{
  "best_metric": 2.0822627544403076,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.04989190088142358,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003326126725428239,
      "grad_norm": 1.5779170989990234,
      "learning_rate": 1e-05,
      "loss": 2.578,
      "step": 1
    },
    {
      "epoch": 0.0003326126725428239,
      "eval_loss": 2.890110492706299,
      "eval_runtime": 143.2137,
      "eval_samples_per_second": 35.36,
      "eval_steps_per_second": 8.84,
      "step": 1
    },
    {
      "epoch": 0.0006652253450856477,
      "grad_norm": 1.942592740058899,
      "learning_rate": 2e-05,
      "loss": 2.6554,
      "step": 2
    },
    {
      "epoch": 0.0009978380176284716,
      "grad_norm": 2.1519877910614014,
      "learning_rate": 3e-05,
      "loss": 2.6751,
      "step": 3
    },
    {
      "epoch": 0.0013304506901712955,
      "grad_norm": 2.0223259925842285,
      "learning_rate": 4e-05,
      "loss": 2.7234,
      "step": 4
    },
    {
      "epoch": 0.0016630633627141194,
      "grad_norm": 2.1754114627838135,
      "learning_rate": 5e-05,
      "loss": 2.6795,
      "step": 5
    },
    {
      "epoch": 0.0019956760352569432,
      "grad_norm": 1.9673004150390625,
      "learning_rate": 6e-05,
      "loss": 2.5201,
      "step": 6
    },
    {
      "epoch": 0.002328288707799767,
      "grad_norm": 1.9511888027191162,
      "learning_rate": 7e-05,
      "loss": 2.6134,
      "step": 7
    },
    {
      "epoch": 0.002660901380342591,
      "grad_norm": 1.9460816383361816,
      "learning_rate": 8e-05,
      "loss": 2.5508,
      "step": 8
    },
    {
      "epoch": 0.002993514052885415,
      "grad_norm": 2.072754383087158,
      "learning_rate": 9e-05,
      "loss": 2.5035,
      "step": 9
    },
    {
      "epoch": 0.0033261267254282387,
      "grad_norm": 1.8564409017562866,
      "learning_rate": 0.0001,
      "loss": 2.4293,
      "step": 10
    },
    {
      "epoch": 0.0036587393979710626,
      "grad_norm": 1.9724938869476318,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.5721,
      "step": 11
    },
    {
      "epoch": 0.0039913520705138865,
      "grad_norm": 1.9574224948883057,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4073,
      "step": 12
    },
    {
      "epoch": 0.00432396474305671,
      "grad_norm": 2.2013673782348633,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.3064,
      "step": 13
    },
    {
      "epoch": 0.004656577415599534,
      "grad_norm": 2.178459405899048,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.341,
      "step": 14
    },
    {
      "epoch": 0.004989190088142358,
      "grad_norm": 2.1170661449432373,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.4502,
      "step": 15
    },
    {
      "epoch": 0.005321802760685182,
      "grad_norm": 2.190675973892212,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.3961,
      "step": 16
    },
    {
      "epoch": 0.005654415433228006,
      "grad_norm": 2.2960801124572754,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.5492,
      "step": 17
    },
    {
      "epoch": 0.00598702810577083,
      "grad_norm": 2.2598717212677,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.144,
      "step": 18
    },
    {
      "epoch": 0.006319640778313654,
      "grad_norm": 2.0504443645477295,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.2617,
      "step": 19
    },
    {
      "epoch": 0.0066522534508564775,
      "grad_norm": 2.1086559295654297,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.2074,
      "step": 20
    },
    {
      "epoch": 0.006984866123399301,
      "grad_norm": 2.138704538345337,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.1696,
      "step": 21
    },
    {
      "epoch": 0.007317478795942125,
      "grad_norm": 2.263592004776001,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.3905,
      "step": 22
    },
    {
      "epoch": 0.007650091468484949,
      "grad_norm": 2.0490214824676514,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.369,
      "step": 23
    },
    {
      "epoch": 0.007982704141027773,
      "grad_norm": 2.120150566101074,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.0843,
      "step": 24
    },
    {
      "epoch": 0.008315316813570598,
      "grad_norm": 2.1268203258514404,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.3661,
      "step": 25
    },
    {
      "epoch": 0.00864792948611342,
      "grad_norm": 2.0948963165283203,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.1879,
      "step": 26
    },
    {
      "epoch": 0.008980542158656245,
      "grad_norm": 2.2930335998535156,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.9811,
      "step": 27
    },
    {
      "epoch": 0.009313154831199068,
      "grad_norm": 2.029155969619751,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.9891,
      "step": 28
    },
    {
      "epoch": 0.009645767503741893,
      "grad_norm": 2.1162171363830566,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8595,
      "step": 29
    },
    {
      "epoch": 0.009978380176284716,
