{
  "best_metric": 1.8535966873168945,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03421435292105038,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001710717646052519,
      "grad_norm": 0.383236289024353,
      "learning_rate": 1.004e-05,
      "loss": 2.0165,
      "step": 1
    },
    {
      "epoch": 0.0001710717646052519,
      "eval_loss": 2.0891342163085938,
      "eval_runtime": 473.9324,
      "eval_samples_per_second": 5.195,
      "eval_steps_per_second": 1.3,
      "step": 1
    },
    {
      "epoch": 0.0003421435292105038,
      "grad_norm": 0.38923412561416626,
      "learning_rate": 2.008e-05,
      "loss": 1.7318,
      "step": 2
    },
    {
      "epoch": 0.0005132152938157557,
      "grad_norm": 0.4268319606781006,
      "learning_rate": 3.012e-05,
      "loss": 2.0336,
      "step": 3
    },
    {
      "epoch": 0.0006842870584210076,
      "grad_norm": 0.4290253520011902,
      "learning_rate": 4.016e-05,
      "loss": 1.8747,
      "step": 4
    },
    {
      "epoch": 0.0008553588230262595,
      "grad_norm": 0.44560176134109497,
      "learning_rate": 5.02e-05,
      "loss": 2.1207,
      "step": 5
    },
    {
      "epoch": 0.0010264305876315114,
      "grad_norm": 0.4551117718219757,
      "learning_rate": 6.024e-05,
      "loss": 2.0431,
      "step": 6
    },
    {
      "epoch": 0.0011975023522367632,
      "grad_norm": 0.4633933901786804,
      "learning_rate": 7.028e-05,
      "loss": 1.7246,
      "step": 7
    },
    {
      "epoch": 0.0013685741168420152,
      "grad_norm": 0.5507611632347107,
      "learning_rate": 8.032e-05,
      "loss": 1.9728,
      "step": 8
    },
    {
      "epoch": 0.001539645881447267,
      "grad_norm": 0.5344508290290833,
      "learning_rate": 9.036000000000001e-05,
      "loss": 1.8793,
      "step": 9
    },
    {
      "epoch": 0.001710717646052519,
      "grad_norm": 0.5629733204841614,
      "learning_rate": 0.0001004,
      "loss": 2.0234,
      "step": 10
    },
    {
      "epoch": 0.0018817894106577708,
      "grad_norm": 0.554598867893219,
      "learning_rate": 9.987157894736842e-05,
      "loss": 1.8122,
      "step": 11
    },
    {
      "epoch": 0.002052861175263023,
      "grad_norm": 0.6233848929405212,
      "learning_rate": 9.934315789473684e-05,
      "loss": 2.0835,
      "step": 12
    },
    {
      "epoch": 0.002223932939868275,
      "grad_norm": 0.6465232372283936,
      "learning_rate": 9.881473684210525e-05,
      "loss": 1.9595,
      "step": 13
    },
    {
      "epoch": 0.0023950047044735264,
      "grad_norm": 0.6446559429168701,
      "learning_rate": 9.828631578947369e-05,
      "loss": 1.7788,
      "step": 14
    },
    {
      "epoch": 0.0025660764690787785,
      "grad_norm": 0.5892208814620972,
      "learning_rate": 9.77578947368421e-05,
      "loss": 1.7229,
      "step": 15
    },
    {
      "epoch": 0.0027371482336840305,
      "grad_norm": 0.6372520923614502,
      "learning_rate": 9.722947368421052e-05,
      "loss": 1.7322,
      "step": 16
    },
    {
      "epoch": 0.0029082199982892825,
      "grad_norm": 0.6278177499771118,
      "learning_rate": 9.670105263157895e-05,
      "loss": 1.8333,
      "step": 17
    },
    {
      "epoch": 0.003079291762894534,
      "grad_norm": 0.6287798285484314,
      "learning_rate": 9.617263157894737e-05,
      "loss": 1.8528,
      "step": 18
    },
    {
      "epoch": 0.003250363527499786,
      "grad_norm": 0.5991953015327454,
      "learning_rate": 9.564421052631579e-05,
      "loss": 1.7871,
      "step": 19
    },
    {
      "epoch": 0.003421435292105038,
      "grad_norm": 0.573375940322876,
      "learning_rate": 9.511578947368421e-05,
      "loss": 1.6581,
      "step": 20
    },
    {
      "epoch": 0.00359250705671029,
      "grad_norm": 0.5814819931983948,
      "learning_rate": 9.458736842105264e-05,
      "loss": 1.8643,
      "step": 21
    },
    {
      "epoch": 0.0037635788213155417,
      "grad_norm": 0.665965735912323,
      "learning_rate": 9.405894736842106e-05,
      "loss": 1.8961,
      "step": 22
    },
    {
      "epoch": 0.003934650585920794,
      "grad_norm": 0.6515952944755554,
      "learning_rate": 9.353052631578947e-05,
      "loss": 1.9137,
      "step": 23
    },
    {
      "epoch": 0.004105722350526046,
      "grad_norm": 0.5990787744522095,
      "learning_rate": 9.300210526315789e-05,
      "loss": 1.8396,
      "step": 24
    },
    {
      "epoch": 0.004276794115131297,
      "grad_norm": 0.6736911535263062,
