{
  "best_metric": 1.0859266519546509,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.011229803899549404,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.614901949774702e-05,
      "grad_norm": 1.6964712142944336,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.8367,
      "step": 1
    },
    {
      "epoch": 5.614901949774702e-05,
      "eval_loss": 2.332831859588623,
      "eval_runtime": 2103.2828,
      "eval_samples_per_second": 14.261,
      "eval_steps_per_second": 7.131,
      "step": 1
    },
    {
      "epoch": 0.00011229803899549404,
      "grad_norm": 2.1738104820251465,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.0045,
      "step": 2
    },
    {
      "epoch": 0.00016844705849324105,
      "grad_norm": 1.8070042133331299,
      "learning_rate": 1e-05,
      "loss": 1.9568,
      "step": 3
    },
    {
      "epoch": 0.00022459607799098807,
      "grad_norm": 2.225158214569092,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.1097,
      "step": 4
    },
    {
      "epoch": 0.0002807450974887351,
      "grad_norm": 2.132608413696289,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.1125,
      "step": 5
    },
    {
      "epoch": 0.0003368941169864821,
      "grad_norm": 1.9958487749099731,
      "learning_rate": 2e-05,
      "loss": 2.0075,
      "step": 6
    },
    {
      "epoch": 0.0003930431364842291,
      "grad_norm": 1.7949007749557495,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.9498,
      "step": 7
    },
    {
      "epoch": 0.00044919215598197615,
      "grad_norm": 1.705701231956482,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.9204,
      "step": 8
    },
    {
      "epoch": 0.0005053411754797232,
      "grad_norm": 1.5467288494110107,
      "learning_rate": 3e-05,
      "loss": 1.8477,
      "step": 9
    },
    {
      "epoch": 0.0005614901949774703,
      "grad_norm": 1.6063212156295776,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8923,
      "step": 10
    },
    {
      "epoch": 0.0006176392144752172,
      "grad_norm": 1.7272061109542847,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.7052,
      "step": 11
    },
    {
      "epoch": 0.0006737882339729642,
      "grad_norm": 1.8120886087417603,
      "learning_rate": 4e-05,
      "loss": 1.634,
      "step": 12
    },
    {
      "epoch": 0.0007299372534707113,
      "grad_norm": 2.0960566997528076,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 1.5591,
      "step": 13
    },
    {
      "epoch": 0.0007860862729684582,
      "grad_norm": 1.6172031164169312,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.5971,
      "step": 14
    },
    {
      "epoch": 0.0008422352924662053,
      "grad_norm": 1.3660484552383423,
      "learning_rate": 5e-05,
      "loss": 1.4006,
      "step": 15
    },
    {
      "epoch": 0.0008983843119639523,
      "grad_norm": 1.2967218160629272,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.4234,
      "step": 16
    },
    {
      "epoch": 0.0009545333314616994,
      "grad_norm": 1.1410720348358154,
      "learning_rate": 5.666666666666667e-05,
      "loss": 1.387,
      "step": 17
    },
    {
      "epoch": 0.0010106823509594463,
      "grad_norm": 0.9723636507987976,
      "learning_rate": 6e-05,
      "loss": 1.2976,
      "step": 18
    },
    {
      "epoch": 0.0010668313704571934,
      "grad_norm": 1.0372251272201538,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.4022,
      "step": 19
    },
    {
      "epoch": 0.0011229803899549405,
      "grad_norm": 1.0744377374649048,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2579,
      "step": 20
    },
    {
      "epoch": 0.0011791294094526874,
      "grad_norm": 0.9931140542030334,
      "learning_rate": 7e-05,
      "loss": 1.3209,
      "step": 21
    },
    {
      "epoch": 0.0012352784289504344,
      "grad_norm": 0.9062037467956543,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.3623,
      "step": 22
    },
    {
      "epoch": 0.0012914274484481815,
      "grad_norm": 0.9782098531723022,
      "learning_rate": 7.666666666666667e-05,
      "loss": 1.2306,
      "step": 23
    },
    {
      "epoch": 0.0013475764679459284,
      "grad_norm": 0.9081342816352844,
      "learning_rate": 8e-05,
      "loss": 1.2469,
      "step": 24
    },
    {
      "epoch": 0.0014037254874436755,
      "grad_norm": 0.8905002474784851,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2408,
