{
  "best_metric": 2.1182491779327393,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.0081504702194357,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010031347962382446,
      "grad_norm": 0.5013210773468018,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.0579,
      "step": 1
    },
    {
      "epoch": 0.010031347962382446,
      "eval_loss": 2.4447879791259766,
      "eval_runtime": 49.2666,
      "eval_samples_per_second": 13.64,
      "eval_steps_per_second": 1.705,
      "step": 1
    },
    {
      "epoch": 0.02006269592476489,
      "grad_norm": 0.5867398381233215,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.1459,
      "step": 2
    },
    {
      "epoch": 0.030094043887147336,
      "grad_norm": 0.6160461902618408,
      "learning_rate": 1.5e-06,
      "loss": 2.1973,
      "step": 3
    },
    {
      "epoch": 0.04012539184952978,
      "grad_norm": 0.6387326717376709,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.2502,
      "step": 4
    },
    {
      "epoch": 0.050156739811912224,
      "grad_norm": 0.6501869559288025,
      "learning_rate": 2.5e-06,
      "loss": 2.2475,
      "step": 5
    },
    {
      "epoch": 0.06018808777429467,
      "grad_norm": 0.6972927451133728,
      "learning_rate": 3e-06,
      "loss": 2.3085,
      "step": 6
    },
    {
      "epoch": 0.07021943573667712,
      "grad_norm": 0.7163339853286743,
      "learning_rate": 3.5e-06,
      "loss": 2.2789,
      "step": 7
    },
    {
      "epoch": 0.08025078369905957,
      "grad_norm": 0.7239258885383606,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.2794,
      "step": 8
    },
    {
      "epoch": 0.090282131661442,
      "grad_norm": 0.7243937253952026,
      "learning_rate": 4.5e-06,
      "loss": 2.2982,
      "step": 9
    },
    {
      "epoch": 0.10031347962382445,
      "grad_norm": 0.7575347423553467,
      "learning_rate": 5e-06,
      "loss": 2.3438,
      "step": 10
    },
    {
      "epoch": 0.1103448275862069,
      "grad_norm": 0.7794107794761658,
      "learning_rate": 4.99847706754774e-06,
      "loss": 2.354,
      "step": 11
    },
    {
      "epoch": 0.12037617554858934,
      "grad_norm": 0.8005712628364563,
      "learning_rate": 4.993910125649561e-06,
      "loss": 2.3741,
      "step": 12
    },
    {
      "epoch": 0.1304075235109718,
      "grad_norm": 0.843438446521759,
      "learning_rate": 4.986304738420684e-06,
      "loss": 2.3853,
      "step": 13
    },
    {
      "epoch": 0.14043887147335424,
      "grad_norm": 0.8797963261604309,
      "learning_rate": 4.975670171853926e-06,
      "loss": 2.4064,
      "step": 14
    },
    {
      "epoch": 0.15047021943573669,
      "grad_norm": 0.9428530931472778,
      "learning_rate": 4.962019382530521e-06,
      "loss": 2.4542,
      "step": 15
    },
    {
      "epoch": 0.16050156739811913,
      "grad_norm": 0.9352163076400757,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 2.4665,
      "step": 16
    },
    {
      "epoch": 0.17053291536050158,
      "grad_norm": 1.0022633075714111,
      "learning_rate": 4.925739315689991e-06,
      "loss": 2.4377,
      "step": 17
    },
    {
      "epoch": 0.180564263322884,
      "grad_norm": 1.0534271001815796,
      "learning_rate": 4.903154239845798e-06,
      "loss": 2.5266,
      "step": 18
    },
    {
      "epoch": 0.19059561128526645,
      "grad_norm": 1.0811848640441895,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 2.5807,
      "step": 19
    },
    {
      "epoch": 0.2006269592476489,
      "grad_norm": 1.1316111087799072,
      "learning_rate": 4.849231551964771e-06,
      "loss": 2.5902,
      "step": 20
    },
    {
      "epoch": 0.21065830721003134,
      "grad_norm": 1.189561367034912,
      "learning_rate": 4.817959636416969e-06,
      "loss": 2.6038,
      "step": 21
    },
    {
      "epoch": 0.2206896551724138,
      "grad_norm": 1.2571277618408203,
      "learning_rate": 4.783863644106502e-06,
      "loss": 2.7178,
      "step": 22
    },
    {
      "epoch": 0.23072100313479624,
      "grad_norm": 1.4015403985977173,
      "learning_rate": 4.746985115747918e-06,
      "loss": 2.8131,
      "step": 23
    },
    {
      "epoch": 0.24075235109717869,
      "grad_norm": 1.7429771423339844,
      "learning_rate": 4.707368982147318e-06,
      "loss": 3.1713,
      "step": 24
    },
    {
      "epoch": 0.2507836990595611,