      "learning_rate": 9.247368421052631e-05,
      "loss": 2.018,
      "step": 25
    },
    {
      "epoch": 0.00444786587973655,
      "grad_norm": 0.6013162732124329,
      "learning_rate": 9.194526315789473e-05,
      "loss": 1.6318,
      "step": 26
    },
    {
      "epoch": 0.004618937644341801,
      "grad_norm": 0.6049439907073975,
      "learning_rate": 9.141684210526316e-05,
      "loss": 1.8607,
      "step": 27
    },
    {
      "epoch": 0.004790009408947053,
      "grad_norm": 0.6569304466247559,
      "learning_rate": 9.088842105263158e-05,
      "loss": 1.8646,
      "step": 28
    },
    {
      "epoch": 0.004961081173552305,
      "grad_norm": 0.6664987802505493,
      "learning_rate": 9.036000000000001e-05,
      "loss": 1.7735,
      "step": 29
    },
    {
      "epoch": 0.005132152938157557,
      "grad_norm": 0.7716237902641296,
      "learning_rate": 8.983157894736843e-05,
      "loss": 2.1894,
      "step": 30
    },
    {
      "epoch": 0.005303224702762809,
      "grad_norm": 0.7701791524887085,
      "learning_rate": 8.930315789473684e-05,
      "loss": 1.9132,
      "step": 31
    },
    {
      "epoch": 0.005474296467368061,
      "grad_norm": 0.6804842352867126,
      "learning_rate": 8.877473684210526e-05,
      "loss": 1.7197,
      "step": 32
    },
    {
      "epoch": 0.0056453682319733125,
      "grad_norm": 0.7339447736740112,
      "learning_rate": 8.824631578947368e-05,
      "loss": 1.8394,
      "step": 33
    },
    {
      "epoch": 0.005816439996578565,
      "grad_norm": 0.731982409954071,
      "learning_rate": 8.771789473684211e-05,
      "loss": 1.8362,
      "step": 34
    },
    {
      "epoch": 0.0059875117611838165,
      "grad_norm": 0.8712673187255859,
      "learning_rate": 8.718947368421053e-05,
      "loss": 1.7972,
      "step": 35
    },
    {
      "epoch": 0.006158583525789068,
      "grad_norm": 0.8886252641677856,
      "learning_rate": 8.666105263157895e-05,
      "loss": 2.1816,
      "step": 36
    },
    {
      "epoch": 0.006329655290394321,
      "grad_norm": 0.913334310054779,
      "learning_rate": 8.613263157894737e-05,
      "loss": 1.8242,
      "step": 37
    },
    {
      "epoch": 0.006500727054999572,
      "grad_norm": 0.8896219730377197,
      "learning_rate": 8.560421052631578e-05,
      "loss": 1.8448,
      "step": 38
    },
    {
      "epoch": 0.006671798819604825,
      "grad_norm": 0.9681621193885803,
      "learning_rate": 8.50757894736842e-05,
      "loss": 1.6235,
      "step": 39
    },
    {
      "epoch": 0.006842870584210076,
      "grad_norm": 1.0905768871307373,
      "learning_rate": 8.454736842105263e-05,
      "loss": 1.8704,
      "step": 40
    },
    {
      "epoch": 0.007013942348815328,
      "grad_norm": 0.9447023272514343,
      "learning_rate": 8.401894736842106e-05,
      "loss": 1.8091,
      "step": 41
    },
    {
      "epoch": 0.00718501411342058,
      "grad_norm": 1.0970029830932617,
      "learning_rate": 8.349052631578948e-05,
      "loss": 2.0633,
      "step": 42
    },
    {
      "epoch": 0.007356085878025832,
      "grad_norm": 1.2916038036346436,
      "learning_rate": 8.29621052631579e-05,
      "loss": 2.2442,
      "step": 43
    },
    {
      "epoch": 0.007527157642631083,
      "grad_norm": 1.0917505025863647,
      "learning_rate": 8.243368421052632e-05,
      "loss": 1.8491,
      "step": 44
    },
    {
      "epoch": 0.007698229407236336,
      "grad_norm": 1.5188097953796387,
      "learning_rate": 8.190526315789474e-05,
      "loss": 1.6231,
      "step": 45
    },
    {
      "epoch": 0.007869301171841588,
      "grad_norm": 1.479370355606079,
      "learning_rate": 8.137684210526315e-05,
      "loss": 1.7806,
      "step": 46
    },
    {
      "epoch": 0.008040372936446839,
      "grad_norm": 1.4857006072998047,
      "learning_rate": 8.084842105263157e-05,
      "loss": 1.7682,
      "step": 47
    },
    {
      "epoch": 0.008211444701052091,
      "grad_norm": 2.0244221687316895,
      "learning_rate": 8.032e-05,
      "loss": 2.0125,
      "step": 48
    },
    {
      "epoch": 0.008382516465657344,
      "grad_norm": 1.8919278383255005,
      "learning_rate": 7.979157894736842e-05,
      "loss": 1.7106,
      "step": 49
    },
    {
      "epoch": 0.008553588230262595,
      "grad_norm": 4.771112442016602,
      "learning_rate": 7.926315789473684e-05,
      "loss": 1.6001,
      "step": 50
    },
    {
      "epoch": 0.008553588230262595,