      "step": 25
    },
    {
      "epoch": 0.0014598745069414225,
      "grad_norm": 0.8712568283081055,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.2736,
      "step": 26
    },
    {
      "epoch": 0.0015160235264391696,
      "grad_norm": 0.8708600401878357,
      "learning_rate": 9e-05,
      "loss": 1.3103,
      "step": 27
    },
    {
      "epoch": 0.0015721725459369165,
      "grad_norm": 0.8328787684440613,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.1652,
      "step": 28
    },
    {
      "epoch": 0.0016283215654346636,
      "grad_norm": 0.9395551681518555,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.2507,
      "step": 29
    },
    {
      "epoch": 0.0016844705849324106,
      "grad_norm": 0.833618700504303,
      "learning_rate": 0.0001,
      "loss": 1.2448,
      "step": 30
    },
    {
      "epoch": 0.0017406196044301577,
      "grad_norm": 0.786113440990448,
      "learning_rate": 9.999146252290264e-05,
      "loss": 1.1294,
      "step": 31
    },
    {
      "epoch": 0.0017967686239279046,
      "grad_norm": 0.7803535461425781,
      "learning_rate": 9.996585300715116e-05,
      "loss": 1.3006,
      "step": 32
    },
    {
      "epoch": 0.0018529176434256517,
      "grad_norm": 0.8093225359916687,
      "learning_rate": 9.99231801983717e-05,
      "loss": 1.2727,
      "step": 33
    },
    {
      "epoch": 0.0019090666629233987,
      "grad_norm": 0.8416083455085754,
      "learning_rate": 9.986345866928941e-05,
      "loss": 1.2161,
      "step": 34
    },
    {
      "epoch": 0.001965215682421146,
      "grad_norm": 0.808966338634491,
      "learning_rate": 9.978670881475172e-05,
      "loss": 1.226,
      "step": 35
    },
    {
      "epoch": 0.0020213647019188927,
      "grad_norm": 0.8698236346244812,
      "learning_rate": 9.96929568447637e-05,
      "loss": 1.2468,
      "step": 36
    },
    {
      "epoch": 0.0020775137214166395,
      "grad_norm": 0.8239580392837524,
      "learning_rate": 9.958223477553714e-05,
      "loss": 1.1281,
      "step": 37
    },
    {
      "epoch": 0.002133662740914387,
      "grad_norm": 0.8561798334121704,
      "learning_rate": 9.94545804185573e-05,
      "loss": 1.2069,
      "step": 38
    },
    {
      "epoch": 0.0021898117604121337,
      "grad_norm": 0.801845133304596,
      "learning_rate": 9.931003736767013e-05,
      "loss": 1.1058,
      "step": 39
    },
    {
      "epoch": 0.002245960779909881,
      "grad_norm": 0.7623407244682312,
      "learning_rate": 9.91486549841951e-05,
      "loss": 1.0845,
      "step": 40
    },
    {
      "epoch": 0.002302109799407628,
      "grad_norm": 0.8105125427246094,
      "learning_rate": 9.89704883800683e-05,
      "loss": 1.1078,
      "step": 41
    },
    {
      "epoch": 0.0023582588189053747,
      "grad_norm": 0.7941719889640808,
      "learning_rate": 9.877559839902184e-05,
      "loss": 1.1488,
      "step": 42
    },
    {
      "epoch": 0.002414407838403122,
      "grad_norm": 0.7803497314453125,
      "learning_rate": 9.85640515958057e-05,
      "loss": 1.0903,
      "step": 43
    },
    {
      "epoch": 0.002470556857900869,
      "grad_norm": 0.8070552945137024,
      "learning_rate": 9.833592021345937e-05,
      "loss": 1.1027,
      "step": 44
    },
    {
      "epoch": 0.0025267058773986158,
      "grad_norm": 0.8156814575195312,
      "learning_rate": 9.809128215864097e-05,
      "loss": 1.0472,
      "step": 45
    },
    {
      "epoch": 0.002582854896896363,
      "grad_norm": 0.8596224188804626,
      "learning_rate": 9.783022097502204e-05,
      "loss": 1.1419,
      "step": 46
    },
    {
      "epoch": 0.00263900391639411,
      "grad_norm": 0.989962100982666,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0993,
      "step": 47
    },
    {
      "epoch": 0.0026951529358918568,
      "grad_norm": 0.9050401449203491,
      "learning_rate": 9.725919140804099e-05,
      "loss": 1.0727,
      "step": 48
    },
    {
      "epoch": 0.002751301955389604,
      "grad_norm": 0.9351814985275269,
      "learning_rate": 9.694941803075283e-05,
      "loss": 1.068,
      "step": 49
    },
    {
      "epoch": 0.002807450974887351,
      "grad_norm": 1.1098612546920776,
      "learning_rate": 9.662361147021779e-05,
      "loss": 1.0088,
      "step": 50
    },
    {
      "epoch": 0.002807450974887351,
      "eval_loss": 1.2799263000488281,
      "eval_runtime": 2107.8009,