      "grad_norm": 0.6240499019622803,
      "learning_rate": 4.665063509461098e-06,
      "loss": 2.0797,
      "step": 25
    },
    {
      "epoch": 0.2608150470219436,
      "grad_norm": 0.7012020349502563,
      "learning_rate": 4.620120240391065e-06,
      "loss": 2.0826,
      "step": 26
    },
    {
      "epoch": 0.270846394984326,
      "grad_norm": 0.7514374256134033,
      "learning_rate": 4.572593931387604e-06,
      "loss": 2.1961,
      "step": 27
    },
    {
      "epoch": 0.2808777429467085,
      "grad_norm": 0.7977500557899475,
      "learning_rate": 4.522542485937369e-06,
      "loss": 2.153,
      "step": 28
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.7912695407867432,
      "learning_rate": 4.470026884016805e-06,
      "loss": 2.176,
      "step": 29
    },
    {
      "epoch": 0.30094043887147337,
      "grad_norm": 0.8330540060997009,
      "learning_rate": 4.415111107797445e-06,
      "loss": 2.1654,
      "step": 30
    },
    {
      "epoch": 0.3109717868338558,
      "grad_norm": 0.8662275075912476,
      "learning_rate": 4.357862063693486e-06,
      "loss": 2.1926,
      "step": 31
    },
    {
      "epoch": 0.32100313479623827,
      "grad_norm": 0.8899848461151123,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 2.197,
      "step": 32
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 0.963080883026123,
      "learning_rate": 4.236645926147493e-06,
      "loss": 2.3028,
      "step": 33
    },
    {
      "epoch": 0.34106583072100316,
      "grad_norm": 0.9748149514198303,
      "learning_rate": 4.172826515897146e-06,
      "loss": 2.2829,
      "step": 34
    },
    {
      "epoch": 0.3510971786833856,
      "grad_norm": 0.9774594306945801,
      "learning_rate": 4.106969024216348e-06,
      "loss": 2.272,
      "step": 35
    },
    {
      "epoch": 0.361128526645768,
      "grad_norm": 0.9856119155883789,
      "learning_rate": 4.039153688314146e-06,
      "loss": 2.2706,
      "step": 36
    },
    {
      "epoch": 0.3711598746081505,
      "grad_norm": 1.0438799858093262,
      "learning_rate": 3.969463130731183e-06,
      "loss": 2.3098,
      "step": 37
    },
    {
      "epoch": 0.3811912225705329,
      "grad_norm": 1.0557576417922974,
      "learning_rate": 3.897982258676867e-06,
      "loss": 2.236,
      "step": 38
    },
    {
      "epoch": 0.39122257053291537,
      "grad_norm": 1.1337238550186157,
      "learning_rate": 3.824798160583012e-06,
      "loss": 2.3059,
      "step": 39
    },
    {
      "epoch": 0.4012539184952978,
      "grad_norm": 1.1216912269592285,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 2.3342,
      "step": 40
    },
    {
      "epoch": 0.41128526645768027,
      "grad_norm": 1.1198524236679077,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 2.32,
      "step": 41
    },
    {
      "epoch": 0.4213166144200627,
      "grad_norm": 1.182173252105713,
      "learning_rate": 3.595927866972694e-06,
      "loss": 2.4223,
      "step": 42
    },
    {
      "epoch": 0.43134796238244516,
      "grad_norm": 1.2724802494049072,
      "learning_rate": 3.516841607689501e-06,
      "loss": 2.4149,
      "step": 43
    },
    {
      "epoch": 0.4413793103448276,
      "grad_norm": 1.2972792387008667,
      "learning_rate": 3.436516483539781e-06,
      "loss": 2.4336,
      "step": 44
    },
    {
      "epoch": 0.45141065830721006,
      "grad_norm": 1.3523412942886353,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 2.4776,
      "step": 45
    },
    {
      "epoch": 0.4614420062695925,
      "grad_norm": 1.4430625438690186,
      "learning_rate": 3.272542485937369e-06,
      "loss": 2.5075,
      "step": 46
    },
    {
      "epoch": 0.4714733542319749,
      "grad_norm": 1.5807729959487915,
      "learning_rate": 3.189093389542498e-06,
      "loss": 2.6176,
      "step": 47
    },
    {
      "epoch": 0.48150470219435737,
      "grad_norm": 1.8612488508224487,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 2.9744,
      "step": 48
    },
    {
      "epoch": 0.4915360501567398,
      "grad_norm": 0.6271159648895264,
      "learning_rate": 3.019779227044398e-06,
      "loss": 1.9217,
      "step": 49
    },
    {
      "epoch": 0.5015673981191222,
      "grad_norm": 0.7170687317848206,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 2.0208,
      "step": 50
    },
    {
      "epoch": 0.5015673981191222,
