{
  "best_metric": 1.954980492591858,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.01631787214947171,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001631787214947171,
      "grad_norm": 0.9626743197441101,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.3231,
      "step": 1
    },
    {
      "epoch": 0.0001631787214947171,
      "eval_loss": 2.1344542503356934,
      "eval_runtime": 976.0493,
      "eval_samples_per_second": 10.575,
      "eval_steps_per_second": 2.644,
      "step": 1
    },
    {
      "epoch": 0.0003263574429894342,
      "grad_norm": 0.8612233996391296,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.1608,
      "step": 2
    },
    {
      "epoch": 0.0004895361644841513,
      "grad_norm": 0.9304367899894714,
      "learning_rate": 1.5e-06,
      "loss": 2.2746,
      "step": 3
    },
    {
      "epoch": 0.0006527148859788684,
      "grad_norm": 0.8620933294296265,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.1838,
      "step": 4
    },
    {
      "epoch": 0.0008158936074735855,
      "grad_norm": 0.8950667977333069,
      "learning_rate": 2.5e-06,
      "loss": 2.1265,
      "step": 5
    },
    {
      "epoch": 0.0009790723289683026,
      "grad_norm": 0.8841383457183838,
      "learning_rate": 3e-06,
      "loss": 2.2276,
      "step": 6
    },
    {
      "epoch": 0.0011422510504630196,
      "grad_norm": 0.8289633989334106,
      "learning_rate": 3.5e-06,
      "loss": 2.2067,
      "step": 7
    },
    {
      "epoch": 0.0013054297719577368,
      "grad_norm": 0.8701562881469727,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.1737,
      "step": 8
    },
    {
      "epoch": 0.0014686084934524537,
      "grad_norm": 0.836694598197937,
      "learning_rate": 4.5e-06,
      "loss": 2.1575,
      "step": 9
    },
    {
      "epoch": 0.001631787214947171,
      "grad_norm": 0.8217163681983948,
      "learning_rate": 5e-06,
      "loss": 2.1041,
      "step": 10
    },
    {
      "epoch": 0.001794965936441888,
      "grad_norm": 0.8088410496711731,
      "learning_rate": 4.99847706754774e-06,
      "loss": 2.1987,
      "step": 11
    },
    {
      "epoch": 0.001958144657936605,
      "grad_norm": 0.8314682245254517,
      "learning_rate": 4.993910125649561e-06,
      "loss": 2.0736,
      "step": 12
    },
    {
      "epoch": 0.0021213233794313223,
      "grad_norm": 0.8567140698432922,
      "learning_rate": 4.986304738420684e-06,
      "loss": 2.1567,
      "step": 13
    },
    {
      "epoch": 0.002284502100926039,
      "grad_norm": 0.8521527051925659,
      "learning_rate": 4.975670171853926e-06,
      "loss": 2.0756,
      "step": 14
    },
    {
      "epoch": 0.0024476808224207563,
      "grad_norm": 0.890558123588562,
      "learning_rate": 4.962019382530521e-06,
      "loss": 2.0736,
      "step": 15
    },
    {
      "epoch": 0.0026108595439154735,
      "grad_norm": 0.8253862857818604,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 2.0023,
      "step": 16
    },
    {
      "epoch": 0.0027740382654101907,
      "grad_norm": 0.8322637677192688,
      "learning_rate": 4.925739315689991e-06,
      "loss": 2.0468,
      "step": 17
    },
    {
      "epoch": 0.0029372169869049075,
      "grad_norm": 0.8288842439651489,
      "learning_rate": 4.903154239845798e-06,
      "loss": 1.9811,
      "step": 18
    },
    {
      "epoch": 0.0031003957083996247,
      "grad_norm": 0.9009273648262024,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 2.1364,
      "step": 19
    },
    {
      "epoch": 0.003263574429894342,
      "grad_norm": 0.8775635957717896,
      "learning_rate": 4.849231551964771e-06,
      "loss": 2.0339,
      "step": 20
    },
    {
      "epoch": 0.0034267531513890587,
      "grad_norm": 0.9163408279418945,
      "learning_rate": 4.817959636416969e-06,
      "loss": 2.0333,
      "step": 21
    },
    {
      "epoch": 0.003589931872883776,
      "grad_norm": 0.9037641286849976,
      "learning_rate": 4.783863644106502e-06,
      "loss": 2.0447,
      "step": 22
    },
    {
      "epoch": 0.003753110594378493,
      "grad_norm": 0.9167019724845886,
      "learning_rate": 4.746985115747918e-06,
      "loss": 1.9999,
      "step": 23
    },
    {
      "epoch": 0.00391628931587321,
      "grad_norm": 0.8852622509002686,
      "learning_rate": 4.707368982147318e-06,
      "loss": 2.0036,
      "step": 24
    },
    {
      "epoch": 0.0040794680373679275,
      "grad_norm": 0.890647292137146,