      "eval_samples_per_second": 14.23,
      "eval_steps_per_second": 7.115,
      "step": 50
    },
    {
      "epoch": 0.0028635999943850982,
      "grad_norm": 1.7174652814865112,
      "learning_rate": 9.628188298907782e-05,
      "loss": 1.4528,
      "step": 51
    },
    {
      "epoch": 0.002919749013882845,
      "grad_norm": 1.5406450033187866,
      "learning_rate": 9.592434928729616e-05,
      "loss": 1.4099,
      "step": 52
    },
    {
      "epoch": 0.002975898033380592,
      "grad_norm": 1.2001056671142578,
      "learning_rate": 9.555113246230442e-05,
      "loss": 1.3917,
      "step": 53
    },
    {
      "epoch": 0.0030320470528783392,
      "grad_norm": 0.9413912296295166,
      "learning_rate": 9.516235996730645e-05,
      "loss": 1.2862,
      "step": 54
    },
    {
      "epoch": 0.003088196072376086,
      "grad_norm": 0.6574397087097168,
      "learning_rate": 9.475816456775313e-05,
      "loss": 1.2614,
      "step": 55
    },
    {
      "epoch": 0.003144345091873833,
      "grad_norm": 0.6218005418777466,
      "learning_rate": 9.43386842960031e-05,
      "loss": 1.2038,
      "step": 56
    },
    {
      "epoch": 0.0032004941113715803,
      "grad_norm": 0.7471184730529785,
      "learning_rate": 9.39040624041849e-05,
      "loss": 1.1666,
      "step": 57
    },
    {
      "epoch": 0.003256643130869327,
      "grad_norm": 0.7934604287147522,
      "learning_rate": 9.345444731527642e-05,
      "loss": 1.2472,
      "step": 58
    },
    {
      "epoch": 0.0033127921503670744,
      "grad_norm": 0.8308062553405762,
      "learning_rate": 9.298999257241863e-05,
      "loss": 1.2442,
      "step": 59
    },
    {
      "epoch": 0.0033689411698648213,
      "grad_norm": 0.6573333740234375,
      "learning_rate": 9.251085678648072e-05,
      "loss": 1.1986,
      "step": 60
    },
    {
      "epoch": 0.003425090189362568,
      "grad_norm": 0.6570683717727661,
      "learning_rate": 9.201720358189464e-05,
      "loss": 1.2302,
      "step": 61
    },
    {
      "epoch": 0.0034812392088603154,
      "grad_norm": 0.6069157719612122,
      "learning_rate": 9.150920154077754e-05,
      "loss": 1.1475,
      "step": 62
    },
    {
      "epoch": 0.0035373882283580623,
      "grad_norm": 0.600216269493103,
      "learning_rate": 9.098702414536107e-05,
      "loss": 1.102,
      "step": 63
    },
    {
      "epoch": 0.003593537247855809,
      "grad_norm": 0.6119481921195984,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1455,
      "step": 64
    },
    {
      "epoch": 0.0036496862673535565,
      "grad_norm": 0.6701284646987915,
      "learning_rate": 8.9900861364012e-05,
      "loss": 1.192,
      "step": 65
    },
    {
      "epoch": 0.0037058352868513033,
      "grad_norm": 0.6195027828216553,
      "learning_rate": 8.933724690167417e-05,
      "loss": 1.1548,
      "step": 66
    },
    {
      "epoch": 0.00376198430634905,
      "grad_norm": 0.6576624512672424,
      "learning_rate": 8.876019880555649e-05,
      "loss": 1.23,
      "step": 67
    },
    {
      "epoch": 0.0038181333258467975,
      "grad_norm": 0.6199018955230713,
      "learning_rate": 8.816991413705516e-05,
      "loss": 1.085,
      "step": 68
    },
    {
      "epoch": 0.0038742823453445444,
      "grad_norm": 0.6421352624893188,
      "learning_rate": 8.756659447784368e-05,
      "loss": 1.1397,
      "step": 69
    },
    {
      "epoch": 0.003930431364842292,
      "grad_norm": 0.7040902376174927,
      "learning_rate": 8.695044586103296e-05,
      "loss": 1.1982,
      "step": 70
    },
    {
      "epoch": 0.003986580384340038,
      "grad_norm": 0.6545359492301941,
      "learning_rate": 8.632167870081121e-05,
      "loss": 1.1224,
      "step": 71
    },
    {
      "epoch": 0.004042729403837785,
      "grad_norm": 0.7151196002960205,
      "learning_rate": 8.568050772058762e-05,
      "loss": 1.1129,
      "step": 72
    },
    {
      "epoch": 0.004098878423335533,
      "grad_norm": 0.6587552428245544,
      "learning_rate": 8.502715187966455e-05,
      "loss": 1.1292,
      "step": 73
    },
    {
      "epoch": 0.004155027442833279,
      "grad_norm": 0.6608380079269409,
      "learning_rate": 8.436183429846313e-05,
      "loss": 1.124,
      "step": 74
    },
    {
      "epoch": 0.004211176462331026,
      "grad_norm": 0.6702746152877808,
      "learning_rate": 8.368478218232787e-05,
      "loss": 1.1656,