      "eval_loss": 2.2289443016052246,
      "eval_runtime": 49.8574,
      "eval_samples_per_second": 13.478,
      "eval_steps_per_second": 1.685,
      "step": 50
    },
    {
      "epoch": 0.5115987460815047,
      "grad_norm": 0.7622096538543701,
      "learning_rate": 2.847932752400164e-06,
      "loss": 2.0219,
      "step": 51
    },
    {
      "epoch": 0.5216300940438872,
      "grad_norm": 0.7824783325195312,
      "learning_rate": 2.761321158169134e-06,
      "loss": 2.0423,
      "step": 52
    },
    {
      "epoch": 0.5316614420062696,
      "grad_norm": 0.8110308647155762,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 2.0342,
      "step": 53
    },
    {
      "epoch": 0.541692789968652,
      "grad_norm": 0.8110449314117432,
      "learning_rate": 2.587248741756253e-06,
      "loss": 2.0627,
      "step": 54
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.8489147424697876,
      "learning_rate": 2.5e-06,
      "loss": 2.0647,
      "step": 55
    },
    {
      "epoch": 0.561755485893417,
      "grad_norm": 0.835385799407959,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 2.0835,
      "step": 56
    },
    {
      "epoch": 0.5717868338557994,
      "grad_norm": 0.8666210770606995,
      "learning_rate": 2.325608815639687e-06,
      "loss": 2.0915,
      "step": 57
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.893517255783081,
      "learning_rate": 2.238678841830867e-06,
      "loss": 2.122,
      "step": 58
    },
    {
      "epoch": 0.5918495297805643,
      "grad_norm": 0.9489184617996216,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 2.1537,
      "step": 59
    },
    {
      "epoch": 0.6018808777429467,
      "grad_norm": 0.9988653659820557,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 2.1574,
      "step": 60
    },
    {
      "epoch": 0.6119122257053291,
      "grad_norm": 0.9343753457069397,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 2.1283,
      "step": 61
    },
    {
      "epoch": 0.6219435736677116,
      "grad_norm": 0.9588767290115356,
      "learning_rate": 1.895195261000831e-06,
      "loss": 2.0984,
      "step": 62
    },
    {
      "epoch": 0.631974921630094,
      "grad_norm": 1.0283074378967285,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 2.1398,
      "step": 63
    },
    {
      "epoch": 0.6420062695924765,
      "grad_norm": 1.0181758403778076,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 2.1759,
      "step": 64
    },
    {
      "epoch": 0.6520376175548589,
      "grad_norm": 1.0908583402633667,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 2.2327,
      "step": 65
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 1.1794666051864624,
      "learning_rate": 1.56348351646022e-06,
      "loss": 2.2237,
      "step": 66
    },
    {
      "epoch": 0.6721003134796238,
      "grad_norm": 1.2034351825714111,
      "learning_rate": 1.4831583923105e-06,
      "loss": 2.2669,
      "step": 67
    },
    {
      "epoch": 0.6821316614420063,
      "grad_norm": 1.1914037466049194,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 2.3433,
      "step": 68
    },
    {
      "epoch": 0.6921630094043887,
      "grad_norm": 1.2532089948654175,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 2.2484,
      "step": 69
    },
    {
      "epoch": 0.7021943573667712,
      "grad_norm": 1.376366376876831,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 2.3746,
      "step": 70
    },
    {
      "epoch": 0.7122257053291536,
      "grad_norm": 1.4628711938858032,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 2.4658,
      "step": 71
    },
    {
      "epoch": 0.722257053291536,
      "grad_norm": 1.7385092973709106,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 2.7303,
      "step": 72
    },
    {
      "epoch": 0.7322884012539185,
      "grad_norm": 0.5511379837989807,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 1.9222,
      "step": 73
    },
    {
      "epoch": 0.742319749216301,
      "grad_norm": 0.6141335964202881,
      "learning_rate": 9.608463116858544e-07,
      "loss": 1.9357,
      "step": 74
    },
    {
      "epoch": 0.7523510971786834,
      "grad_norm": 0.6731216311454773,
      "learning_rate": 8.930309757836517e-07,
      "loss": 1.9706,
      "step": 75
    },
    {
      "epoch": 0.7623824451410658,
      "grad_norm": 0.6861745119094849,
      "learning_rate": 8.271734841028553e-07,