      "grad_norm": 2.0919315814971924,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.9611,
      "step": 30
    },
    {
      "epoch": 0.010310992848827541,
      "grad_norm": 2.2008674144744873,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.2932,
      "step": 31
    },
    {
      "epoch": 0.010643605521370364,
      "grad_norm": 2.4158740043640137,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.1525,
      "step": 32
    },
    {
      "epoch": 0.010976218193913189,
      "grad_norm": 2.352757215499878,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.1047,
      "step": 33
    },
    {
      "epoch": 0.011308830866456012,
      "grad_norm": 2.383190870285034,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.0044,
      "step": 34
    },
    {
      "epoch": 0.011641443538998836,
      "grad_norm": 2.3409194946289062,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.3371,
      "step": 35
    },
    {
      "epoch": 0.01197405621154166,
      "grad_norm": 2.489692211151123,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.2883,
      "step": 36
    },
    {
      "epoch": 0.012306668884084484,
      "grad_norm": 2.5469415187835693,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.9101,
      "step": 37
    },
    {
      "epoch": 0.012639281556627307,
      "grad_norm": 2.4313035011291504,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.8939,
      "step": 38
    },
    {
      "epoch": 0.012971894229170132,
      "grad_norm": 2.5194132328033447,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.9572,
      "step": 39
    },
    {
      "epoch": 0.013304506901712955,
      "grad_norm": 2.6455283164978027,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.9544,
      "step": 40
    },
    {
      "epoch": 0.01363711957425578,
      "grad_norm": 2.6215243339538574,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.0965,
      "step": 41
    },
    {
      "epoch": 0.013969732246798603,
      "grad_norm": 2.5845704078674316,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.1711,
      "step": 42
    },
    {
      "epoch": 0.014302344919341427,
      "grad_norm": 2.6958465576171875,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.9599,
      "step": 43
    },
    {
      "epoch": 0.01463495759188425,
      "grad_norm": 2.6708405017852783,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.1328,
      "step": 44
    },
    {
      "epoch": 0.014967570264427075,
      "grad_norm": 2.6289267539978027,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.8849,
      "step": 45
    },
    {
      "epoch": 0.015300182936969898,
      "grad_norm": 3.140578031539917,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.0067,
      "step": 46
    },
    {
      "epoch": 0.015632795609512723,
      "grad_norm": 3.0503008365631104,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.2709,
      "step": 47
    },
    {
      "epoch": 0.015965408282055546,
      "grad_norm": 3.050830841064453,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3409,
      "step": 48
    },
    {
      "epoch": 0.01629802095459837,
      "grad_norm": 3.448582649230957,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.2677,
      "step": 49
    },
    {
      "epoch": 0.016630633627141195,
      "grad_norm": 4.578643321990967,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.3374,
      "step": 50
    },
    {
      "epoch": 0.016630633627141195,
      "eval_loss": 2.4419381618499756,
      "eval_runtime": 143.8304,
      "eval_samples_per_second": 35.208,
      "eval_steps_per_second": 8.802,
      "step": 50
    },
    {
      "epoch": 0.01696324629968402,
      "grad_norm": 3.9427003860473633,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.916,
      "step": 51
    },
    {
      "epoch": 0.01729585897222684,
      "grad_norm": 4.049047470092773,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.9218,
      "step": 52
    },
    {
      "epoch": 0.017628471644769664,
      "grad_norm": 3.301952600479126,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.8823,
      "step": 53
    },
    {
      "epoch": 0.01796108431731249,
      "grad_norm": 2.565366744995117,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.7786,
      "step": 54
    },
    {
      "epoch": 0.018293696989855314,
      "grad_norm": 1.9284350872039795,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.6176,
      "step": 55
    },
    {
      "epoch": 0.018626309662398137,
      "grad_norm": 1.6514313220977783,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.6221,
      "step": 56
    },
    {
      "epoch": 0.01895892233494096,
      "grad_norm": 1.6821293830871582,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.5794,
      "step": 57
    },
    {
      "epoch": 0.019291535007483786,
      "grad_norm": 1.6589399576187134,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.4024,
      "step": 58
    },
    {
      "epoch": 0.01962414768002661,
      "grad_norm": 1.7105402946472168,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.3768,
      "step": 59
    },
    {
      "epoch": 0.019956760352569432,