      "step": 75
    },
    {
      "epoch": 0.004267325481828774,
      "grad_norm": 0.6599065661430359,
      "learning_rate": 8.299622674393614e-05,
      "loss": 1.1543,
      "step": 76
    },
    {
      "epoch": 0.004323474501326521,
      "grad_norm": 0.6634683012962341,
      "learning_rate": 8.229640312433937e-05,
      "loss": 1.193,
      "step": 77
    },
    {
      "epoch": 0.004379623520824267,
      "grad_norm": 0.683447539806366,
      "learning_rate": 8.158555031266254e-05,
      "loss": 1.1215,
      "step": 78
    },
    {
      "epoch": 0.004435772540322015,
      "grad_norm": 0.6692266464233398,
      "learning_rate": 8.086391106448965e-05,
      "loss": 1.0958,
      "step": 79
    },
    {
      "epoch": 0.004491921559819762,
      "grad_norm": 0.6918296813964844,
      "learning_rate": 8.013173181896283e-05,
      "loss": 1.2255,
      "step": 80
    },
    {
      "epoch": 0.0045480705793175084,
      "grad_norm": 0.6787101626396179,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1807,
      "step": 81
    },
    {
      "epoch": 0.004604219598815256,
      "grad_norm": 0.7259939908981323,
      "learning_rate": 7.863675700402526e-05,
      "loss": 1.1612,
      "step": 82
    },
    {
      "epoch": 0.004660368618313003,
      "grad_norm": 0.6921144723892212,
      "learning_rate": 7.787447196714427e-05,
      "loss": 1.1331,
      "step": 83
    },
    {
      "epoch": 0.0047165176378107495,
      "grad_norm": 0.7044004797935486,
      "learning_rate": 7.710266782362247e-05,
      "loss": 1.1469,
      "step": 84
    },
    {
      "epoch": 0.004772666657308497,
      "grad_norm": 0.7107269763946533,
      "learning_rate": 7.63216081438678e-05,
      "loss": 1.2156,
      "step": 85
    },
    {
      "epoch": 0.004828815676806244,
      "grad_norm": 0.7129175662994385,
      "learning_rate": 7.553155965904535e-05,
      "loss": 1.118,
      "step": 86
    },
    {
      "epoch": 0.0048849646963039905,
      "grad_norm": 0.6944028735160828,
      "learning_rate": 7.473279216998895e-05,
      "loss": 1.1684,
      "step": 87
    },
    {
      "epoch": 0.004941113715801738,
      "grad_norm": 0.6979909539222717,
      "learning_rate": 7.392557845506432e-05,
      "loss": 1.1503,
      "step": 88
    },
    {
      "epoch": 0.004997262735299485,
      "grad_norm": 0.6969708800315857,
      "learning_rate": 7.311019417701566e-05,
      "loss": 1.0991,
      "step": 89
    },
    {
      "epoch": 0.0050534117547972315,
      "grad_norm": 0.7195575833320618,
      "learning_rate": 7.228691778882693e-05,
      "loss": 1.1541,
      "step": 90
    },
    {
      "epoch": 0.005109560774294979,
      "grad_norm": 0.7229387164115906,
      "learning_rate": 7.145603043863045e-05,
      "loss": 1.0439,
      "step": 91
    },
    {
      "epoch": 0.005165709793792726,
      "grad_norm": 0.7308394908905029,
      "learning_rate": 7.061781587369519e-05,
      "loss": 1.1037,
      "step": 92
    },
    {
      "epoch": 0.0052218588132904725,
      "grad_norm": 0.7165358662605286,
      "learning_rate": 6.977256034352712e-05,
      "loss": 1.0528,
      "step": 93
    },
    {
      "epoch": 0.00527800783278822,
      "grad_norm": 0.7242848873138428,
      "learning_rate": 6.892055250211552e-05,
      "loss": 1.0637,
      "step": 94
    },
    {
      "epoch": 0.005334156852285967,
      "grad_norm": 0.7282512784004211,
      "learning_rate": 6.806208330935766e-05,
      "loss": 1.0407,
      "step": 95
    },
    {
      "epoch": 0.0053903058717837135,
      "grad_norm": 0.7488335967063904,
      "learning_rate": 6.719744593169641e-05,
      "loss": 1.0557,
      "step": 96
    },
    {
      "epoch": 0.005446454891281461,
      "grad_norm": 0.8261488676071167,
      "learning_rate": 6.632693564200416e-05,
      "loss": 1.1658,
      "step": 97
    },
    {
      "epoch": 0.005502603910779208,
      "grad_norm": 0.7976979613304138,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0287,
      "step": 98
    },
    {
      "epoch": 0.005558752930276955,
      "grad_norm": 0.8135994076728821,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.9347,
      "step": 99
    },
    {
      "epoch": 0.005614901949774702,
      "grad_norm": 0.9864936470985413,
      "learning_rate": 6.368314950360415e-05,
      "loss": 1.0265,
      "step": 100
    },
    {
      "epoch": 0.005614901949774702,
      "eval_loss": 1.1527422666549683,