      "eval_loss": 2.019399881362915,
      "eval_runtime": 474.1809,
      "eval_samples_per_second": 5.192,
      "eval_steps_per_second": 1.299,
      "step": 50
    },
    {
      "epoch": 0.008724659994867847,
      "grad_norm": 0.7101765275001526,
      "learning_rate": 7.873473684210526e-05,
      "loss": 1.8857,
      "step": 51
    },
    {
      "epoch": 0.0088957317594731,
      "grad_norm": 0.776714026927948,
      "learning_rate": 7.820631578947369e-05,
      "loss": 1.8346,
      "step": 52
    },
    {
      "epoch": 0.00906680352407835,
      "grad_norm": 0.7492753863334656,
      "learning_rate": 7.76778947368421e-05,
      "loss": 2.0555,
      "step": 53
    },
    {
      "epoch": 0.009237875288683603,
      "grad_norm": 0.532320499420166,
      "learning_rate": 7.714947368421052e-05,
      "loss": 1.833,
      "step": 54
    },
    {
      "epoch": 0.009408947053288855,
      "grad_norm": 0.506446361541748,
      "learning_rate": 7.662105263157896e-05,
      "loss": 1.8922,
      "step": 55
    },
    {
      "epoch": 0.009580018817894106,
      "grad_norm": 0.4671626389026642,
      "learning_rate": 7.609263157894737e-05,
      "loss": 1.9379,
      "step": 56
    },
    {
      "epoch": 0.009751090582499358,
      "grad_norm": 0.5219800472259521,
      "learning_rate": 7.556421052631579e-05,
      "loss": 1.9508,
      "step": 57
    },
    {
      "epoch": 0.00992216234710461,
      "grad_norm": 0.4187794029712677,
      "learning_rate": 7.503578947368421e-05,
      "loss": 1.5711,
      "step": 58
    },
    {
      "epoch": 0.010093234111709863,
      "grad_norm": 0.47037985920906067,
      "learning_rate": 7.450736842105263e-05,
      "loss": 1.8885,
      "step": 59
    },
    {
      "epoch": 0.010264305876315114,
      "grad_norm": 0.45489931106567383,
      "learning_rate": 7.397894736842105e-05,
      "loss": 2.0025,
      "step": 60
    },
    {
      "epoch": 0.010435377640920366,
      "grad_norm": 0.4538400173187256,
      "learning_rate": 7.345052631578948e-05,
      "loss": 1.8172,
      "step": 61
    },
    {
      "epoch": 0.010606449405525619,
      "grad_norm": 0.4797042906284332,
      "learning_rate": 7.29221052631579e-05,
      "loss": 1.8545,
      "step": 62
    },
    {
      "epoch": 0.01077752117013087,
      "grad_norm": 0.48613712191581726,
      "learning_rate": 7.239368421052631e-05,
      "loss": 1.7661,
      "step": 63
    },
    {
      "epoch": 0.010948592934736122,
      "grad_norm": 0.5110929012298584,
      "learning_rate": 7.186526315789474e-05,
      "loss": 1.8899,
      "step": 64
    },
    {
      "epoch": 0.011119664699341374,
      "grad_norm": 0.47642821073532104,
      "learning_rate": 7.133684210526316e-05,
      "loss": 1.7915,
      "step": 65
    },
    {
      "epoch": 0.011290736463946625,
      "grad_norm": 0.5066452622413635,
      "learning_rate": 7.080842105263158e-05,
      "loss": 1.7244,
      "step": 66
    },
    {
      "epoch": 0.011461808228551877,
      "grad_norm": 0.5502453446388245,
      "learning_rate": 7.028e-05,
      "loss": 1.7781,
      "step": 67
    },
    {
      "epoch": 0.01163287999315713,
      "grad_norm": 0.5751240253448486,
      "learning_rate": 6.975157894736843e-05,
      "loss": 1.8453,
      "step": 68
    },
    {
      "epoch": 0.01180395175776238,
      "grad_norm": 0.5743075609207153,
      "learning_rate": 6.922315789473685e-05,
      "loss": 1.8647,
      "step": 69
    },
    {
      "epoch": 0.011975023522367633,
      "grad_norm": 0.5658362507820129,
      "learning_rate": 6.869473684210527e-05,
      "loss": 1.9551,
      "step": 70
    },
    {
      "epoch": 0.012146095286972886,
      "grad_norm": 0.5974031686782837,
      "learning_rate": 6.816631578947368e-05,
      "loss": 1.9202,
      "step": 71
    },
    {
      "epoch": 0.012317167051578136,
      "grad_norm": 0.6650647521018982,
      "learning_rate": 6.76378947368421e-05,
      "loss": 1.7682,
      "step": 72
    },
    {
      "epoch": 0.012488238816183389,
      "grad_norm": 0.6288644671440125,
      "learning_rate": 6.710947368421052e-05,
      "loss": 2.042,
      "step": 73
    },
    {
      "epoch": 0.012659310580788641,
      "grad_norm": 0.6033047437667847,
      "learning_rate": 6.658105263157894e-05,
      "loss": 1.8117,
      "step": 74
    },
    {
      "epoch": 0.012830382345393894,
      "grad_norm": 0.6429676413536072,
      "learning_rate": 6.605263157894737e-05,
      "loss": 1.9016,
      "step": 75
    },
    {
