{
  "best_metric": 0.5686683736744995,
  "best_model_checkpoint": "/data0/checkpoints/Qwen2.5-Math-7B-ScalePRM-v3.3/checkpoint-400",
  "epoch": 0.9995943204868154,
  "eval_steps": 100,
  "global_step": 1540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006490872210953347,
      "grad_norm": 2.605618476867676,
      "learning_rate": 7e-06,
      "loss": 1.1423,
      "step": 1
    },
    {
      "epoch": 0.0012981744421906693,
      "grad_norm": 1.9402536153793335,
      "learning_rate": 7e-06,
      "loss": 1.0,
      "step": 2
    },
    {
      "epoch": 0.001947261663286004,
      "grad_norm": 1.08159339427948,
      "learning_rate": 7e-06,
      "loss": 0.8091,
      "step": 3
    },
    {
      "epoch": 0.0025963488843813386,
      "grad_norm": 0.8678656816482544,
      "learning_rate": 7e-06,
      "loss": 3.1376,
      "step": 4
    },
    {
      "epoch": 0.0032454361054766734,
      "grad_norm": 0.9116173386573792,
      "learning_rate": 7e-06,
      "loss": 2.2859,
      "step": 5
    },
    {
      "epoch": 0.003894523326572008,
      "grad_norm": 0.8966250419616699,
      "learning_rate": 7e-06,
      "loss": 2.3023,
      "step": 6
    },
    {
      "epoch": 0.004543610547667343,
      "grad_norm": 0.610904335975647,
      "learning_rate": 7e-06,
      "loss": 1.9812,
      "step": 7
    },
    {
      "epoch": 0.005192697768762677,
      "grad_norm": 0.5735733509063721,
      "learning_rate": 7e-06,
      "loss": 1.7649,
      "step": 8
    },
    {
      "epoch": 0.0058417849898580124,
      "grad_norm": 0.4209045469760895,
      "learning_rate": 7e-06,
      "loss": 1.1464,
      "step": 9
    },
    {
      "epoch": 0.006490872210953347,
      "grad_norm": 0.3616688847541809,
      "learning_rate": 7e-06,
      "loss": 1.7947,
      "step": 10
    },
    {
      "epoch": 0.007139959432048682,
      "grad_norm": 0.7953066825866699,
      "learning_rate": 7e-06,
      "loss": 0.9352,
      "step": 11
    },
    {
      "epoch": 0.007789046653144016,
      "grad_norm": 0.5078253746032715,
      "learning_rate": 7e-06,
      "loss": 0.7498,
      "step": 12
    },
    {
      "epoch": 0.008438133874239351,
      "grad_norm": 0.3091255724430084,
      "learning_rate": 7e-06,
      "loss": 0.4489,
      "step": 13
    },
    {
      "epoch": 0.009087221095334686,
      "grad_norm": 0.2803177237510681,
      "learning_rate": 7e-06,
      "loss": 0.7401,
      "step": 14
    },
    {
      "epoch": 0.00973630831643002,
      "grad_norm": 0.39973577857017517,
      "learning_rate": 7e-06,
      "loss": 2.1559,
      "step": 15
    },
    {
      "epoch": 0.010385395537525354,
      "grad_norm": 0.26134350895881653,
      "learning_rate": 7e-06,
      "loss": 0.5338,
      "step": 16
    },
    {
      "epoch": 0.011034482758620689,
      "grad_norm": 0.41533222794532776,
      "learning_rate": 7e-06,
      "loss": 0.5028,
      "step": 17
    },
    {
      "epoch": 0.011683569979716025,
      "grad_norm": 0.1823364496231079,
      "learning_rate": 7e-06,
      "loss": 0.7632,
      "step": 18
    },
    {
      "epoch": 0.01233265720081136,
      "grad_norm": 0.24924695491790771,
      "learning_rate": 7e-06,
      "loss": 0.4132,
      "step": 19
    },
    {
      "epoch": 0.012981744421906694,
      "grad_norm": 0.37526997923851013,
      "learning_rate": 7e-06,
      "loss": 0.4098,
      "step": 20
    },
    {
      "epoch": 0.013630831643002028,
      "grad_norm": 0.2427705079317093,
      "learning_rate": 7e-06,
      "loss": 0.439,
      "step": 21
    },
    {
      "epoch": 0.014279918864097364,
      "grad_norm": 0.3296060860157013,
      "learning_rate": 7e-06,
