657,
      "learning_rate": 8.339895749467238e-05,
      "loss": 0.7612,
      "step": 29
    },
    {
      "epoch": 0.24260803639120546,
      "grad_norm": 0.41572484374046326,
      "learning_rate": 8.219063752844926e-05,
      "loss": 0.6753,
      "step": 30
    },
    {
      "epoch": 0.250694970937579,
      "grad_norm": 0.391692578792572,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.7202,
      "step": 31
    },
    {
      "epoch": 0.25878190548395247,
      "grad_norm": 0.4226691722869873,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.6996,
      "step": 32
    },
    {
      "epoch": 0.266868840030326,
      "grad_norm": 0.43875357508659363,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.7064,
      "step": 33
    },
    {
      "epoch": 0.2749557745766995,
      "grad_norm": 0.3757180869579315,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.6694,
      "step": 34
    },
    {
      "epoch": 0.28304270912307306,
      "grad_norm": 0.41616472601890564,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.6895,
      "step": 35
    },
    {
      "epoch": 0.29112964366944655,
      "grad_norm": 0.4041263461112976,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.6098,
      "step": 36
    },
    {
      "epoch": 0.29921657821582004,
      "grad_norm": 0.39486125111579895,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.6039,
      "step": 37
    },
    {
      "epoch": 0.3073035127621936,
      "grad_norm": 0.35433000326156616,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.5956,
      "step": 38
    },
    {
      "epoch": 0.3153904473085671,
      "grad_norm": 0.3867066204547882,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.6729,
      "step": 39
    },
    {
      "epoch": 0.3234773818549406,
      "grad_norm": 0.40773889422416687,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.6722,
      "step": 40
    },
    {
      "epoch": 0.3315643164013141,
      "grad_norm": 0.36118409037590027,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.6863,
      "step": 41
    },
    {
      "epoch": 0.33965125094768767,
      "grad_norm": 0.42860254645347595,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.7423,
      "step": 42
    },
    {
      "epoch": 0.34773818549406116,
      "grad_norm": 0.3781806528568268,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.6734,
      "step": 43
    },
    {
      "epoch": 0.35582512004043465,
      "grad_norm": 0.45583733916282654,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.7366,
      "step": 44
    },
    {
      "epoch": 0.3639120545868082,
      "grad_norm": 0.42888590693473816,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.6791,
      "step": 45
    },
    {
      "epoch": 0.3719989891331817,
      "grad_norm": 0.5353739261627197,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.6581,
      "step": 46
    },
    {
      "epoch": 0.38008592367955524,
      "grad_norm": 0.6451358199119568,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.6297,
      "step": 47
    },
    {
      "epoch": 0.38817285822592873,
      "grad_norm": 0.4006296396255493,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.614,
      "step": 48
    },
    {
      "epoch": 0.3962597927723022,
      "grad_norm": 0.4140074849128723,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.5914,
      "step": 49
    },
    {
      "epoch": 0.40434672731867577,
      "grad_norm": 0.3834184408187866,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.5771,
      "step": 50
    },
    {
      "epoch": 0.40434672731867577,
      "eval_loss": 0.6258954405784607,
      "eval_runtime": 3.5135,
      "eval_samples_per_second": 14.231,
      "eval_steps_per_second": 3.7,
      "step": 50
    },
    {
      "epoch": 0.41243366186504926,
      "grad_norm": 0.4838196933269501,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.7284,
      "step": 51
    },
    {
      "epoch": 0.4205205964114228,
      "grad_norm": 0.49653565883636475,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.6909,
      "step": 52
    },
    {
      "epoch": 0.4286075309577963,
      "grad_norm": 0.5994144678115845,
      "learning_rate": 4.887250079066892e-05,
      "loss": 0.7597,
      "step": 53
    },
    {
      "epoch": 0.43669446550416985,
      "grad_norm": 0.5351035594940186,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 0.7537,
      "step": 54
    },
    {
      "epoch": 0.44478140005054334,
      "grad_norm": 0.4333861470222473,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.6553,
      "step": 55
    },
    {
      "epoch": 0.45286833459691683,
      "grad_norm": 0.39463362097740173,
      "learning_rate": 4.43456010790099e-05,
      "loss": 0.7712,
      "step": 56
    },
    {
      "epoch": 0.4609552691432904,
      "grad_norm": 0.36598527431488037,
      "learning_rate": 4.285914529793391e-05,
      "loss": 0.6333,
      "step": 57
    },
    {
      "epoch": 0.4690422036896639,
      "grad_norm": 0.3563452661037445,
      "learning_rate": 4.13868452103516e-05,
      "loss": 0.6562,
      "step": 58
    },
    {
      "epoch": 0.4771291382360374,
      "grad_norm": 0.451840341091156,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.711,
      "step": 59
    },
    {
      "epoch": 0.4852160727824109,
      "grad_norm": 0.37084537744522095,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 0.6075,
      "step": 60
    },
    {
      "epoch": 0.49330300732878446,
      "grad_norm": 0.47421273589134216,
      "learning_rate": 3.707195095691913e-05,
      "loss": 0.7213,
      "step": 61
    },
    {
      "epoch": 0.501389941875158,
      "grad_norm": 0.5006868243217468,
      "learning_rate": 3.567324506364632e-05,
      "loss": 0.5814,
      "step": 62