      "eval_runtime": 2109.9145,
      "eval_samples_per_second": 14.216,
      "eval_steps_per_second": 7.108,
      "step": 100
    },
    {
      "epoch": 0.005671050969272449,
      "grad_norm": 0.9625142216682434,
      "learning_rate": 6.279213887972179e-05,
      "loss": 1.2661,
      "step": 101
    },
    {
      "epoch": 0.0057271999887701965,
      "grad_norm": 0.8259492516517639,
      "learning_rate": 6.189675975213094e-05,
      "loss": 1.183,
      "step": 102
    },
    {
      "epoch": 0.005783349008267943,
      "grad_norm": 0.7474063038825989,
      "learning_rate": 6.099731789198344e-05,
      "loss": 1.1909,
      "step": 103
    },
    {
      "epoch": 0.00583949802776569,
      "grad_norm": 0.6665073037147522,
      "learning_rate": 6.009412045785051e-05,
      "loss": 1.1906,
      "step": 104
    },
    {
      "epoch": 0.0058956470472634375,
      "grad_norm": 0.5617001056671143,
      "learning_rate": 5.918747589082853e-05,
      "loss": 1.1469,
      "step": 105
    },
    {
      "epoch": 0.005951796066761184,
      "grad_norm": 0.5758078694343567,
      "learning_rate": 5.82776938092065e-05,
      "loss": 1.1253,
      "step": 106
    },
    {
      "epoch": 0.006007945086258931,
      "grad_norm": 0.5974460244178772,
      "learning_rate": 5.736508490273188e-05,
      "loss": 1.2063,
      "step": 107
    },
    {
      "epoch": 0.0060640941057566785,
      "grad_norm": 0.5717722773551941,
      "learning_rate": 5.644996082651017e-05,
      "loss": 1.1057,
      "step": 108
    },
    {
      "epoch": 0.006120243125254425,
      "grad_norm": 0.5892115831375122,
      "learning_rate": 5.553263409457504e-05,
      "loss": 1.1582,
      "step": 109
    },
    {
      "epoch": 0.006176392144752172,
      "grad_norm": 0.6166552901268005,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 1.1201,
      "step": 110
    },
    {
      "epoch": 0.0062325411642499195,
      "grad_norm": 0.6164728403091431,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 1.0756,
      "step": 111
    },
    {
      "epoch": 0.006288690183747666,
      "grad_norm": 0.6641255021095276,
      "learning_rate": 5.27705737457985e-05,
      "loss": 1.2174,
      "step": 112
    },
    {
      "epoch": 0.006344839203245413,
      "grad_norm": 0.6208594441413879,
      "learning_rate": 5.184757496945726e-05,
      "loss": 1.146,
      "step": 113
    },
    {
      "epoch": 0.0064009882227431605,
      "grad_norm": 0.6231671571731567,
      "learning_rate": 5.092394524795649e-05,
      "loss": 1.1246,
      "step": 114
    },
    {
      "epoch": 0.006457137242240907,
      "grad_norm": 0.6354531049728394,
      "learning_rate": 5e-05,
      "loss": 1.1637,
      "step": 115
    },
    {
      "epoch": 0.006513286261738654,
      "grad_norm": 0.6056180596351624,
      "learning_rate": 4.907605475204352e-05,
      "loss": 1.1256,
      "step": 116
    },
    {
      "epoch": 0.0065694352812364016,
      "grad_norm": 0.5787081718444824,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 1.0863,
      "step": 117
    },
    {
      "epoch": 0.006625584300734149,
      "grad_norm": 0.5680846571922302,
      "learning_rate": 4.72294262542015e-05,
      "loss": 1.0733,
      "step": 118
    },
    {
      "epoch": 0.006681733320231895,
      "grad_norm": 0.5850681066513062,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 1.0659,
      "step": 119
    },
    {
      "epoch": 0.006737882339729643,
      "grad_norm": 0.5893137454986572,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 1.0891,
      "step": 120
    },
    {
      "epoch": 0.00679403135922739,
      "grad_norm": 0.5821502208709717,
      "learning_rate": 4.446736590542497e-05,
      "loss": 1.1219,
      "step": 121
    },
    {
      "epoch": 0.006850180378725136,
      "grad_norm": 0.5872424244880676,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 1.1541,
      "step": 122
    },
    {
      "epoch": 0.006906329398222884,
      "grad_norm": 0.6106603741645813,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 1.153,
      "step": 123
    },
    {
      "epoch": 0.006962478417720631,
      "grad_norm": 0.5763170123100281,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 1.049,
      "step": 124
    },
    {
      "epoch": 0.007018627437218377,
      "grad_norm": 0.5933642387390137,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 1.102,
      "step": 125
