{
  "best_metric": 0.7389546632766724,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.06505122784192552,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006505122784192552,
      "grad_norm": 0.5383875966072083,
      "learning_rate": 5.000000000000001e-07,
      "loss": 4.2424,
      "step": 1
    },
    {
      "epoch": 0.0006505122784192552,
      "eval_loss": 0.7576112747192383,
      "eval_runtime": 387.1504,
      "eval_samples_per_second": 6.687,
      "eval_steps_per_second": 1.674,
      "step": 1
    },
    {
      "epoch": 0.0013010245568385104,
      "grad_norm": 0.478141725063324,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.5684,
      "step": 2
    },
    {
      "epoch": 0.0019515368352577655,
      "grad_norm": 0.4837450683116913,
      "learning_rate": 1.5e-06,
      "loss": 4.2392,
      "step": 3
    },
    {
      "epoch": 0.002602049113677021,
      "grad_norm": 0.44819143414497375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.6253,
      "step": 4
    },
    {
      "epoch": 0.0032525613920962758,
      "grad_norm": 0.5502279996871948,
      "learning_rate": 2.5e-06,
      "loss": 4.5011,
      "step": 5
    },
    {
      "epoch": 0.003903073670515531,
      "grad_norm": 0.4934608042240143,
      "learning_rate": 3e-06,
      "loss": 4.504,
      "step": 6
    },
    {
      "epoch": 0.004553585948934786,
      "grad_norm": 0.4622688889503479,
      "learning_rate": 3.5e-06,
      "loss": 4.7412,
      "step": 7
    },
    {
      "epoch": 0.005204098227354042,
      "grad_norm": 0.5313199162483215,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.511,
      "step": 8
    },
    {
      "epoch": 0.005854610505773296,
      "grad_norm": 0.4932001531124115,
      "learning_rate": 4.5e-06,
      "loss": 4.7888,
      "step": 9
    },
    {
      "epoch": 0.0065051227841925515,
      "grad_norm": 0.4534807801246643,
      "learning_rate": 5e-06,
      "loss": 4.6606,
      "step": 10
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.47632548213005066,
      "learning_rate": 4.99847706754774e-06,
      "loss": 4.7327,
      "step": 11
    },
    {
      "epoch": 0.007806147341031062,
      "grad_norm": 0.5320748090744019,
      "learning_rate": 4.993910125649561e-06,
      "loss": 4.5545,
      "step": 12
    },
    {
      "epoch": 0.008456659619450317,
      "grad_norm": 0.4857390820980072,
      "learning_rate": 4.986304738420684e-06,
      "loss": 4.8483,
      "step": 13
    },
    {
      "epoch": 0.009107171897869573,
      "grad_norm": 0.49006789922714233,
      "learning_rate": 4.975670171853926e-06,
      "loss": 4.7094,
      "step": 14
    },
    {
      "epoch": 0.009757684176288828,
      "grad_norm": 0.5228479504585266,
      "learning_rate": 4.962019382530521e-06,
      "loss": 4.5745,
      "step": 15
    },
    {
      "epoch": 0.010408196454708083,
      "grad_norm": 0.5275076627731323,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 4.7949,
      "step": 16
    },
    {
      "epoch": 0.011058708733127337,
      "grad_norm": 0.7754510641098022,
      "learning_rate": 4.925739315689991e-06,
      "loss": 4.7688,
      "step": 17
    },
    {
      "epoch": 0.011709221011546592,
      "grad_norm": 0.5641795992851257,
      "learning_rate": 4.903154239845798e-06,
      "loss": 5.0063,
      "step": 18
    },
    {
      "epoch": 0.012359733289965848,
      "grad_norm": 0.5666624307632446,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 4.7559,
      "step": 19
    },
    {
      "epoch": 0.013010245568385103,
      "grad_norm": 0.5249921679496765,
      "learning_rate": 4.849231551964771e-06,
      "loss": 4.7812,
      "step": 20
    },
    {
      "epoch": 0.013660757846804358,
      "grad_norm": 0.6495589017868042,
      "learning_rate": 4.817959636416969e-06,
      "loss": 4.9568,
      "step": 21
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 0.6530317664146423,
      "learning_rate": 4.783863644106502e-06,
      "loss": 5.3396,
      "step": 22
    },
    {
      "epoch": 0.014961782403642869,
      "grad_norm": 0.7022749185562134,
      "learning_rate": 4.746985115747918e-06,
      "loss": 5.32,
      "step": 23
    },
    {
      "epoch": 0.015612294682062124,
      "grad_norm": 0.7745022773742676,
      "learning_rate": 4.707368982147318e-06,
      "loss": 5.2785,
      "step": 24
    },
    {
      "epoch": 0.01626280696048138,
      "grad_norm": 0.7991130352020264,
