{
  "best_metric": 0.617424488067627,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.11703561116458133,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001231953801732435,
      "grad_norm": 1.4951938390731812,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8121,
      "step": 1
    },
    {
      "epoch": 0.001231953801732435,
      "eval_loss": 2.4635820388793945,
      "eval_runtime": 3.447,
      "eval_samples_per_second": 14.505,
      "eval_steps_per_second": 3.771,
      "step": 1
    },
    {
      "epoch": 0.00246390760346487,
      "grad_norm": 1.7550477981567383,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.1289,
      "step": 2
    },
    {
      "epoch": 0.003695861405197305,
      "grad_norm": 1.997981071472168,
      "learning_rate": 0.0001,
      "loss": 2.1937,
      "step": 3
    },
    {
      "epoch": 0.00492781520692974,
      "grad_norm": 1.8525218963623047,
      "learning_rate": 9.997376600647783e-05,
      "loss": 2.0099,
      "step": 4
    },
    {
      "epoch": 0.006159769008662175,
      "grad_norm": 1.6681252717971802,
      "learning_rate": 9.989509461357426e-05,
      "loss": 1.7067,
      "step": 5
    },
    {
      "epoch": 0.00739172281039461,
      "grad_norm": 1.6790170669555664,
      "learning_rate": 9.976407754861426e-05,
      "loss": 1.549,
      "step": 6
    },
    {
      "epoch": 0.008623676612127045,
      "grad_norm": 2.22214674949646,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.5006,
      "step": 7
    },
    {
      "epoch": 0.00985563041385948,
      "grad_norm": 2.076958417892456,
      "learning_rate": 9.934567829727386e-05,
      "loss": 1.3701,
      "step": 8
    },
    {
      "epoch": 0.011087584215591915,
      "grad_norm": 1.8793498277664185,
      "learning_rate": 9.905878394570453e-05,
      "loss": 1.1889,
      "step": 9
    },
    {
      "epoch": 0.01231953801732435,
      "grad_norm": 1.9051135778427124,
      "learning_rate": 9.872051902290737e-05,
      "loss": 1.1137,
      "step": 10
    },
    {
      "epoch": 0.013551491819056785,
      "grad_norm": 1.5732001066207886,
      "learning_rate": 9.833127793065098e-05,
      "loss": 1.0469,
      "step": 11
    },
    {
      "epoch": 0.01478344562078922,
      "grad_norm": 1.9609421491622925,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.1223,
      "step": 12
    },
    {
      "epoch": 0.016015399422521656,
      "grad_norm": 1.8344721794128418,
      "learning_rate": 9.740174149534693e-05,
      "loss": 1.0626,
      "step": 13
    },
    {
      "epoch": 0.01724735322425409,
      "grad_norm": 1.5016754865646362,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.9166,
      "step": 14
    },
    {
      "epoch": 0.018479307025986526,
      "grad_norm": 1.0660717487335205,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.8678,
      "step": 15
    },
    {
      "epoch": 0.01971126082771896,
      "grad_norm": 0.9451479315757751,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.8882,
      "step": 16
    },
    {
      "epoch": 0.020943214629451395,
      "grad_norm": 0.8659009337425232,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.822,
      "step": 17
    },
    {
      "epoch": 0.02217516843118383,
      "grad_norm": 0.8729805946350098,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.8542,
      "step": 18
    },
    {
      "epoch": 0.023407122232916265,
      "grad_norm": 0.8671184778213501,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.8336,
      "step": 19
    },
    {
      "epoch": 0.0246390760346487,
      "grad_norm": 0.8609638214111328,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.8219,
      "step": 20
    },
    {
      "epoch": 0.025871029836381135,
      "grad_norm": 0.9347344636917114,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.8306,
      "step": 21
    },
    {
      "epoch": 0.02710298363811357,
      "grad_norm": 0.8969244956970215,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.8232,
      "step": 22
    },
    {
      "epoch": 0.028334937439846004,
      "grad_norm": 1.0083746910095215,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.8318,
      "step": 23
    },
    {