      "learning_rate": 4.665063509461098e-06,
      "loss": 2.0591,
      "step": 25
    },
    {
      "epoch": 0.004242646758862645,
      "grad_norm": 0.8380885124206543,
      "learning_rate": 4.620120240391065e-06,
      "loss": 2.0312,
      "step": 26
    },
    {
      "epoch": 0.004405825480357361,
      "grad_norm": 0.9328538179397583,
      "learning_rate": 4.572593931387604e-06,
      "loss": 2.0167,
      "step": 27
    },
    {
      "epoch": 0.004569004201852078,
      "grad_norm": 0.8684221506118774,
      "learning_rate": 4.522542485937369e-06,
      "loss": 2.0018,
      "step": 28
    },
    {
      "epoch": 0.004732182923346795,
      "grad_norm": 0.9270681738853455,
      "learning_rate": 4.470026884016805e-06,
      "loss": 2.0179,
      "step": 29
    },
    {
      "epoch": 0.004895361644841513,
      "grad_norm": 0.9681967496871948,
      "learning_rate": 4.415111107797445e-06,
      "loss": 2.1236,
      "step": 30
    },
    {
      "epoch": 0.00505854036633623,
      "grad_norm": 0.9239471554756165,
      "learning_rate": 4.357862063693486e-06,
      "loss": 1.9945,
      "step": 31
    },
    {
      "epoch": 0.005221719087830947,
      "grad_norm": 0.9569579362869263,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 1.9907,
      "step": 32
    },
    {
      "epoch": 0.005384897809325664,
      "grad_norm": 0.9254785776138306,
      "learning_rate": 4.236645926147493e-06,
      "loss": 2.0334,
      "step": 33
    },
    {
      "epoch": 0.0055480765308203814,
      "grad_norm": 0.8775327205657959,
      "learning_rate": 4.172826515897146e-06,
      "loss": 2.049,
      "step": 34
    },
    {
      "epoch": 0.005711255252315098,
      "grad_norm": 0.9445580840110779,
      "learning_rate": 4.106969024216348e-06,
      "loss": 1.9781,
      "step": 35
    },
    {
      "epoch": 0.005874433973809815,
      "grad_norm": 0.8967560529708862,
      "learning_rate": 4.039153688314146e-06,
      "loss": 2.017,
      "step": 36
    },
    {
      "epoch": 0.006037612695304532,
      "grad_norm": 0.9454420208930969,
      "learning_rate": 3.969463130731183e-06,
      "loss": 1.9148,
      "step": 37
    },
    {
      "epoch": 0.006200791416799249,
      "grad_norm": 1.0066184997558594,
      "learning_rate": 3.897982258676867e-06,
      "loss": 2.0719,
      "step": 38
    },
    {
      "epoch": 0.006363970138293967,
      "grad_norm": 0.9081863164901733,
      "learning_rate": 3.824798160583012e-06,
      "loss": 1.9958,
      "step": 39
    },
    {
      "epoch": 0.006527148859788684,
      "grad_norm": 0.9053497314453125,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 2.0227,
      "step": 40
    },
    {
      "epoch": 0.006690327581283401,
      "grad_norm": 0.9111195206642151,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 1.9154,
      "step": 41
    },
    {
      "epoch": 0.006853506302778117,
      "grad_norm": 0.8714330792427063,
      "learning_rate": 3.595927866972694e-06,
      "loss": 2.0181,
      "step": 42
    },
    {
      "epoch": 0.0070166850242728345,
      "grad_norm": 0.9528706073760986,
      "learning_rate": 3.516841607689501e-06,
      "loss": 2.1378,
      "step": 43
    },
    {
      "epoch": 0.007179863745767552,
      "grad_norm": 0.9247714877128601,
      "learning_rate": 3.436516483539781e-06,
      "loss": 2.0865,
      "step": 44
    },
    {
      "epoch": 0.007343042467262269,
      "grad_norm": 1.0060503482818604,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 2.1272,
      "step": 45
    },
    {
      "epoch": 0.007506221188756986,
      "grad_norm": 1.0275453329086304,
      "learning_rate": 3.272542485937369e-06,
      "loss": 2.0768,
      "step": 46
    },
    {
      "epoch": 0.007669399910251703,
      "grad_norm": 1.0227175951004028,
      "learning_rate": 3.189093389542498e-06,
      "loss": 2.1448,
      "step": 47
    },
    {
      "epoch": 0.00783257863174642,
      "grad_norm": 1.136629343032837,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 2.2079,
      "step": 48
    },
    {
      "epoch": 0.007995757353241137,
      "grad_norm": 1.1337389945983887,
      "learning_rate": 3.019779227044398e-06,
      "loss": 2.1598,
      "step": 49
    },
    {
      "epoch": 0.008158936074735855,
      "grad_norm": 1.3956023454666138,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 2.1415,
      "step": 50
    },
    {
      "epoch": 0.008158936074735855,
      "eval_loss": 1.986087441444397,