      "epoch": 0.013001454109999144,
      "grad_norm": 0.7156361937522888,
      "learning_rate": 6.55242105263158e-05,
      "loss": 2.0832,
      "step": 76
    },
    {
      "epoch": 0.013172525874604397,
      "grad_norm": 0.6470149755477905,
      "learning_rate": 6.499578947368422e-05,
      "loss": 1.7331,
      "step": 77
    },
    {
      "epoch": 0.01334359763920965,
      "grad_norm": 0.6850797533988953,
      "learning_rate": 6.446736842105264e-05,
      "loss": 1.9599,
      "step": 78
    },
    {
      "epoch": 0.0135146694038149,
      "grad_norm": 0.6620407700538635,
      "learning_rate": 6.393894736842105e-05,
      "loss": 1.9652,
      "step": 79
    },
    {
      "epoch": 0.013685741168420152,
      "grad_norm": 0.6680328249931335,
      "learning_rate": 6.341052631578947e-05,
      "loss": 1.8194,
      "step": 80
    },
    {
      "epoch": 0.013856812933025405,
      "grad_norm": 0.6848267316818237,
      "learning_rate": 6.288210526315789e-05,
      "loss": 1.9067,
      "step": 81
    },
    {
      "epoch": 0.014027884697630656,
      "grad_norm": 0.7361618876457214,
      "learning_rate": 6.235368421052632e-05,
      "loss": 1.8385,
      "step": 82
    },
    {
      "epoch": 0.014198956462235908,
      "grad_norm": 0.7371098399162292,
      "learning_rate": 6.182526315789474e-05,
      "loss": 1.8822,
      "step": 83
    },
    {
      "epoch": 0.01437002822684116,
      "grad_norm": 0.7366199493408203,
      "learning_rate": 6.129684210526316e-05,
      "loss": 1.7163,
      "step": 84
    },
    {
      "epoch": 0.014541099991446411,
      "grad_norm": 0.9039151668548584,
      "learning_rate": 6.076842105263158e-05,
      "loss": 2.2045,
      "step": 85
    },
    {
      "epoch": 0.014712171756051664,
      "grad_norm": 0.7939276695251465,
      "learning_rate": 6.024e-05,
      "loss": 1.9084,
      "step": 86
    },
    {
      "epoch": 0.014883243520656916,
      "grad_norm": 0.8294872641563416,
      "learning_rate": 5.971157894736842e-05,
      "loss": 1.9239,
      "step": 87
    },
    {
      "epoch": 0.015054315285262167,
      "grad_norm": 0.8802934288978577,
      "learning_rate": 5.9183157894736835e-05,
      "loss": 2.0455,
      "step": 88
    },
    {
      "epoch": 0.01522538704986742,
      "grad_norm": 0.889517068862915,
      "learning_rate": 5.8654736842105267e-05,
      "loss": 1.9911,
      "step": 89
    },
    {
      "epoch": 0.015396458814472672,
      "grad_norm": 1.0230233669281006,
      "learning_rate": 5.8126315789473684e-05,
      "loss": 1.5023,
      "step": 90
    },
    {
      "epoch": 0.015567530579077922,
      "grad_norm": 0.9384157657623291,
      "learning_rate": 5.759789473684211e-05,
      "loss": 1.9499,
      "step": 91
    },
    {
      "epoch": 0.015738602343683177,
      "grad_norm": 0.9163877367973328,
      "learning_rate": 5.706947368421053e-05,
      "loss": 1.7279,
      "step": 92
    },
    {
      "epoch": 0.015909674108288425,
      "grad_norm": 1.0640720129013062,
      "learning_rate": 5.6541052631578945e-05,
      "loss": 2.0255,
      "step": 93
    },
    {
      "epoch": 0.016080745872893678,
      "grad_norm": 1.0487096309661865,
      "learning_rate": 5.601263157894736e-05,
      "loss": 1.7711,
      "step": 94
    },
    {
      "epoch": 0.01625181763749893,
      "grad_norm": 1.0018972158432007,
      "learning_rate": 5.5484210526315794e-05,
      "loss": 1.5404,
      "step": 95
    },
    {
      "epoch": 0.016422889402104183,
      "grad_norm": 1.243520736694336,
      "learning_rate": 5.495578947368421e-05,
      "loss": 1.5571,
      "step": 96
    },
    {
      "epoch": 0.016593961166709435,
      "grad_norm": 1.3318722248077393,
      "learning_rate": 5.442736842105264e-05,
      "loss": 1.9937,
      "step": 97
    },
    {
      "epoch": 0.016765032931314688,
      "grad_norm": 1.5980501174926758,
      "learning_rate": 5.3898947368421055e-05,
      "loss": 1.7534,
      "step": 98
    },
    {
      "epoch": 0.016936104695919937,
      "grad_norm": 2.008939266204834,
      "learning_rate": 5.337052631578947e-05,
      "loss": 1.5161,
      "step": 99
    },
    {
      "epoch": 0.01710717646052519,
      "grad_norm": 3.1472246646881104,
      "learning_rate": 5.284210526315789e-05,
      "loss": 2.7117,
      "step": 100
    },
    {
      "epoch": 0.01710717646052519,
      "eval_loss": 1.9197953939437866,
      "eval_runtime": 473.5626,
      "eval_samples_per_second": 5.199,