      "epoch": 0.02956689124157844,
      "grad_norm": 1.0339181423187256,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.8636,
      "step": 24
    },
    {
      "epoch": 0.030798845043310877,
      "grad_norm": 1.1391716003417969,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.9234,
      "step": 25
    },
    {
      "epoch": 0.030798845043310877,
      "eval_loss": 0.7983564734458923,
      "eval_runtime": 3.5175,
      "eval_samples_per_second": 14.214,
      "eval_steps_per_second": 3.696,
      "step": 25
    },
    {
      "epoch": 0.03203079884504331,
      "grad_norm": 1.529720425605774,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.8309,
      "step": 26
    },
    {
      "epoch": 0.033262752646775744,
      "grad_norm": 1.6183327436447144,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.7803,
      "step": 27
    },
    {
      "epoch": 0.03449470644850818,
      "grad_norm": 1.110182285308838,
      "learning_rate": 8.457416554680877e-05,
      "loss": 0.7443,
      "step": 28
    },
    {
      "epoch": 0.03572666025024061,
      "grad_norm": 0.8818290829658508,
      "learning_rate": 8.339895749467238e-05,
      "loss": 0.7466,
      "step": 29
    },
    {
      "epoch": 0.03695861405197305,
      "grad_norm": 0.9471279978752136,
      "learning_rate": 8.219063752844926e-05,
      "loss": 0.7426,
      "step": 30
    },
    {
      "epoch": 0.03819056785370548,
      "grad_norm": 1.0536586046218872,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.7339,
      "step": 31
    },
    {
      "epoch": 0.03942252165543792,
      "grad_norm": 0.8326343894004822,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.6976,
      "step": 32
    },
    {
      "epoch": 0.04065447545717036,
      "grad_norm": 0.823235273361206,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.7378,
      "step": 33
    },
    {
      "epoch": 0.04188642925890279,
      "grad_norm": 0.8146088719367981,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.7537,
      "step": 34
    },
    {
      "epoch": 0.04311838306063523,
      "grad_norm": 0.852783739566803,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.7191,
      "step": 35
    },
    {
      "epoch": 0.04435033686236766,
      "grad_norm": 0.9801528453826904,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.774,
      "step": 36
    },
    {
      "epoch": 0.0455822906641001,
      "grad_norm": 1.0414175987243652,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.8229,
      "step": 37
    },
    {
      "epoch": 0.04681424446583253,
      "grad_norm": 0.8394467234611511,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.7731,
      "step": 38
    },
    {
      "epoch": 0.04804619826756497,
      "grad_norm": 0.8109716773033142,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.6696,
      "step": 39
    },
    {
      "epoch": 0.0492781520692974,
      "grad_norm": 0.7383696436882019,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.6555,
      "step": 40
    },
    {
      "epoch": 0.05051010587102984,
      "grad_norm": 0.7810937166213989,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.6789,
      "step": 41
    },
    {
      "epoch": 0.05174205967276227,
      "grad_norm": 0.7691031694412231,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.6582,
      "step": 42
    },
    {
      "epoch": 0.05297401347449471,
      "grad_norm": 0.9100735783576965,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.7069,
      "step": 43
    },
    {
      "epoch": 0.05420596727622714,
      "grad_norm": 0.931399405002594,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.7135,
      "step": 44
    },
    {
      "epoch": 0.05543792107795958,
      "grad_norm": 0.8463882803916931,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.6697,
      "step": 45
    },
    {
      "epoch": 0.05666987487969201,
      "grad_norm": 0.85605788230896,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.6989,
      "step": 46
    },
    {
      "epoch": 0.05790182868142445,
      "grad_norm": 0.8102529048919678,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.6696,
      "step": 47
    },
    {
      "epoch": 0.05913378248315688,