      "eval_runtime": 980.5339,
      "eval_samples_per_second": 10.527,
      "eval_steps_per_second": 2.632,
      "step": 50
    },
    {
      "epoch": 0.008322114796230571,
      "grad_norm": 0.6517155170440674,
      "learning_rate": 2.847932752400164e-06,
      "loss": 2.1295,
      "step": 51
    },
    {
      "epoch": 0.00848529351772529,
      "grad_norm": 0.6166985034942627,
      "learning_rate": 2.761321158169134e-06,
      "loss": 2.0326,
      "step": 52
    },
    {
      "epoch": 0.008648472239220006,
      "grad_norm": 0.6049599647521973,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 2.069,
      "step": 53
    },
    {
      "epoch": 0.008811650960714722,
      "grad_norm": 0.5539830923080444,
      "learning_rate": 2.587248741756253e-06,
      "loss": 2.0095,
      "step": 54
    },
    {
      "epoch": 0.00897482968220944,
      "grad_norm": 0.5926068425178528,
      "learning_rate": 2.5e-06,
      "loss": 2.1317,
      "step": 55
    },
    {
      "epoch": 0.009138008403704156,
      "grad_norm": 0.6043214797973633,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 2.0575,
      "step": 56
    },
    {
      "epoch": 0.009301187125198875,
      "grad_norm": 0.5795297622680664,
      "learning_rate": 2.325608815639687e-06,
      "loss": 2.0149,
      "step": 57
    },
    {
      "epoch": 0.00946436584669359,
      "grad_norm": 0.5584662556648254,
      "learning_rate": 2.238678841830867e-06,
      "loss": 2.0126,
      "step": 58
    },
    {
      "epoch": 0.009627544568188309,
      "grad_norm": 0.6003333330154419,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 2.0313,
      "step": 59
    },
    {
      "epoch": 0.009790723289683025,
      "grad_norm": 0.5960946679115295,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 1.9306,
      "step": 60
    },
    {
      "epoch": 0.009953902011177742,
      "grad_norm": 0.5591971278190613,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 2.0074,
      "step": 61
    },
    {
      "epoch": 0.01011708073267246,
      "grad_norm": 0.5890583395957947,
      "learning_rate": 1.895195261000831e-06,
      "loss": 1.9372,
      "step": 62
    },
    {
      "epoch": 0.010280259454167176,
      "grad_norm": 0.5822552442550659,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 1.9925,
      "step": 63
    },
    {
      "epoch": 0.010443438175661894,
      "grad_norm": 0.5664207339286804,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 1.8616,
      "step": 64
    },
    {
      "epoch": 0.01060661689715661,
      "grad_norm": 0.5835029482841492,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 1.9502,
      "step": 65
    },
    {
      "epoch": 0.010769795618651328,
      "grad_norm": 0.5808869004249573,
      "learning_rate": 1.56348351646022e-06,
      "loss": 1.9177,
      "step": 66
    },
    {
      "epoch": 0.010932974340146045,
      "grad_norm": 0.5943641662597656,
      "learning_rate": 1.4831583923105e-06,
      "loss": 1.8628,
      "step": 67
    },
    {
      "epoch": 0.011096153061640763,
      "grad_norm": 0.6218149662017822,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 1.8908,
      "step": 68
    },
    {
      "epoch": 0.01125933178313548,
      "grad_norm": 0.5880563855171204,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 1.9614,
      "step": 69
    },
    {
      "epoch": 0.011422510504630196,
      "grad_norm": 0.5864894986152649,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 1.8818,
      "step": 70
    },
    {
      "epoch": 0.011585689226124914,
      "grad_norm": 0.5821499824523926,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 1.9263,
      "step": 71
    },
    {
      "epoch": 0.01174886794761963,
      "grad_norm": 0.5684424638748169,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 1.9137,
      "step": 72
    },
    {
      "epoch": 0.011912046669114348,
      "grad_norm": 0.5831771492958069,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 1.8792,
      "step": 73
    },
    {
      "epoch": 0.012075225390609064,
      "grad_norm": 0.6676979660987854,
      "learning_rate": 9.608463116858544e-07,
      "loss": 1.8534,
      "step": 74
    },
    {
      "epoch": 0.012238404112103782,
      "grad_norm": 0.614493727684021,
      "learning_rate": 8.930309757836517e-07,
      "loss": 1.9241,
      "step": 75
    },
    {
      "epoch": 0.012401582833598499,
      "grad_norm": 0.6089916229248047,
      "learning_rate": 8.271734841028553e-07,