      "learning_rate": 4.665063509461098e-06,
      "loss": 5.1155,
      "step": 25
    },
    {
      "epoch": 0.016913319238900635,
      "grad_norm": 0.818338930606842,
      "learning_rate": 4.620120240391065e-06,
      "loss": 5.4624,
      "step": 26
    },
    {
      "epoch": 0.01756383151731989,
      "grad_norm": 0.8657534122467041,
      "learning_rate": 4.572593931387604e-06,
      "loss": 5.0129,
      "step": 27
    },
    {
      "epoch": 0.018214343795739146,
      "grad_norm": 0.87333083152771,
      "learning_rate": 4.522542485937369e-06,
      "loss": 5.3868,
      "step": 28
    },
    {
      "epoch": 0.0188648560741584,
      "grad_norm": 1.0244101285934448,
      "learning_rate": 4.470026884016805e-06,
      "loss": 5.9281,
      "step": 29
    },
    {
      "epoch": 0.019515368352577656,
      "grad_norm": 1.0960421562194824,
      "learning_rate": 4.415111107797445e-06,
      "loss": 5.1099,
      "step": 30
    },
    {
      "epoch": 0.02016588063099691,
      "grad_norm": 1.068715214729309,
      "learning_rate": 4.357862063693486e-06,
      "loss": 5.3573,
      "step": 31
    },
    {
      "epoch": 0.020816392909416167,
      "grad_norm": 1.0725743770599365,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 6.0611,
      "step": 32
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 1.251522183418274,
      "learning_rate": 4.236645926147493e-06,
      "loss": 5.9569,
      "step": 33
    },
    {
      "epoch": 0.022117417466254674,
      "grad_norm": 1.264089822769165,
      "learning_rate": 4.172826515897146e-06,
      "loss": 6.3243,
      "step": 34
    },
    {
      "epoch": 0.02276792974467393,
      "grad_norm": 1.2084214687347412,
      "learning_rate": 4.106969024216348e-06,
      "loss": 6.2985,
      "step": 35
    },
    {
      "epoch": 0.023418442023093185,
      "grad_norm": 1.3795757293701172,
      "learning_rate": 4.039153688314146e-06,
      "loss": 6.158,
      "step": 36
    },
    {
      "epoch": 0.02406895430151244,
      "grad_norm": 1.3586288690567017,
      "learning_rate": 3.969463130731183e-06,
      "loss": 5.9415,
      "step": 37
    },
    {
      "epoch": 0.024719466579931695,
      "grad_norm": 1.8889917135238647,
      "learning_rate": 3.897982258676867e-06,
      "loss": 6.4683,
      "step": 38
    },
    {
      "epoch": 0.02536997885835095,
      "grad_norm": 2.1334280967712402,
      "learning_rate": 3.824798160583012e-06,
      "loss": 7.9267,
      "step": 39
    },
    {
      "epoch": 0.026020491136770206,
      "grad_norm": 1.782041072845459,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 6.9762,
      "step": 40
    },
    {
      "epoch": 0.02667100341518946,
      "grad_norm": 1.85926353931427,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 7.9339,
      "step": 41
    },
    {
      "epoch": 0.027321515693608717,
      "grad_norm": 1.8683347702026367,
      "learning_rate": 3.595927866972694e-06,
      "loss": 7.0318,
      "step": 42
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 1.893679141998291,
      "learning_rate": 3.516841607689501e-06,
      "loss": 7.1298,
      "step": 43
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 2.0049362182617188,
      "learning_rate": 3.436516483539781e-06,
      "loss": 7.2029,
      "step": 44
    },
    {
      "epoch": 0.029273052528866483,
      "grad_norm": 3.3010072708129883,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 10.0037,
      "step": 45
    },
    {
      "epoch": 0.029923564807285738,
      "grad_norm": 2.9284486770629883,
      "learning_rate": 3.272542485937369e-06,
      "loss": 8.6325,
      "step": 46
    },
    {
      "epoch": 0.030574077085704993,
      "grad_norm": 3.9905970096588135,
      "learning_rate": 3.189093389542498e-06,
      "loss": 11.5896,
      "step": 47
    },
    {
      "epoch": 0.03122458936412425,
      "grad_norm": 6.702117443084717,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 13.1525,
      "step": 48
    },
    {
      "epoch": 0.0318751016425435,
      "grad_norm": 5.863316535949707,
      "learning_rate": 3.019779227044398e-06,
      "loss": 13.7784,
      "step": 49
    },
    {
      "epoch": 0.03252561392096276,
      "grad_norm": 13.9373197555542,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 24.6156,
      "step": 50
    },
    {
      "epoch": 0.03252561392096276,
      "eval_loss": 0.7435109615325928,