      "loss": 0.3626,
      "step": 22
    },
    {
      "epoch": 0.014929006085192698,
      "grad_norm": 0.21128149330615997,
      "learning_rate": 7e-06,
      "loss": 0.4329,
      "step": 23
    },
    {
      "epoch": 0.015578093306288033,
      "grad_norm": 0.1735735982656479,
      "learning_rate": 7e-06,
      "loss": 0.4906,
      "step": 24
    },
    {
      "epoch": 0.016227180527383367,
      "grad_norm": 0.26841220259666443,
      "learning_rate": 7e-06,
      "loss": 0.5905,
      "step": 25
    },
    {
      "epoch": 0.016876267748478703,
      "grad_norm": 0.24791638553142548,
      "learning_rate": 7e-06,
      "loss": 0.4459,
      "step": 26
    },
    {
      "epoch": 0.017525354969574036,
      "grad_norm": 0.26500746607780457,
      "learning_rate": 7e-06,
      "loss": 0.3965,
      "step": 27
    },
    {
      "epoch": 0.01817444219066937,
      "grad_norm": 0.16852189600467682,
      "learning_rate": 7e-06,
      "loss": 0.3598,
      "step": 28
    },
    {
      "epoch": 0.018823529411764704,
      "grad_norm": 0.2144036740064621,
      "learning_rate": 7e-06,
      "loss": 0.3755,
      "step": 29
    },
    {
      "epoch": 0.01947261663286004,
      "grad_norm": 0.1435825079679489,
      "learning_rate": 7e-06,
      "loss": 0.3722,
      "step": 30
    },
    {
      "epoch": 0.020121703853955376,
      "grad_norm": 0.19116070866584778,
      "learning_rate": 7e-06,
      "loss": 0.4265,
      "step": 31
    },
    {
      "epoch": 0.02077079107505071,
      "grad_norm": 0.15488632023334503,
      "learning_rate": 7e-06,
      "loss": 0.3086,
      "step": 32
    },
    {
      "epoch": 0.021419878296146045,
      "grad_norm": 0.14452320337295532,
      "learning_rate": 7e-06,
      "loss": 0.3455,
      "step": 33
    },
    {
      "epoch": 0.022068965517241378,
      "grad_norm": 0.1810225397348404,
      "learning_rate": 7e-06,
      "loss": 0.3874,
      "step": 34
    },
    {
      "epoch": 0.022718052738336714,
      "grad_norm": 0.18408165872097015,
      "learning_rate": 7e-06,
      "loss": 0.37,
      "step": 35
    },
    {
      "epoch": 0.02336713995943205,
      "grad_norm": 0.1539960354566574,
      "learning_rate": 7e-06,
      "loss": 0.3825,
      "step": 36
    },
    {
      "epoch": 0.024016227180527382,
      "grad_norm": 0.12805905938148499,
      "learning_rate": 7e-06,
      "loss": 0.3608,
      "step": 37
    },
    {
      "epoch": 0.02466531440162272,
      "grad_norm": 0.1480168104171753,
      "learning_rate": 7e-06,
      "loss": 0.3706,
      "step": 38
    },
    {
      "epoch": 0.025314401622718054,
      "grad_norm": 0.17585790157318115,
      "learning_rate": 7e-06,
      "loss": 0.3515,
      "step": 39
    },
    {
      "epoch": 0.025963488843813387,
      "grad_norm": 0.12918131053447723,
      "learning_rate": 7e-06,
      "loss": 0.3391,
      "step": 40
    },
    {
      "epoch": 0.026612576064908723,
      "grad_norm": 0.15384109318256378,
      "learning_rate": 7e-06,
      "loss": 0.3686,
      "step": 41
    },
    {
      "epoch": 0.027261663286004056,
      "grad_norm": 0.1404956877231598,
      "learning_rate": 7e-06,
      "loss": 0.3201,
      "step": 42
    },
    {
      "epoch": 0.027910750507099392,
      "grad_norm": 0.16374953091144562,
      "learning_rate": 7e-06,
      "loss": 0.4096,
      "step": 43
    },
    {
      "epoch": 0.028559837728194728,
      "grad_norm": 0.11714208871126175,
      "learning_rate": 7e-06,
      "loss": 0.2623,
      "step": 44
    },
    {
      "epoch": 0.02920892494929006,
      "grad_norm": 0.16720964014530182,
      "learning_rate": 7e-06,