      "grad_norm": 1.525919795036316,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.509,
      "step": 60
    },
    {
      "epoch": 0.020289373025112255,
      "grad_norm": 1.5568736791610718,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.3095,
      "step": 61
    },
    {
      "epoch": 0.020621985697655082,
      "grad_norm": 1.544844150543213,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.1774,
      "step": 62
    },
    {
      "epoch": 0.020954598370197905,
      "grad_norm": 1.5373493432998657,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.4096,
      "step": 63
    },
    {
      "epoch": 0.021287211042740728,
      "grad_norm": 1.7022396326065063,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.0818,
      "step": 64
    },
    {
      "epoch": 0.02161982371528355,
      "grad_norm": 1.7093448638916016,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.2859,
      "step": 65
    },
    {
      "epoch": 0.021952436387826377,
      "grad_norm": 1.7917174100875854,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.1643,
      "step": 66
    },
    {
      "epoch": 0.0222850490603692,
      "grad_norm": 1.6668987274169922,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0675,
      "step": 67
    },
    {
      "epoch": 0.022617661732912023,
      "grad_norm": 1.6066144704818726,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.0654,
      "step": 68
    },
    {
      "epoch": 0.022950274405454846,
      "grad_norm": 1.6282004117965698,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.0247,
      "step": 69
    },
    {
      "epoch": 0.023282887077997673,
      "grad_norm": 1.655032992362976,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.2264,
      "step": 70
    },
    {
      "epoch": 0.023615499750540496,
      "grad_norm": 1.6748640537261963,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.9976,
      "step": 71
    },
    {
      "epoch": 0.02394811242308332,
      "grad_norm": 1.7039382457733154,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.1503,
      "step": 72
    },
    {
      "epoch": 0.024280725095626142,
      "grad_norm": 1.5381526947021484,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.2606,
      "step": 73
    },
    {
      "epoch": 0.02461333776816897,
      "grad_norm": 1.7283302545547485,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.031,
      "step": 74
    },
    {
      "epoch": 0.02494595044071179,
      "grad_norm": 1.8382872343063354,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.1637,
      "step": 75
    },
    {
      "epoch": 0.025278563113254614,
      "grad_norm": 1.7266231775283813,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.9744,
      "step": 76
    },
    {
      "epoch": 0.025611175785797437,
      "grad_norm": 1.7093006372451782,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.8992,
      "step": 77
    },
    {
      "epoch": 0.025943788458340264,
      "grad_norm": 1.7118191719055176,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.9792,
      "step": 78
    },
    {
      "epoch": 0.026276401130883087,
      "grad_norm": 1.8484402894973755,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.806,
      "step": 79
    },
    {
      "epoch": 0.02660901380342591,
      "grad_norm": 1.876543641090393,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.0128,
      "step": 80
    },
    {
      "epoch": 0.026941626475968733,
      "grad_norm": 2.1587491035461426,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.1131,
      "step": 81
    },
    {
      "epoch": 0.02727423914851156,
      "grad_norm": 1.7994778156280518,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.0639,
      "step": 82
    },
    {
      "epoch": 0.027606851821054382,
      "grad_norm": 1.8916665315628052,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.0266,
      "step": 83
    },
    {
      "epoch": 0.027939464493597205,
      "grad_norm": 1.9809986352920532,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.1777,
      "step": 84
    },
    {
      "epoch": 0.02827207716614003,
      "grad_norm": 1.9533638954162598,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.1803,
      "step": 85
    },
    {
      "epoch": 0.028604689838682855,
      "grad_norm": 1.9945489168167114,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.0768,
      "step": 86
    },
    {
      "epoch": 0.028937302511225678,
      "grad_norm": 1.9451024532318115,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.9837,
      "step": 87
    },
    {
      "epoch": 0.0292699151837685,
      "grad_norm": 2.1750686168670654,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.0869,
      "step": 88
    },
    {
      "epoch": 0.029602527856311324,
      "grad_norm": 1.9105833768844604,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.9622,
      "step": 89
    },
    {
      "epoch": 0.02993514052885415,
      "grad_norm": 2.1066477298736572,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0641,
      "step": 90
    },
    {
      "epoch": 0.030267753201396973,
      "grad_norm": 2.303431272506714,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.9929,