      "grad_norm": 0.8773670196533203,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.7289,
      "step": 48
    },
    {
      "epoch": 0.06036573628488932,
      "grad_norm": 0.856377363204956,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.7178,
      "step": 49
    },
    {
      "epoch": 0.061597690086621755,
      "grad_norm": 0.9929988384246826,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.7789,
      "step": 50
    },
    {
      "epoch": 0.061597690086621755,
      "eval_loss": 0.6646984219551086,
      "eval_runtime": 3.5125,
      "eval_samples_per_second": 14.235,
      "eval_steps_per_second": 3.701,
      "step": 50
    },
    {
      "epoch": 0.06282964388835419,
      "grad_norm": 0.8724278807640076,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.69,
      "step": 51
    },
    {
      "epoch": 0.06406159769008662,
      "grad_norm": 0.9073512554168701,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.6701,
      "step": 52
    },
    {
      "epoch": 0.06529355149181906,
      "grad_norm": 0.8863846659660339,
      "learning_rate": 4.887250079066892e-05,
      "loss": 0.6345,
      "step": 53
    },
    {
      "epoch": 0.06652550529355149,
      "grad_norm": 0.8188042044639587,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 0.6611,
      "step": 54
    },
    {
      "epoch": 0.06775745909528393,
      "grad_norm": 0.7507838606834412,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.6475,
      "step": 55
    },
    {
      "epoch": 0.06898941289701636,
      "grad_norm": 0.7349779605865479,
      "learning_rate": 4.43456010790099e-05,
      "loss": 0.6515,
      "step": 56
    },
    {
      "epoch": 0.0702213666987488,
      "grad_norm": 0.7216666340827942,
      "learning_rate": 4.285914529793391e-05,
      "loss": 0.64,
      "step": 57
    },
    {
      "epoch": 0.07145332050048123,
      "grad_norm": 0.8082278966903687,
      "learning_rate": 4.13868452103516e-05,
      "loss": 0.664,
      "step": 58
    },
    {
      "epoch": 0.07268527430221366,
      "grad_norm": 0.80323326587677,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.6373,
      "step": 59
    },
    {
      "epoch": 0.0739172281039461,
      "grad_norm": 0.9069752097129822,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 0.6496,
      "step": 60
    },
    {
      "epoch": 0.07514918190567854,
      "grad_norm": 0.8475314378738403,
      "learning_rate": 3.707195095691913e-05,
      "loss": 0.6553,
      "step": 61
    },
    {
      "epoch": 0.07638113570741097,
      "grad_norm": 0.9898352026939392,
      "learning_rate": 3.567324506364632e-05,
      "loss": 0.7292,
      "step": 62
    },
    {
      "epoch": 0.0776130895091434,
      "grad_norm": 0.7595363259315491,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.6807,
      "step": 63
    },
    {
      "epoch": 0.07884504331087584,
      "grad_norm": 0.781152069568634,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 0.5905,
      "step": 64
    },
    {
      "epoch": 0.08007699711260828,
      "grad_norm": 0.7119630575180054,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.6144,
      "step": 65
    },
    {
      "epoch": 0.08130895091434072,
      "grad_norm": 0.7199792861938477,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.6314,
      "step": 66
    },
    {
      "epoch": 0.08254090471607314,
      "grad_norm": 0.8011656999588013,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.5818,
      "step": 67
    },
    {
      "epoch": 0.08377285851780558,
      "grad_norm": 0.7348117232322693,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 0.6245,
      "step": 68
    },
    {
      "epoch": 0.08500481231953802,
      "grad_norm": 0.7128881812095642,
      "learning_rate": 2.660104250532764e-05,
      "loss": 0.6185,
      "step": 69
    },
    {
      "epoch": 0.08623676612127046,
      "grad_norm": 0.7044535875320435,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.6437,
      "step": 70
    },
    {
      "epoch": 0.08746871992300288,
      "grad_norm": 0.7829747200012207,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.6293,
      "step": 71
    },
    {