    },
    {
      "epoch": 0.5094768764215315,
      "grad_norm": 0.38857290148735046,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.6031,
      "step": 63
    },
    {
      "epoch": 0.5175638109679049,
      "grad_norm": 0.3656562268733978,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 0.7153,
      "step": 64
    },
    {
      "epoch": 0.5256507455142785,
      "grad_norm": 0.3729749023914337,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.7616,
      "step": 65
    },
    {
      "epoch": 0.533737680060652,
      "grad_norm": 0.3745996654033661,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.7703,
      "step": 66
    },
    {
      "epoch": 0.5418246146070256,
      "grad_norm": 0.3874468505382538,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.7703,
      "step": 67
    },
    {
      "epoch": 0.549911549153399,
      "grad_norm": 0.40286222100257874,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 0.7155,
      "step": 68
    },
    {
      "epoch": 0.5579984836997726,
      "grad_norm": 0.3780246078968048,
      "learning_rate": 2.660104250532764e-05,
      "loss": 0.6842,
      "step": 69
    },
    {
      "epoch": 0.5660854182461461,
      "grad_norm": 0.34932300448417664,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.6526,
      "step": 70
    },
    {
      "epoch": 0.5741723527925195,
      "grad_norm": 0.37983378767967224,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.6156,
      "step": 71
    },
    {
      "epoch": 0.5822592873388931,
      "grad_norm": 0.3535488545894623,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.5966,
      "step": 72
    },
    {
      "epoch": 0.5903462218852666,
      "grad_norm": 0.5434425473213196,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 0.7458,
      "step": 73
    },
    {
      "epoch": 0.5984331564316401,
      "grad_norm": 0.37971338629722595,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 0.6074,
      "step": 74
    },
    {
      "epoch": 0.6065200909780136,
      "grad_norm": 0.4319310188293457,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.5151,
      "step": 75
    },
    {
      "epoch": 0.6065200909780136,
      "eval_loss": 0.6152855753898621,
      "eval_runtime": 3.512,
      "eval_samples_per_second": 14.237,
      "eval_steps_per_second": 3.702,
      "step": 75
    },
    {
      "epoch": 0.6146070255243872,
      "grad_norm": 0.34593966603279114,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.6562,
      "step": 76
    },
    {
      "epoch": 0.6226939600707607,
      "grad_norm": 0.36323046684265137,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 0.6715,
      "step": 77
    },
    {
      "epoch": 0.6307808946171342,
      "grad_norm": 0.39813435077667236,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.7863,
      "step": 78
    },
    {
      "epoch": 0.6388678291635077,
      "grad_norm": 0.34668055176734924,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.6792,
      "step": 79
    },
    {
      "epoch": 0.6469547637098813,
      "grad_norm": 0.38668936491012573,
      "learning_rate": 1.577527884852619e-05,
      "loss": 0.8067,
      "step": 80
    },
    {
      "epoch": 0.6550416982562547,
      "grad_norm": 0.38659054040908813,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 0.7092,
      "step": 81
    },
    {
      "epoch": 0.6631286328026282,
      "grad_norm": 0.34319162368774414,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 0.6067,
      "step": 82
    },
    {
      "epoch": 0.6712155673490018,
      "grad_norm": 0.38419049978256226,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.7169,
      "step": 83
    },
    {
      "epoch": 0.6793025018953753,
      "grad_norm": 0.3796985149383545,
      "learning_rate": 1.313747004979751e-05,
      "loss": 0.7196,
      "step": 84
    },
    {
      "epoch": 0.6873894364417488,
      "grad_norm": 0.38364750146865845,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 0.6701,
      "step": 85
    },
    {
      "epoch": 0.6954763709881223,
      "grad_norm": 0.4333467185497284,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 0.6451,
      "step": 86
    },
    {
      "epoch": 0.7035633055344959,
      "grad_norm": 0.38475340604782104,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.6131,
      "step": 87
    },
    {
      "epoch": 0.7116502400808693,
      "grad_norm": 0.34996670484542847,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 0.5663,
      "step": 88
    },
    {
      "epoch": 0.7197371746272428,
      "grad_norm": 0.3536860942840576,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.6976,
      "step": 89
    },
    {
      "epoch": 0.7278241091736164,
      "grad_norm": 0.36633411049842834,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.6998,
      "step": 90
    },
    {
      "epoch": 0.7359110437199899,
      "grad_norm": 0.37283647060394287,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.6256,
      "step": 91
    },
    {
      "epoch": 0.7439979782663634,
      "grad_norm": 0.35322660207748413,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.6615,
      "step": 92
    },
    {
      "epoch": 0.7520849128127369,
      "grad_norm": 0.41877758502960205,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 0.7689,
      "step": 93
    },
    {
      "epoch": 0.7601718473591105,
      "grad_norm": 0.3584843575954437,
      "learning_rate": 1.002623399352217e-05,
      "loss": 0.6636,
      "step": 94
    },
    {
      "epoch": 0.7682587819054839,
      "grad_norm": 0.3423212170600891,
      "learning_rate": 1e-05,
      "loss": 0.5993,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1339358872902042e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}