      "eval_runtime": 389.9826,
      "eval_samples_per_second": 6.639,
      "eval_steps_per_second": 1.662,
      "step": 50
    },
    {
      "epoch": 0.03317612619938201,
      "grad_norm": 0.48402392864227295,
      "learning_rate": 2.847932752400164e-06,
      "loss": 4.2489,
      "step": 51
    },
    {
      "epoch": 0.03382663847780127,
      "grad_norm": 0.5398579835891724,
      "learning_rate": 2.761321158169134e-06,
      "loss": 4.166,
      "step": 52
    },
    {
      "epoch": 0.03447715075622052,
      "grad_norm": 0.5588984489440918,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 4.6712,
      "step": 53
    },
    {
      "epoch": 0.03512766303463978,
      "grad_norm": 0.5224852561950684,
      "learning_rate": 2.587248741756253e-06,
      "loss": 4.4866,
      "step": 54
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 0.5074653029441833,
      "learning_rate": 2.5e-06,
      "loss": 4.466,
      "step": 55
    },
    {
      "epoch": 0.03642868759147829,
      "grad_norm": 0.5670197606086731,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 4.3119,
      "step": 56
    },
    {
      "epoch": 0.03707919986989754,
      "grad_norm": 0.4569515287876129,
      "learning_rate": 2.325608815639687e-06,
      "loss": 4.5278,
      "step": 57
    },
    {
      "epoch": 0.0377297121483168,
      "grad_norm": 0.5136495232582092,
      "learning_rate": 2.238678841830867e-06,
      "loss": 4.5103,
      "step": 58
    },
    {
      "epoch": 0.038380224426736054,
      "grad_norm": 0.45289337635040283,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 4.5161,
      "step": 59
    },
    {
      "epoch": 0.03903073670515531,
      "grad_norm": 0.5101237297058105,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 4.3636,
      "step": 60
    },
    {
      "epoch": 0.039681248983574564,
      "grad_norm": 0.4960824251174927,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 4.6382,
      "step": 61
    },
    {
      "epoch": 0.04033176126199382,
      "grad_norm": 0.47291213274002075,
      "learning_rate": 1.895195261000831e-06,
      "loss": 4.7356,
      "step": 62
    },
    {
      "epoch": 0.040982273540413075,
      "grad_norm": 0.5523029565811157,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 4.6053,
      "step": 63
    },
    {
      "epoch": 0.041632785818832334,
      "grad_norm": 0.4428810775279999,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 4.5437,
      "step": 64
    },
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 0.49818718433380127,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 4.8466,
      "step": 65
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 0.4763147234916687,
      "learning_rate": 1.56348351646022e-06,
      "loss": 4.5998,
      "step": 66
    },
    {
      "epoch": 0.043584322654090096,
      "grad_norm": 0.597857654094696,
      "learning_rate": 1.4831583923105e-06,
      "loss": 4.5964,
      "step": 67
    },
    {
      "epoch": 0.04423483493250935,
      "grad_norm": 0.5390750169754028,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 4.3763,
      "step": 68
    },
    {
      "epoch": 0.04488534721092861,
      "grad_norm": 0.49823203682899475,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 4.7298,
      "step": 69
    },
    {
      "epoch": 0.04553585948934786,
      "grad_norm": 0.5256410837173462,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 4.8487,
      "step": 70
    },
    {
      "epoch": 0.04618637176776712,
      "grad_norm": 0.5595061182975769,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 4.9873,
      "step": 71
    },
    {
      "epoch": 0.04683688404618637,
      "grad_norm": 0.6115620136260986,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 4.8716,
      "step": 72
    },
    {
      "epoch": 0.04748739632460563,
      "grad_norm": 0.601868212223053,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 4.8483,
      "step": 73
    },
    {
      "epoch": 0.04813790860302488,
      "grad_norm": 0.619591474533081,
      "learning_rate": 9.608463116858544e-07,
      "loss": 5.1136,
      "step": 74
    },
    {
      "epoch": 0.04878842088144414,
      "grad_norm": 0.7487257719039917,
      "learning_rate": 8.930309757836517e-07,
      "loss": 4.9936,
      "step": 75
    },
    {
      "epoch": 0.04943893315986339,
      "grad_norm": 0.6831351518630981,
      "learning_rate": 8.271734841028553e-07,