    },
    {
      "epoch": 0.007074776456716125,
      "grad_norm": 0.6378093361854553,
      "learning_rate": 3.99058795421495e-05,
      "loss": 1.1363,
      "step": 126
    },
    {
      "epoch": 0.007130925476213872,
      "grad_norm": 0.6463841199874878,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 1.1423,
      "step": 127
    },
    {
      "epoch": 0.007187074495711618,
      "grad_norm": 0.6380355954170227,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 1.1044,
      "step": 128
    },
    {
      "epoch": 0.007243223515209366,
      "grad_norm": 0.610107421875,
      "learning_rate": 3.720786112027822e-05,
      "loss": 1.1541,
      "step": 129
    },
    {
      "epoch": 0.007299372534707113,
      "grad_norm": 0.6335543990135193,
      "learning_rate": 3.631685049639586e-05,
      "loss": 1.0622,
      "step": 130
    },
    {
      "epoch": 0.007355521554204859,
      "grad_norm": 0.6455392837524414,
      "learning_rate": 3.543051265553377e-05,
      "loss": 1.1027,
      "step": 131
    },
    {
      "epoch": 0.007411670573702607,
      "grad_norm": 0.6415156126022339,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0584,
      "step": 132
    },
    {
      "epoch": 0.007467819593200354,
      "grad_norm": 0.6462504863739014,
      "learning_rate": 3.367306435799584e-05,
      "loss": 1.002,
      "step": 133
    },
    {
      "epoch": 0.0075239686126981,
      "grad_norm": 0.6440901756286621,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 1.0837,
      "step": 134
    },
    {
      "epoch": 0.007580117632195848,
      "grad_norm": 0.6546915173530579,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 1.1001,
      "step": 135
    },
    {
      "epoch": 0.007636266651693595,
      "grad_norm": 0.6541869044303894,
      "learning_rate": 3.107944749788449e-05,
      "loss": 1.0195,
      "step": 136
    },
    {
      "epoch": 0.007692415671191341,
      "grad_norm": 0.6587697267532349,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.999,
      "step": 137
    },
    {
      "epoch": 0.007748564690689089,
      "grad_norm": 0.6729567646980286,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 1.1028,
      "step": 138
    },
    {
      "epoch": 0.007804713710186836,
      "grad_norm": 0.6894831657409668,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 1.2005,
      "step": 139
    },
    {
      "epoch": 0.007860862729684583,
      "grad_norm": 0.6334856748580933,
      "learning_rate": 2.771308221117309e-05,
      "loss": 1.02,
      "step": 140
    },
    {
      "epoch": 0.00791701174918233,
      "grad_norm": 0.7342789173126221,
      "learning_rate": 2.688980582298435e-05,
      "loss": 1.1491,
      "step": 141
    },
    {
      "epoch": 0.007973160768680076,
      "grad_norm": 0.6831063628196716,
      "learning_rate": 2.607442154493568e-05,
      "loss": 1.1042,
      "step": 142
    },
    {
      "epoch": 0.008029309788177823,
      "grad_norm": 0.7168252468109131,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 1.0282,
      "step": 143
    },
    {
      "epoch": 0.00808545880767557,
      "grad_norm": 0.7018248438835144,
      "learning_rate": 2.446844034095466e-05,
      "loss": 1.0509,
      "step": 144
    },
    {
      "epoch": 0.008141607827173318,
      "grad_norm": 0.7139812111854553,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 1.0501,
      "step": 145
    },
    {
      "epoch": 0.008197756846671065,
      "grad_norm": 0.704173743724823,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 1.0048,
      "step": 146
    },
    {
      "epoch": 0.008253905866168813,
      "grad_norm": 0.7042719721794128,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.9387,
      "step": 147
    },
    {
      "epoch": 0.008310054885666558,
      "grad_norm": 0.7368987798690796,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.8796,
      "step": 148
    },
    {
      "epoch": 0.008366203905164305,
      "grad_norm": 0.711969792842865,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9497,
      "step": 149
    },
    {
      "epoch": 0.008422352924662053,
      "grad_norm": 0.8901267647743225,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 0.8115,
      "step": 150
    },
    {
      "epoch": 0.008422352924662053,
      "eval_loss": 1.1007310152053833,
      "eval_runtime": 2113.3876,
      "eval_samples_per_second": 14.193,
      "eval_steps_per_second": 7.097,