      "eval_steps_per_second": 1.301,
      "step": 100
    },
    {
      "epoch": 0.01727824822513044,
      "grad_norm": 0.6856660842895508,
      "learning_rate": 5.231368421052631e-05,
      "loss": 1.8056,
      "step": 101
    },
    {
      "epoch": 0.017449319989735694,
      "grad_norm": 0.8271840810775757,
      "learning_rate": 5.178526315789474e-05,
      "loss": 1.915,
      "step": 102
    },
    {
      "epoch": 0.017620391754340946,
      "grad_norm": 0.7571515440940857,
      "learning_rate": 5.1256842105263165e-05,
      "loss": 1.9442,
      "step": 103
    },
    {
      "epoch": 0.0177914635189462,
      "grad_norm": 0.867884635925293,
      "learning_rate": 5.072842105263158e-05,
      "loss": 2.145,
      "step": 104
    },
    {
      "epoch": 0.01796253528355145,
      "grad_norm": 0.7025319933891296,
      "learning_rate": 5.02e-05,
      "loss": 1.7341,
      "step": 105
    },
    {
      "epoch": 0.0181336070481567,
      "grad_norm": 0.6765435934066772,
      "learning_rate": 4.967157894736842e-05,
      "loss": 2.1242,
      "step": 106
    },
    {
      "epoch": 0.018304678812761953,
      "grad_norm": 0.5824732184410095,
      "learning_rate": 4.914315789473684e-05,
      "loss": 1.9422,
      "step": 107
    },
    {
      "epoch": 0.018475750577367205,
      "grad_norm": 0.5176606178283691,
      "learning_rate": 4.861473684210526e-05,
      "loss": 2.0242,
      "step": 108
    },
    {
      "epoch": 0.018646822341972458,
      "grad_norm": 0.5743870139122009,
      "learning_rate": 4.8086315789473686e-05,
      "loss": 2.0175,
      "step": 109
    },
    {
      "epoch": 0.01881789410657771,
      "grad_norm": 0.5101130604743958,
      "learning_rate": 4.7557894736842104e-05,
      "loss": 1.8344,
      "step": 110
    },
    {
      "epoch": 0.018988965871182963,
      "grad_norm": 0.5062516927719116,
      "learning_rate": 4.702947368421053e-05,
      "loss": 1.9409,
      "step": 111
    },
    {
      "epoch": 0.01916003763578821,
      "grad_norm": 0.48760825395584106,
      "learning_rate": 4.6501052631578946e-05,
      "loss": 1.8474,
      "step": 112
    },
    {
      "epoch": 0.019331109400393464,
      "grad_norm": 0.492199182510376,
      "learning_rate": 4.5972631578947364e-05,
      "loss": 1.9067,
      "step": 113
    },
    {
      "epoch": 0.019502181164998716,
      "grad_norm": 0.4930146336555481,
      "learning_rate": 4.544421052631579e-05,
      "loss": 1.7696,
      "step": 114
    },
    {
      "epoch": 0.01967325292960397,
      "grad_norm": 0.5493840575218201,
      "learning_rate": 4.4915789473684213e-05,
      "loss": 2.0178,
      "step": 115
    },
    {
      "epoch": 0.01984432469420922,
      "grad_norm": 0.5961560606956482,
      "learning_rate": 4.438736842105263e-05,
      "loss": 1.6976,
      "step": 116
    },
    {
      "epoch": 0.020015396458814474,
      "grad_norm": 0.5364917516708374,
      "learning_rate": 4.3858947368421056e-05,
      "loss": 1.847,
      "step": 117
    },
    {
      "epoch": 0.020186468223419726,
      "grad_norm": 0.5656726956367493,
      "learning_rate": 4.3330526315789474e-05,
      "loss": 1.9252,
      "step": 118
    },
    {
      "epoch": 0.020357539988024975,
      "grad_norm": 0.5928261876106262,
      "learning_rate": 4.280210526315789e-05,
      "loss": 1.9079,
      "step": 119
    },
    {
      "epoch": 0.020528611752630228,
      "grad_norm": 0.5389055609703064,
      "learning_rate": 4.2273684210526317e-05,
      "loss": 1.7967,
      "step": 120
    },
    {
      "epoch": 0.02069968351723548,
      "grad_norm": 0.6076517701148987,
      "learning_rate": 4.174526315789474e-05,
      "loss": 1.793,
      "step": 121
    },
    {
      "epoch": 0.020870755281840733,
      "grad_norm": 0.6341645121574402,
      "learning_rate": 4.121684210526316e-05,
      "loss": 1.9671,
      "step": 122
    },
    {
      "epoch": 0.021041827046445985,
      "grad_norm": 0.6870526075363159,
      "learning_rate": 4.068842105263158e-05,
      "loss": 1.7407,
      "step": 123
    },
    {
      "epoch": 0.021212898811051237,
      "grad_norm": 0.6322492957115173,
      "learning_rate": 4.016e-05,
      "loss": 1.949,
      "step": 124
    },
    {
      "epoch": 0.021383970575656486,
      "grad_norm": 0.6672692894935608,
      "learning_rate": 3.963157894736842e-05,
      "loss": 1.9643,
      "step": 125
    },
    {
      "epoch": 0.02155504234026174,
      "grad_norm": 0.6229186058044434,
      "learning_rate": 3.9103157894736844e-05,