      "step": 91
    },
    {
      "epoch": 0.030600365873939796,
      "grad_norm": 2.4638309478759766,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.9753,
      "step": 92
    },
    {
      "epoch": 0.03093297854648262,
      "grad_norm": 2.31965970993042,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.6215,
      "step": 93
    },
    {
      "epoch": 0.031265591219025446,
      "grad_norm": 2.359222412109375,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.9149,
      "step": 94
    },
    {
      "epoch": 0.03159820389156827,
      "grad_norm": 2.524587631225586,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.0632,
      "step": 95
    },
    {
      "epoch": 0.03193081656411109,
      "grad_norm": 2.571028232574463,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.9691,
      "step": 96
    },
    {
      "epoch": 0.032263429236653915,
      "grad_norm": 2.6425232887268066,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.064,
      "step": 97
    },
    {
      "epoch": 0.03259604190919674,
      "grad_norm": 2.4869885444641113,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.988,
      "step": 98
    },
    {
      "epoch": 0.03292865458173956,
      "grad_norm": 2.8188388347625732,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.2323,
      "step": 99
    },
    {
      "epoch": 0.03326126725428239,
      "grad_norm": 3.6765828132629395,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.1146,
      "step": 100
    },
    {
      "epoch": 0.03326126725428239,
      "eval_loss": 2.176445245742798,
      "eval_runtime": 144.0142,
      "eval_samples_per_second": 35.163,
      "eval_steps_per_second": 8.791,
      "step": 100
    },
    {
      "epoch": 0.033593879926825214,
      "grad_norm": 1.998793601989746,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.7214,
      "step": 101
    },
    {
      "epoch": 0.03392649259936804,
      "grad_norm": 2.4588496685028076,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.5049,
      "step": 102
    },
    {
      "epoch": 0.03425910527191086,
      "grad_norm": 2.194648027420044,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.4729,
      "step": 103
    },
    {
      "epoch": 0.03459171794445368,
      "grad_norm": 1.8511162996292114,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.4895,
      "step": 104
    },
    {
      "epoch": 0.034924330616996506,
      "grad_norm": 1.4428975582122803,
      "learning_rate": 5e-05,
      "loss": 2.2717,
      "step": 105
    },
    {
      "epoch": 0.03525694328953933,
      "grad_norm": 1.228561282157898,
      "learning_rate": 4.917330276168208e-05,
      "loss": 2.4998,
      "step": 106
    },
    {
      "epoch": 0.03558955596208215,
      "grad_norm": 1.4488962888717651,
      "learning_rate": 4.834683153413459e-05,
      "loss": 2.2597,
      "step": 107
    },
    {
      "epoch": 0.03592216863462498,
      "grad_norm": 1.5021672248840332,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.4591,
      "step": 108
    },
    {
      "epoch": 0.036254781307167805,
      "grad_norm": 1.6298645734786987,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.3154,
      "step": 109
    },
    {
      "epoch": 0.03658739397971063,
      "grad_norm": 1.3568925857543945,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.2506,
      "step": 110
    },
    {
      "epoch": 0.03692000665225345,
      "grad_norm": 1.3625819683074951,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.106,
      "step": 111
    },
    {
      "epoch": 0.037252619324796274,
      "grad_norm": 1.351493000984192,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.1529,
      "step": 112
    },
    {
      "epoch": 0.0375852319973391,
      "grad_norm": 1.3277156352996826,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.243,
      "step": 113
    },
    {
      "epoch": 0.03791784466988192,
      "grad_norm": 1.325668454170227,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.211,
      "step": 114
    },
    {
      "epoch": 0.03825045734242474,
      "grad_norm": 1.480718970298767,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.8159,
      "step": 115
    },
    {
      "epoch": 0.03858307001496757,
      "grad_norm": 1.3680843114852905,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.9483,
      "step": 116
    },
    {
      "epoch": 0.038915682687510396,
      "grad_norm": 1.484681248664856,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.2424,
      "step": 117
    },
    {
      "epoch": 0.03924829536005322,
      "grad_norm": 1.536088466644287,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.1566,
      "step": 118
    },
    {
      "epoch": 0.03958090803259604,
      "grad_norm": 1.6112810373306274,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.9328,
      "step": 119
    },
    {
      "epoch": 0.039913520705138865,
      "grad_norm": 1.5569220781326294,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.0705,
      "step": 120
    },
    {
      "epoch": 0.04024613337768169,
      "grad_norm": 1.5234591960906982,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.2097,