      "step": 150
    },
    {
      "epoch": 0.0084785019441598,
      "grad_norm": 0.6676438450813293,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 1.1377,
      "step": 151
    },
    {
      "epoch": 0.008534650963657547,
      "grad_norm": 0.665339469909668,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 1.1947,
      "step": 152
    },
    {
      "epoch": 0.008590799983155295,
      "grad_norm": 0.6559942364692688,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 1.1952,
      "step": 153
    },
    {
      "epoch": 0.008646949002653042,
      "grad_norm": 0.6559615135192871,
      "learning_rate": 1.700377325606388e-05,
      "loss": 1.2047,
      "step": 154
    },
    {
      "epoch": 0.008703098022150788,
      "grad_norm": 0.6157370805740356,
      "learning_rate": 1.631521781767214e-05,
      "loss": 1.1413,
      "step": 155
    },
    {
      "epoch": 0.008759247041648535,
      "grad_norm": 0.611395537853241,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 1.124,
      "step": 156
    },
    {
      "epoch": 0.008815396061146282,
      "grad_norm": 0.619073212146759,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 1.1655,
      "step": 157
    },
    {
      "epoch": 0.00887154508064403,
      "grad_norm": 0.6087830662727356,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 1.1688,
      "step": 158
    },
    {
      "epoch": 0.008927694100141777,
      "grad_norm": 0.5968063473701477,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 1.1121,
      "step": 159
    },
    {
      "epoch": 0.008983843119639524,
      "grad_norm": 0.5817863941192627,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 1.1656,
      "step": 160
    },
    {
      "epoch": 0.00903999213913727,
      "grad_norm": 0.6048336625099182,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 1.1053,
      "step": 161
    },
    {
      "epoch": 0.009096141158635017,
      "grad_norm": 0.590214192867279,
      "learning_rate": 1.183008586294485e-05,
      "loss": 1.0622,
      "step": 162
    },
    {
      "epoch": 0.009152290178132764,
      "grad_norm": 0.5889133810997009,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 1.1065,
      "step": 163
    },
    {
      "epoch": 0.009208439197630511,
      "grad_norm": 0.5919927954673767,
      "learning_rate": 1.066275309832584e-05,
      "loss": 1.13,
      "step": 164
    },
    {
      "epoch": 0.009264588217128259,
      "grad_norm": 0.5542485117912292,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 1.0676,
      "step": 165
    },
    {
      "epoch": 0.009320737236626006,
      "grad_norm": 0.5679227709770203,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0308,
      "step": 166
    },
    {
      "epoch": 0.009376886256123752,
      "grad_norm": 0.6166754961013794,
      "learning_rate": 9.012975854638949e-06,
      "loss": 1.109,
      "step": 167
    },
    {
      "epoch": 0.009433035275621499,
      "grad_norm": 0.6386741995811462,
      "learning_rate": 8.490798459222476e-06,
      "loss": 1.1193,
      "step": 168
    },
    {
      "epoch": 0.009489184295119246,
      "grad_norm": 0.5977522730827332,
      "learning_rate": 7.982796418105371e-06,
      "loss": 1.1409,
      "step": 169
    },
    {
      "epoch": 0.009545333314616994,
      "grad_norm": 0.5759233236312866,
      "learning_rate": 7.489143213519301e-06,
      "loss": 1.0567,
      "step": 170
    },
    {
      "epoch": 0.00960148233411474,
      "grad_norm": 0.6274077296257019,
      "learning_rate": 7.010007427581378e-06,
      "loss": 1.1048,
      "step": 171
    },
    {
      "epoch": 0.009657631353612488,
      "grad_norm": 0.658632218837738,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 1.1384,
      "step": 172
    },
    {
      "epoch": 0.009713780373110235,
      "grad_norm": 0.6003522872924805,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 1.111,
      "step": 173
    },
    {
      "epoch": 0.009769929392607981,
      "grad_norm": 0.5976920127868652,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 1.0147,
      "step": 174
    },
    {
      "epoch": 0.009826078412105728,
      "grad_norm": 0.6562578082084656,
      "learning_rate": 5.241835432246889e-06,
      "loss": 1.0583,
      "step": 175
    },
    {
      "epoch": 0.009882227431603476,
      "grad_norm": 0.6632155179977417,
      "learning_rate": 4.837640032693558e-06,