      "loss": 1.9294,
      "step": 76
    },
    {
      "epoch": 0.012564761555093215,
      "grad_norm": 0.6394822597503662,
      "learning_rate": 7.633540738525066e-07,
      "loss": 1.9013,
      "step": 77
    },
    {
      "epoch": 0.012727940276587933,
      "grad_norm": 0.6592298150062561,
      "learning_rate": 7.016504991533727e-07,
      "loss": 1.9368,
      "step": 78
    },
    {
      "epoch": 0.01289111899808265,
      "grad_norm": 0.6934499144554138,
      "learning_rate": 6.421379363065142e-07,
      "loss": 1.9195,
      "step": 79
    },
    {
      "epoch": 0.013054297719577368,
      "grad_norm": 0.7235682606697083,
      "learning_rate": 5.848888922025553e-07,
      "loss": 1.9364,
      "step": 80
    },
    {
      "epoch": 0.013217476441072084,
      "grad_norm": 0.6777318716049194,
      "learning_rate": 5.299731159831953e-07,
      "loss": 1.9084,
      "step": 81
    },
    {
      "epoch": 0.013380655162566802,
      "grad_norm": 0.6706295609474182,
      "learning_rate": 4.774575140626317e-07,
      "loss": 1.8473,
      "step": 82
    },
    {
      "epoch": 0.013543833884061518,
      "grad_norm": 0.7311359643936157,
      "learning_rate": 4.27406068612396e-07,
      "loss": 1.8132,
      "step": 83
    },
    {
      "epoch": 0.013707012605556235,
      "grad_norm": 0.6486523747444153,
      "learning_rate": 3.798797596089351e-07,
      "loss": 1.8764,
      "step": 84
    },
    {
      "epoch": 0.013870191327050953,
      "grad_norm": 0.6983171105384827,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 1.8729,
      "step": 85
    },
    {
      "epoch": 0.014033370048545669,
      "grad_norm": 0.6943270564079285,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 1.7492,
      "step": 86
    },
    {
      "epoch": 0.014196548770040387,
      "grad_norm": 0.6928853988647461,
      "learning_rate": 2.53014884252083e-07,
      "loss": 1.8753,
      "step": 87
    },
    {
      "epoch": 0.014359727491535103,
      "grad_norm": 0.7341625094413757,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 1.828,
      "step": 88
    },
    {
      "epoch": 0.014522906213029822,
      "grad_norm": 0.7738997340202332,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 1.9893,
      "step": 89
    },
    {
      "epoch": 0.014686084934524538,
      "grad_norm": 0.7556887269020081,
      "learning_rate": 1.507684480352292e-07,
      "loss": 1.9602,
      "step": 90
    },
    {
      "epoch": 0.014849263656019254,
      "grad_norm": 0.7297267913818359,
      "learning_rate": 1.223587092621162e-07,
      "loss": 1.9517,
      "step": 91
    },
    {
      "epoch": 0.015012442377513972,
      "grad_norm": 0.8259098529815674,
      "learning_rate": 9.684576015420277e-08,
      "loss": 2.0288,
      "step": 92
    },
    {
      "epoch": 0.015175621099008689,
      "grad_norm": 0.8356319665908813,
      "learning_rate": 7.426068431000883e-08,
      "loss": 2.0425,
      "step": 93
    },
    {
      "epoch": 0.015338799820503407,
      "grad_norm": 0.8901850581169128,
      "learning_rate": 5.463099816548578e-08,
      "loss": 1.9574,
      "step": 94
    },
    {
      "epoch": 0.015501978541998123,
      "grad_norm": 0.8994855284690857,
      "learning_rate": 3.798061746947995e-08,
      "loss": 1.9856,
      "step": 95
    },
    {
      "epoch": 0.01566515726349284,
      "grad_norm": 0.9636688828468323,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 2.1306,
      "step": 96
    },
    {
      "epoch": 0.01582833598498756,
      "grad_norm": 1.0676484107971191,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 2.0383,
      "step": 97
    },
    {
      "epoch": 0.015991514706482274,
      "grad_norm": 0.999144971370697,
      "learning_rate": 6.089874350439507e-09,
      "loss": 2.2039,
      "step": 98
    },
    {
      "epoch": 0.016154693427976992,
      "grad_norm": 1.143728494644165,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 2.0779,
      "step": 99
    },
    {
      "epoch": 0.01631787214947171,
      "grad_norm": 1.522695779800415,
      "learning_rate": 0.0,
      "loss": 2.1333,
      "step": 100
    },
    {
      "epoch": 0.01631787214947171,
      "eval_loss": 1.954980492591858,
      "eval_runtime": 980.7518,
      "eval_samples_per_second": 10.525,
      "eval_steps_per_second": 2.632,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7378709617403494e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}