      "loss": 1.9597,
      "step": 76
    },
    {
      "epoch": 0.7724137931034483,
      "grad_norm": 0.7158825397491455,
      "learning_rate": 7.633540738525066e-07,
      "loss": 1.9872,
      "step": 77
    },
    {
      "epoch": 0.7824451410658307,
      "grad_norm": 0.7349813580513,
      "learning_rate": 7.016504991533727e-07,
      "loss": 1.971,
      "step": 78
    },
    {
      "epoch": 0.7924764890282132,
      "grad_norm": 0.7533213496208191,
      "learning_rate": 6.421379363065142e-07,
      "loss": 1.987,
      "step": 79
    },
    {
      "epoch": 0.8025078369905956,
      "grad_norm": 0.8110781908035278,
      "learning_rate": 5.848888922025553e-07,
      "loss": 2.0393,
      "step": 80
    },
    {
      "epoch": 0.812539184952978,
      "grad_norm": 0.8404735922813416,
      "learning_rate": 5.299731159831953e-07,
      "loss": 2.0574,
      "step": 81
    },
    {
      "epoch": 0.8225705329153605,
      "grad_norm": 0.8332526087760925,
      "learning_rate": 4.774575140626317e-07,
      "loss": 2.0136,
      "step": 82
    },
    {
      "epoch": 0.8326018808777429,
      "grad_norm": 0.8636597394943237,
      "learning_rate": 4.27406068612396e-07,
      "loss": 2.0972,
      "step": 83
    },
    {
      "epoch": 0.8426332288401254,
      "grad_norm": 0.9107650518417358,
      "learning_rate": 3.798797596089351e-07,
      "loss": 2.0861,
      "step": 84
    },
    {
      "epoch": 0.8526645768025078,
      "grad_norm": 0.9134276509284973,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 2.1062,
      "step": 85
    },
    {
      "epoch": 0.8626959247648903,
      "grad_norm": 0.9543719291687012,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 2.1049,
      "step": 86
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.9964223504066467,
      "learning_rate": 2.53014884252083e-07,
      "loss": 2.1389,
      "step": 87
    },
    {
      "epoch": 0.8827586206896552,
      "grad_norm": 0.9783273935317993,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 2.1203,
      "step": 88
    },
    {
      "epoch": 0.8927899686520376,
      "grad_norm": 1.0522716045379639,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 2.1538,
      "step": 89
    },
    {
      "epoch": 0.9028213166144201,
      "grad_norm": 1.0797299146652222,
      "learning_rate": 1.507684480352292e-07,
      "loss": 2.1707,
      "step": 90
    },
    {
      "epoch": 0.9128526645768025,
      "grad_norm": 1.0894622802734375,
      "learning_rate": 1.223587092621162e-07,
      "loss": 2.1841,
      "step": 91
    },
    {
      "epoch": 0.922884012539185,
      "grad_norm": 1.1516773700714111,
      "learning_rate": 9.684576015420277e-08,
      "loss": 2.2291,
      "step": 92
    },
    {
      "epoch": 0.9329153605015674,
      "grad_norm": 1.241176962852478,
      "learning_rate": 7.426068431000883e-08,
      "loss": 2.2777,
      "step": 93
    },
    {
      "epoch": 0.9429467084639498,
      "grad_norm": 1.3007570505142212,
      "learning_rate": 5.463099816548578e-08,
      "loss": 2.33,
      "step": 94
    },
    {
      "epoch": 0.9529780564263323,
      "grad_norm": 1.4791982173919678,
      "learning_rate": 3.798061746947995e-08,
      "loss": 2.4737,
      "step": 95
    },
    {
      "epoch": 0.9630094043887147,
      "grad_norm": 1.7149653434753418,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 2.7394,
      "step": 96
    },
    {
      "epoch": 0.9730407523510972,
      "grad_norm": 0.6517561078071594,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 1.9604,
      "step": 97
    },
    {
      "epoch": 0.9830721003134796,
      "grad_norm": 0.7938938736915588,
      "learning_rate": 6.089874350439507e-09,
      "loss": 2.0268,
      "step": 98
    },
    {
      "epoch": 0.993103448275862,
      "grad_norm": 1.0271896123886108,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 2.1866,
      "step": 99
    },
    {
      "epoch": 1.0081504702194357,
      "grad_norm": 1.5798444747924805,
      "learning_rate": 0.0,
      "loss": 3.9263,
      "step": 100
    },
    {
      "epoch": 1.0081504702194357,
      "eval_loss": 2.1182491779327393,
      "eval_runtime": 49.8296,
      "eval_samples_per_second": 13.486,
      "eval_steps_per_second": 1.686,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.305280287997952e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}