      "loss": 4.9526,
      "step": 76
    },
    {
      "epoch": 0.05008944543828265,
      "grad_norm": 0.7687312364578247,
      "learning_rate": 7.633540738525066e-07,
      "loss": 5.0725,
      "step": 77
    },
    {
      "epoch": 0.0507399577167019,
      "grad_norm": 0.7937861680984497,
      "learning_rate": 7.016504991533727e-07,
      "loss": 5.294,
      "step": 78
    },
    {
      "epoch": 0.05139046999512116,
      "grad_norm": 0.9356114268302917,
      "learning_rate": 6.421379363065142e-07,
      "loss": 5.6726,
      "step": 79
    },
    {
      "epoch": 0.05204098227354041,
      "grad_norm": 0.9393124580383301,
      "learning_rate": 5.848888922025553e-07,
      "loss": 5.3861,
      "step": 80
    },
    {
      "epoch": 0.05269149455195967,
      "grad_norm": 1.04855477809906,
      "learning_rate": 5.299731159831953e-07,
      "loss": 6.1938,
      "step": 81
    },
    {
      "epoch": 0.05334200683037892,
      "grad_norm": 1.0108082294464111,
      "learning_rate": 4.774575140626317e-07,
      "loss": 5.5263,
      "step": 82
    },
    {
      "epoch": 0.05399251910879818,
      "grad_norm": 0.9941501617431641,
      "learning_rate": 4.27406068612396e-07,
      "loss": 5.3024,
      "step": 83
    },
    {
      "epoch": 0.05464303138721743,
      "grad_norm": 1.0947118997573853,
      "learning_rate": 3.798797596089351e-07,
      "loss": 5.6406,
      "step": 84
    },
    {
      "epoch": 0.05529354366563669,
      "grad_norm": 1.3851187229156494,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 6.3249,
      "step": 85
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 1.4180490970611572,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 6.6054,
      "step": 86
    },
    {
      "epoch": 0.056594568222475196,
      "grad_norm": 1.4259532690048218,
      "learning_rate": 2.53014884252083e-07,
      "loss": 6.1053,
      "step": 87
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 1.4208811521530151,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 5.9681,
      "step": 88
    },
    {
      "epoch": 0.057895592779313707,
      "grad_norm": 1.4157319068908691,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 6.4869,
      "step": 89
    },
    {
      "epoch": 0.058546105057732965,
      "grad_norm": 1.6923154592514038,
      "learning_rate": 1.507684480352292e-07,
      "loss": 6.8299,
      "step": 90
    },
    {
      "epoch": 0.05919661733615222,
      "grad_norm": 1.7933100461959839,
      "learning_rate": 1.223587092621162e-07,
      "loss": 6.8221,
      "step": 91
    },
    {
      "epoch": 0.059847129614571476,
      "grad_norm": 1.8865070343017578,
      "learning_rate": 9.684576015420277e-08,
      "loss": 6.7431,
      "step": 92
    },
    {
      "epoch": 0.06049764189299073,
      "grad_norm": 2.5307703018188477,
      "learning_rate": 7.426068431000883e-08,
      "loss": 8.523,
      "step": 93
    },
    {
      "epoch": 0.06114815417140999,
      "grad_norm": 2.0570056438446045,
      "learning_rate": 5.463099816548578e-08,
      "loss": 7.3828,
      "step": 94
    },
    {
      "epoch": 0.06179866644982924,
      "grad_norm": 2.696568250656128,
      "learning_rate": 3.798061746947995e-08,
      "loss": 7.8743,
      "step": 95
    },
    {
      "epoch": 0.0624491787282485,
      "grad_norm": 4.576745510101318,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 10.2667,
      "step": 96
    },
    {
      "epoch": 0.06309969100666775,
      "grad_norm": 3.2011473178863525,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 9.303,
      "step": 97
    },
    {
      "epoch": 0.063750203285087,
      "grad_norm": 4.851830959320068,
      "learning_rate": 6.089874350439507e-09,
      "loss": 11.6186,
      "step": 98
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 5.677859783172607,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 14.1113,
      "step": 99
    },
    {
      "epoch": 0.06505122784192552,
      "grad_norm": 7.9092607498168945,
      "learning_rate": 0.0,
      "loss": 18.4214,
      "step": 100
    },
    {
      "epoch": 0.06505122784192552,
      "eval_loss": 0.7389546632766724,
      "eval_runtime": 389.1253,
      "eval_samples_per_second": 6.653,
      "eval_steps_per_second": 1.665,
      "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": 3.304045495399219e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}