      "step": 121
    },
    {
      "epoch": 0.04057874605022451,
      "grad_norm": 1.6455223560333252,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.1279,
      "step": 122
    },
    {
      "epoch": 0.04091135872276734,
      "grad_norm": 1.6205483675003052,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.9357,
      "step": 123
    },
    {
      "epoch": 0.041243971395310164,
      "grad_norm": 1.6855875253677368,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0906,
      "step": 124
    },
    {
      "epoch": 0.04157658406785299,
      "grad_norm": 1.7553452253341675,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.2243,
      "step": 125
    },
    {
      "epoch": 0.04190919674039581,
      "grad_norm": 1.6811223030090332,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.9301,
      "step": 126
    },
    {
      "epoch": 0.04224180941293863,
      "grad_norm": 1.6491084098815918,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.8464,
      "step": 127
    },
    {
      "epoch": 0.042574422085481456,
      "grad_norm": 1.565740942955017,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.9936,
      "step": 128
    },
    {
      "epoch": 0.04290703475802428,
      "grad_norm": 1.837349772453308,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.9729,
      "step": 129
    },
    {
      "epoch": 0.0432396474305671,
      "grad_norm": 1.8257746696472168,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.2617,
      "step": 130
    },
    {
      "epoch": 0.04357226010310993,
      "grad_norm": 1.6786108016967773,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.8207,
      "step": 131
    },
    {
      "epoch": 0.043904872775652755,
      "grad_norm": 1.8182679414749146,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.9,
      "step": 132
    },
    {
      "epoch": 0.04423748544819558,
      "grad_norm": 1.652309536933899,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.9442,
      "step": 133
    },
    {
      "epoch": 0.0445700981207384,
      "grad_norm": 1.9106497764587402,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.2015,
      "step": 134
    },
    {
      "epoch": 0.044902710793281224,
      "grad_norm": 1.961530327796936,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.2928,
      "step": 135
    },
    {
      "epoch": 0.04523532346582405,
      "grad_norm": 2.0776307582855225,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.8769,
      "step": 136
    },
    {
      "epoch": 0.04556793613836687,
      "grad_norm": 1.9557079076766968,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.9413,
      "step": 137
    },
    {
      "epoch": 0.04590054881090969,
      "grad_norm": 1.9496510028839111,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.8803,
      "step": 138
    },
    {
      "epoch": 0.04623316148345252,
      "grad_norm": 2.051219940185547,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.8867,
      "step": 139
    },
    {
      "epoch": 0.046565774155995346,
      "grad_norm": 2.008782148361206,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.8479,
      "step": 140
    },
    {
      "epoch": 0.04689838682853817,
      "grad_norm": 2.098451614379883,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.7784,
      "step": 141
    },
    {
      "epoch": 0.04723099950108099,
      "grad_norm": 2.2503504753112793,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.8965,
      "step": 142
    },
    {
      "epoch": 0.047563612173623815,
      "grad_norm": 2.399078130722046,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0964,
      "step": 143
    },
    {
      "epoch": 0.04789622484616664,
      "grad_norm": 2.40899395942688,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.9883,
      "step": 144
    },
    {
      "epoch": 0.04822883751870946,
      "grad_norm": 2.327549457550049,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.5362,
      "step": 145
    },
    {
      "epoch": 0.048561450191252284,
      "grad_norm": 2.6798768043518066,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.0726,
      "step": 146
    },
    {
      "epoch": 0.048894062863795114,
      "grad_norm": 2.894099235534668,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.975,
      "step": 147
    },
    {
      "epoch": 0.04922667553633794,
      "grad_norm": 3.2005791664123535,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.8293,
      "step": 148
    },
    {
      "epoch": 0.04955928820888076,
      "grad_norm": 2.8304784297943115,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.9556,
      "step": 149
    },
    {
      "epoch": 0.04989190088142358,
      "grad_norm": 3.975761890411377,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.0097,
      "step": 150
    },
    {
      "epoch": 0.04989190088142358,
      "eval_loss": 2.0822627544403076,
      "eval_runtime": 144.2293,
      "eval_samples_per_second": 35.111,
      "eval_steps_per_second": 8.778,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.205054648339661e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}