      "loss": 1.7221,
      "step": 126
    },
    {
      "epoch": 0.02172611410486699,
      "grad_norm": 0.7301349639892578,
      "learning_rate": 3.857473684210526e-05,
      "loss": 2.0484,
      "step": 127
    },
    {
      "epoch": 0.021897185869472244,
      "grad_norm": 0.7856729626655579,
      "learning_rate": 3.804631578947369e-05,
      "loss": 1.773,
      "step": 128
    },
    {
      "epoch": 0.022068257634077496,
      "grad_norm": 0.8492652177810669,
      "learning_rate": 3.7517894736842105e-05,
      "loss": 1.8202,
      "step": 129
    },
    {
      "epoch": 0.02223932939868275,
      "grad_norm": 0.7252649068832397,
      "learning_rate": 3.698947368421052e-05,
      "loss": 1.8962,
      "step": 130
    },
    {
      "epoch": 0.022410401163287998,
      "grad_norm": 0.7953678369522095,
      "learning_rate": 3.646105263157895e-05,
      "loss": 1.7289,
      "step": 131
    },
    {
      "epoch": 0.02258147292789325,
      "grad_norm": 0.728402853012085,
      "learning_rate": 3.593263157894737e-05,
      "loss": 1.9082,
      "step": 132
    },
    {
      "epoch": 0.022752544692498503,
      "grad_norm": 0.8220646381378174,
      "learning_rate": 3.540421052631579e-05,
      "loss": 1.9591,
      "step": 133
    },
    {
      "epoch": 0.022923616457103755,
      "grad_norm": 0.8018884062767029,
      "learning_rate": 3.4875789473684215e-05,
      "loss": 2.0895,
      "step": 134
    },
    {
      "epoch": 0.023094688221709007,
      "grad_norm": 0.7861109972000122,
      "learning_rate": 3.434736842105263e-05,
      "loss": 1.9219,
      "step": 135
    },
    {
      "epoch": 0.02326575998631426,
      "grad_norm": 0.8565029501914978,
      "learning_rate": 3.381894736842105e-05,
      "loss": 2.0818,
      "step": 136
    },
    {
      "epoch": 0.023436831750919512,
      "grad_norm": 0.986121416091919,
      "learning_rate": 3.329052631578947e-05,
      "loss": 2.0713,
      "step": 137
    },
    {
      "epoch": 0.02360790351552476,
      "grad_norm": 0.8753408789634705,
      "learning_rate": 3.27621052631579e-05,
      "loss": 1.7472,
      "step": 138
    },
    {
      "epoch": 0.023778975280130014,
      "grad_norm": 1.0510600805282593,
      "learning_rate": 3.223368421052632e-05,
      "loss": 2.1363,
      "step": 139
    },
    {
      "epoch": 0.023950047044735266,
      "grad_norm": 1.0964877605438232,
      "learning_rate": 3.1705263157894736e-05,
      "loss": 2.0689,
      "step": 140
    },
    {
      "epoch": 0.02412111880934052,
      "grad_norm": 1.000916838645935,
      "learning_rate": 3.117684210526316e-05,
      "loss": 1.9126,
      "step": 141
    },
    {
      "epoch": 0.02429219057394577,
      "grad_norm": 1.1080740690231323,
      "learning_rate": 3.064842105263158e-05,
      "loss": 2.4376,
      "step": 142
    },
    {
      "epoch": 0.024463262338551024,
      "grad_norm": 1.1512094736099243,
      "learning_rate": 3.012e-05,
      "loss": 1.8156,
      "step": 143
    },
    {
      "epoch": 0.024634334103156273,
      "grad_norm": 1.3569144010543823,
      "learning_rate": 2.9591578947368418e-05,
      "loss": 1.451,
      "step": 144
    },
    {
      "epoch": 0.024805405867761525,
      "grad_norm": 1.311303734779358,
      "learning_rate": 2.9063157894736842e-05,
      "loss": 2.0755,
      "step": 145
    },
    {
      "epoch": 0.024976477632366777,
      "grad_norm": 1.199066400527954,
      "learning_rate": 2.8534736842105264e-05,
      "loss": 1.3857,
      "step": 146
    },
    {
      "epoch": 0.02514754939697203,
      "grad_norm": 1.3259034156799316,
      "learning_rate": 2.800631578947368e-05,
      "loss": 1.804,
      "step": 147
    },
    {
      "epoch": 0.025318621161577282,
      "grad_norm": 1.8676377534866333,
      "learning_rate": 2.7477894736842106e-05,
      "loss": 1.8025,
      "step": 148
    },
    {
      "epoch": 0.025489692926182535,
      "grad_norm": 2.550297498703003,
      "learning_rate": 2.6949473684210527e-05,
      "loss": 2.0316,
      "step": 149
    },
    {
      "epoch": 0.025660764690787787,
      "grad_norm": 2.5897419452667236,
      "learning_rate": 2.6421052631578945e-05,
      "loss": 1.4353,
      "step": 150
    },
    {
      "epoch": 0.025660764690787787,
      "eval_loss": 1.8687154054641724,
      "eval_runtime": 474.321,
      "eval_samples_per_second": 5.191,
      "eval_steps_per_second": 1.299,
      "step": 150
    },
    {
      "epoch": 0.025831836455393036,