      "loss": 1.0997,
      "step": 176
    },
    {
      "epoch": 0.009938376451101223,
      "grad_norm": 0.66261887550354,
      "learning_rate": 4.448867537695578e-06,
      "loss": 1.1141,
      "step": 177
    },
    {
      "epoch": 0.00999452547059897,
      "grad_norm": 0.6599045991897583,
      "learning_rate": 4.075650712703849e-06,
      "loss": 1.0983,
      "step": 178
    },
    {
      "epoch": 0.010050674490096717,
      "grad_norm": 0.6300812363624573,
      "learning_rate": 3.71811701092219e-06,
      "loss": 1.0951,
      "step": 179
    },
    {
      "epoch": 0.010106823509594463,
      "grad_norm": 0.6509256362915039,
      "learning_rate": 3.376388529782215e-06,
      "loss": 1.0763,
      "step": 180
    },
    {
      "epoch": 0.01016297252909221,
      "grad_norm": 0.6628503799438477,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 1.0886,
      "step": 181
    },
    {
      "epoch": 0.010219121548589958,
      "grad_norm": 0.7099509239196777,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 1.1347,
      "step": 182
    },
    {
      "epoch": 0.010275270568087705,
      "grad_norm": 0.671892523765564,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0696,
      "step": 183
    },
    {
      "epoch": 0.010331419587585452,
      "grad_norm": 0.6824628114700317,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 1.0456,
      "step": 184
    },
    {
      "epoch": 0.0103875686070832,
      "grad_norm": 0.6700963973999023,
      "learning_rate": 1.908717841359048e-06,
      "loss": 1.0412,
      "step": 185
    },
    {
      "epoch": 0.010443717626580945,
      "grad_norm": 0.648791491985321,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 1.0254,
      "step": 186
    },
    {
      "epoch": 0.010499866646078692,
      "grad_norm": 0.7626706957817078,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 1.1861,
      "step": 187
    },
    {
      "epoch": 0.01055601566557644,
      "grad_norm": 0.7225971221923828,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 1.1223,
      "step": 188
    },
    {
      "epoch": 0.010612164685074187,
      "grad_norm": 0.7763531804084778,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 1.125,
      "step": 189
    },
    {
      "epoch": 0.010668313704571934,
      "grad_norm": 0.740941047668457,
      "learning_rate": 8.513450158049108e-07,
      "loss": 1.1183,
      "step": 190
    },
    {
      "epoch": 0.010724462724069682,
      "grad_norm": 0.7408305406570435,
      "learning_rate": 6.899626323298713e-07,
      "loss": 1.1307,
      "step": 191
    },
    {
      "epoch": 0.010780611743567427,
      "grad_norm": 0.8153759241104126,
      "learning_rate": 5.454195814427021e-07,
      "loss": 1.1874,
      "step": 192
    },
    {
      "epoch": 0.010836760763065174,
      "grad_norm": 0.7274287939071655,
      "learning_rate": 4.177652244628627e-07,
      "loss": 1.072,
      "step": 193
    },
    {
      "epoch": 0.010892909782562922,
      "grad_norm": 0.7061375379562378,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.9626,
      "step": 194
    },
    {
      "epoch": 0.010949058802060669,
      "grad_norm": 0.785638153553009,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.9788,
      "step": 195
    },
    {
      "epoch": 0.011005207821558416,
      "grad_norm": 0.7976987361907959,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 1.0217,
      "step": 196
    },
    {
      "epoch": 0.011061356841056164,
      "grad_norm": 0.833655595779419,
      "learning_rate": 7.681980162830282e-08,
      "loss": 1.0447,
      "step": 197
    },
    {
      "epoch": 0.01111750586055391,
      "grad_norm": 0.8139376640319824,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.9187,
      "step": 198
    },
    {
      "epoch": 0.011173654880051656,
      "grad_norm": 0.957710325717926,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.9699,
      "step": 199
    },
    {
      "epoch": 0.011229803899549404,
      "grad_norm": 1.0477885007858276,
      "learning_rate": 0.0,
      "loss": 0.8645,
      "step": 200
    },
    {
      "epoch": 0.011229803899549404,
      "eval_loss": 1.0859266519546509,
      "eval_runtime": 2112.9728,
      "eval_samples_per_second": 14.196,
      "eval_steps_per_second": 7.098,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 1.146618963296256e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}