      "epoch": 0.08870067372473532,
      "grad_norm": 0.746275007724762,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.6268,
      "step": 72
    },
    {
      "epoch": 0.08993262752646776,
      "grad_norm": 0.7758780717849731,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 0.636,
      "step": 73
    },
    {
      "epoch": 0.0911645813282002,
      "grad_norm": 0.7950238585472107,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 0.647,
      "step": 74
    },
    {
      "epoch": 0.09239653512993262,
      "grad_norm": 0.9090643525123596,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.665,
      "step": 75
    },
    {
      "epoch": 0.09239653512993262,
      "eval_loss": 0.617424488067627,
      "eval_runtime": 3.5324,
      "eval_samples_per_second": 14.155,
      "eval_steps_per_second": 3.68,
      "step": 75
    },
    {
      "epoch": 0.09362848893166506,
      "grad_norm": 0.7286236882209778,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.6132,
      "step": 76
    },
    {
      "epoch": 0.0948604427333975,
      "grad_norm": 0.753804624080658,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 0.572,
      "step": 77
    },
    {
      "epoch": 0.09609239653512994,
      "grad_norm": 0.7297849655151367,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.5946,
      "step": 78
    },
    {
      "epoch": 0.09732435033686236,
      "grad_norm": 0.7147274017333984,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.5721,
      "step": 79
    },
    {
      "epoch": 0.0985563041385948,
      "grad_norm": 0.6752864718437195,
      "learning_rate": 1.577527884852619e-05,
      "loss": 0.6103,
      "step": 80
    },
    {
      "epoch": 0.09978825794032724,
      "grad_norm": 0.6844044923782349,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 0.6109,
      "step": 81
    },
    {
      "epoch": 0.10102021174205968,
      "grad_norm": 0.6992493867874146,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 0.6177,
      "step": 82
    },
    {
      "epoch": 0.10225216554379211,
      "grad_norm": 0.7029042840003967,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.6083,
      "step": 83
    },
    {
      "epoch": 0.10348411934552454,
      "grad_norm": 0.7730789184570312,
      "learning_rate": 1.313747004979751e-05,
      "loss": 0.5947,
      "step": 84
    },
    {
      "epoch": 0.10471607314725698,
      "grad_norm": 0.7700346112251282,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 0.6205,
      "step": 85
    },
    {
      "epoch": 0.10594802694898942,
      "grad_norm": 0.8437100648880005,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 0.6452,
      "step": 86
    },
    {
      "epoch": 0.10717998075072185,
      "grad_norm": 0.8955070376396179,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.6851,
      "step": 87
    },
    {
      "epoch": 0.10841193455245428,
      "grad_norm": 0.6330913305282593,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 0.6434,
      "step": 88
    },
    {
      "epoch": 0.10964388835418672,
      "grad_norm": 0.6137003302574158,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.5866,
      "step": 89
    },
    {
      "epoch": 0.11087584215591915,
      "grad_norm": 0.6017877459526062,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.5825,
      "step": 90
    },
    {
      "epoch": 0.1121077959576516,
      "grad_norm": 0.6833033561706543,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.5836,
      "step": 91
    },
    {
      "epoch": 0.11333974975938402,
      "grad_norm": 0.7089877128601074,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.5883,
      "step": 92
    },
    {
      "epoch": 0.11457170356111646,
      "grad_norm": 0.6717115640640259,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 0.5702,
      "step": 93
    },
    {
      "epoch": 0.1158036573628489,
      "grad_norm": 0.6961142420768738,
      "learning_rate": 1.002623399352217e-05,
      "loss": 0.5704,
      "step": 94
    },
    {
      "epoch": 0.11703561116458133,
      "grad_norm": 0.7490465044975281,
      "learning_rate": 1e-05,
      "loss": 0.5949,
      "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
}