      "grad_norm": 0.429505318403244,
      "learning_rate": 2.589263157894737e-05,
      "loss": 1.536,
      "step": 151
    },
    {
      "epoch": 0.02600290821999829,
      "grad_norm": 0.45272913575172424,
      "learning_rate": 2.536421052631579e-05,
      "loss": 1.7085,
      "step": 152
    },
    {
      "epoch": 0.02617397998460354,
      "grad_norm": 0.4526635706424713,
      "learning_rate": 2.483578947368421e-05,
      "loss": 1.9542,
      "step": 153
    },
    {
      "epoch": 0.026345051749208794,
      "grad_norm": 0.5670432448387146,
      "learning_rate": 2.430736842105263e-05,
      "loss": 2.0316,
      "step": 154
    },
    {
      "epoch": 0.026516123513814046,
      "grad_norm": 0.5231799483299255,
      "learning_rate": 2.3778947368421052e-05,
      "loss": 2.0184,
      "step": 155
    },
    {
      "epoch": 0.0266871952784193,
      "grad_norm": 0.5869430303573608,
      "learning_rate": 2.3250526315789473e-05,
      "loss": 2.0097,
      "step": 156
    },
    {
      "epoch": 0.026858267043024547,
      "grad_norm": 0.6328916549682617,
      "learning_rate": 2.2722105263157894e-05,
      "loss": 1.865,
      "step": 157
    },
    {
      "epoch": 0.0270293388076298,
      "grad_norm": 0.587527334690094,
      "learning_rate": 2.2193684210526316e-05,
      "loss": 1.9417,
      "step": 158
    },
    {
      "epoch": 0.027200410572235052,
      "grad_norm": 0.5576383471488953,
      "learning_rate": 2.1665263157894737e-05,
      "loss": 1.8592,
      "step": 159
    },
    {
      "epoch": 0.027371482336840305,
      "grad_norm": 0.5361258387565613,
      "learning_rate": 2.1136842105263158e-05,
      "loss": 1.9214,
      "step": 160
    },
    {
      "epoch": 0.027542554101445557,
      "grad_norm": 0.5628899931907654,
      "learning_rate": 2.060842105263158e-05,
      "loss": 1.9765,
      "step": 161
    },
    {
      "epoch": 0.02771362586605081,
      "grad_norm": 0.6240307092666626,
      "learning_rate": 2.008e-05,
      "loss": 2.0202,
      "step": 162
    },
    {
      "epoch": 0.02788469763065606,
      "grad_norm": 0.5304953455924988,
      "learning_rate": 1.9551578947368422e-05,
      "loss": 1.76,
      "step": 163
    },
    {
      "epoch": 0.02805576939526131,
      "grad_norm": 0.5631970763206482,
      "learning_rate": 1.9023157894736843e-05,
      "loss": 1.8933,
      "step": 164
    },
    {
      "epoch": 0.028226841159866563,
      "grad_norm": 0.6594295501708984,
      "learning_rate": 1.849473684210526e-05,
      "loss": 1.9873,
      "step": 165
    },
    {
      "epoch": 0.028397912924471816,
      "grad_norm": 0.5234274864196777,
      "learning_rate": 1.7966315789473686e-05,
      "loss": 1.5752,
      "step": 166
    },
    {
      "epoch": 0.02856898468907707,
      "grad_norm": 0.5521509647369385,
      "learning_rate": 1.7437894736842107e-05,
      "loss": 1.878,
      "step": 167
    },
    {
      "epoch": 0.02874005645368232,
      "grad_norm": 0.5257223844528198,
      "learning_rate": 1.6909473684210525e-05,
      "loss": 1.6768,
      "step": 168
    },
    {
      "epoch": 0.028911128218287573,
      "grad_norm": 0.5715846419334412,
      "learning_rate": 1.638105263157895e-05,
      "loss": 1.7078,
      "step": 169
    },
    {
      "epoch": 0.029082199982892822,
      "grad_norm": 0.5698923468589783,
      "learning_rate": 1.5852631578947368e-05,
      "loss": 1.8397,
      "step": 170
    },
    {
      "epoch": 0.029253271747498075,
      "grad_norm": 0.5703829526901245,
      "learning_rate": 1.532421052631579e-05,
      "loss": 1.667,
      "step": 171
    },
    {
      "epoch": 0.029424343512103327,
      "grad_norm": 0.5842074155807495,
      "learning_rate": 1.4795789473684209e-05,
      "loss": 1.8684,
      "step": 172
    },
    {
      "epoch": 0.02959541527670858,
      "grad_norm": 0.6371638178825378,
      "learning_rate": 1.4267368421052632e-05,
      "loss": 1.932,
      "step": 173
    },
    {
      "epoch": 0.029766487041313832,
      "grad_norm": 0.6441742181777954,
      "learning_rate": 1.3738947368421053e-05,
      "loss": 1.8601,
      "step": 174
    },
    {
      "epoch": 0.029937558805919084,
      "grad_norm": 0.6196243762969971,
      "learning_rate": 1.3210526315789473e-05,
      "loss": 1.9612,
      "step": 175
    },
    {
      "epoch": 0.030108630570524333,
      "grad_norm": 0.6074597239494324,
      "learning_rate": 1.2682105263157896e-05,
      "loss": 1.8816,
      "step": 176
    },
    {
      "epoch": 0.030279702335129586,
      "grad_norm": 0.6216224431991577,
      "learning_rate": 1.2153684210526315e-05,
      "loss": 1.8326,
      "step": 177
    },
    {
      "epoch": 0.03045077409973484,
      "grad_norm": 0.6427397727966309,
      "learning_rate": 1.1625263157894737e-05,
      "loss": 1.65,
      "step": 178
    },
    {
      "epoch": 0.03062184586434009,
      "grad_norm": 0.7216449975967407,
      "learning_rate": 1.1096842105263158e-05,
      "loss": 1.9551,
      "step": 179
    },
    {
      "epoch": 0.030792917628945343,
      "grad_norm": 0.6623689532279968,
      "learning_rate": 1.0568421052631579e-05,
      "loss": 1.7214,
      "step": 180
    },
    {
      "epoch": 0.030963989393550596,
      "grad_norm": 1.0571134090423584,
      "learning_rate": 1.004e-05,
      "loss": 1.9657,
      "step": 181
    },
    {
      "epoch": 0.031135061158155845,
      "grad_norm": 0.7337217330932617,
      "learning_rate": 9.511578947368422e-06,
      "loss": 1.9204,
      "step": 182
    },
    {
      "epoch": 0.0313061329227611,
      "grad_norm": 0.8052051067352295,
      "learning_rate": 8.983157894736843e-06,
      "loss": 1.9703,
      "step": 183
    },
    {
      "epoch": 0.03147720468736635,
      "grad_norm": 0.8778511881828308,
      "learning_rate": 8.454736842105263e-06,
      "loss": 1.8453,
      "step": 184
    },
    {
      "epoch": 0.0316482764519716,
      "grad_norm": 0.8391135931015015,
      "learning_rate": 7.926315789473684e-06,
      "loss": 1.9047,
      "step": 185
    },
    {
      "epoch": 0.03181934821657685,
      "grad_norm": 0.8739292025566101,
      "learning_rate": 7.397894736842104e-06,
      "loss": 1.8505,
      "step": 186
    },
    {
      "epoch": 0.03199041998118211,
      "grad_norm": 0.9787918329238892,
      "learning_rate": 6.8694736842105265e-06,
      "loss": 1.9557,
      "step": 187
    },
    {
      "epoch": 0.032161491745787356,
      "grad_norm": 0.8386358022689819,
      "learning_rate": 6.341052631578948e-06,
      "loss": 1.9371,
      "step": 188
    },
    {
      "epoch": 0.03233256351039261,
      "grad_norm": 0.9877040982246399,
      "learning_rate": 5.812631578947368e-06,
      "loss": 1.945,
      "step": 189
    },
    {
      "epoch": 0.03250363527499786,
      "grad_norm": 0.8487772941589355,
      "learning_rate": 5.2842105263157896e-06,
      "loss": 2.0013,
      "step": 190
    },
    {
      "epoch": 0.03267470703960312,
      "grad_norm": 0.9981456995010376,
      "learning_rate": 4.755789473684211e-06,
      "loss": 2.1154,
      "step": 191
    },
    {
      "epoch": 0.032845778804208366,
      "grad_norm": 0.9859482049942017,
      "learning_rate": 4.227368421052631e-06,
      "loss": 1.6442,
      "step": 192
    },
    {
      "epoch": 0.033016850568813615,
      "grad_norm": 1.0620956420898438,
      "learning_rate": 3.698947368421052e-06,
      "loss": 2.079,
      "step": 193
    },
    {
      "epoch": 0.03318792233341887,
      "grad_norm": 1.0179574489593506,
      "learning_rate": 3.170526315789474e-06,
      "loss": 1.6924,
      "step": 194
    },
    {
      "epoch": 0.03335899409802412,
      "grad_norm": 1.1170974969863892,
      "learning_rate": 2.6421052631578948e-06,
      "loss": 2.0182,
      "step": 195
    },
    {
      "epoch": 0.033530065862629375,
      "grad_norm": 1.1970032453536987,
      "learning_rate": 2.1136842105263157e-06,
      "loss": 1.8493,
      "step": 196
    },
    {
      "epoch": 0.033701137627234624,
      "grad_norm": 1.5224543809890747,
      "learning_rate": 1.585263157894737e-06,
      "loss": 1.8961,
      "step": 197
    },
    {
      "epoch": 0.03387220939183987,
      "grad_norm": 1.648374319076538,
      "learning_rate": 1.0568421052631578e-06,
      "loss": 2.2679,
      "step": 198
    },
    {
      "epoch": 0.03404328115644513,
      "grad_norm": 1.8483800888061523,
      "learning_rate": 5.284210526315789e-07,
      "loss": 1.8236,
      "step": 199
    },
    {
      "epoch": 0.03421435292105038,
      "grad_norm": 2.218536615371704,
      "learning_rate": 0.0,
      "loss": 1.7512,
      "step": 200
    },
    {
      "epoch": 0.03421435292105038,
      "eval_loss": 1.8535966873168945,
      "eval_runtime": 473.8317,
      "eval_samples_per_second": 5.196,
      "eval_steps_per_second": 1.3,
      "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": 1.4129939313013555e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}