      "loss": 0.3636,
      "step": 45
    },
    {
      "epoch": 0.029858012170385397,
      "grad_norm": 0.16197560727596283,
      "learning_rate": 7e-06,
      "loss": 0.3581,
      "step": 46
    },
    {
      "epoch": 0.03050709939148073,
      "grad_norm": 0.15842324495315552,
      "learning_rate": 7e-06,
      "loss": 0.3229,
      "step": 47
    },
    {
      "epoch": 0.031156186612576065,
      "grad_norm": 0.1189582347869873,
      "learning_rate": 7e-06,
      "loss": 0.3173,
      "step": 48
    },
    {
      "epoch": 0.0318052738336714,
      "grad_norm": 0.12760001420974731,
      "learning_rate": 7e-06,
      "loss": 0.3407,
      "step": 49
    },
    {
      "epoch": 0.032454361054766734,
      "grad_norm": 0.1296093910932541,
      "learning_rate": 7e-06,
      "loss": 0.3685,
      "step": 50
    },
    {
      "epoch": 0.03310344827586207,
      "grad_norm": 0.16701029241085052,
      "learning_rate": 7e-06,
      "loss": 0.3713,
      "step": 51
    },
    {
      "epoch": 0.033752535496957406,
      "grad_norm": 0.24331678450107574,
      "learning_rate": 7e-06,
      "loss": 0.3778,
      "step": 52
    },
    {
      "epoch": 0.034401622718052735,
      "grad_norm": 0.12526199221611023,
      "learning_rate": 7e-06,
      "loss": 0.3508,
      "step": 53
    },
    {
      "epoch": 0.03505070993914807,
      "grad_norm": 0.1313614398241043,
      "learning_rate": 7e-06,
      "loss": 0.351,
      "step": 54
    },
    {
      "epoch": 0.03569979716024341,
      "grad_norm": 0.19062532484531403,
      "learning_rate": 7e-06,
      "loss": 0.2639,
      "step": 55
    },
    {
      "epoch": 0.03634888438133874,
      "grad_norm": 0.12752769887447357,
      "learning_rate": 7e-06,
      "loss": 0.3049,
      "step": 56
    },
    {
      "epoch": 0.03699797160243408,
      "grad_norm": 0.2414279282093048,
      "learning_rate": 7e-06,
      "loss": 0.4129,
      "step": 57
    },
    {
      "epoch": 0.03764705882352941,
      "grad_norm": 0.20003190636634827,
      "learning_rate": 7e-06,
      "loss": 0.3825,
      "step": 58
    },
    {
      "epoch": 0.038296146044624745,
      "grad_norm": 0.1120191216468811,
      "learning_rate": 7e-06,
      "loss": 0.4765,
      "step": 59
    },
    {
      "epoch": 0.03894523326572008,
      "grad_norm": 0.13277995586395264,
      "learning_rate": 7e-06,
      "loss": 0.3491,
      "step": 60
    },
    {
      "epoch": 0.03959432048681542,
      "grad_norm": 0.10169010609388351,
      "learning_rate": 7e-06,
      "loss": 0.2875,
      "step": 61
    },
    {
      "epoch": 0.04024340770791075,
      "grad_norm": 0.1307103931903839,
      "learning_rate": 7e-06,
      "loss": 0.3762,
      "step": 62
    },
    {
      "epoch": 0.04089249492900608,
      "grad_norm": 0.19338756799697876,
      "learning_rate": 7e-06,
      "loss": 0.3725,
      "step": 63
    },
    {
      "epoch": 0.04154158215010142,
      "grad_norm": 0.15607407689094543,
      "learning_rate": 7e-06,
      "loss": 0.3653,
      "step": 64
    },
    {
      "epoch": 0.042190669371196754,
      "grad_norm": 0.15056991577148438,
      "learning_rate": 7e-06,
      "loss": 0.3118,
      "step": 65
    },
    {
      "epoch": 0.04283975659229209,
      "grad_norm": 0.12061445415019989,
      "learning_rate": 7e-06,
      "loss": 0.3387,
      "step": 66
    },
    {
      "epoch": 0.043488843813387426,
      "grad_norm": 0.11278267949819565,
      "learning_rate": 7e-06,
      "loss": 0.3084,
      "step": 67
    },
    {
      "epoch": 0.044137931034482755,
      "grad_norm": 0.12167137861251831,
      "learning_rate": 7e-06,
      "loss": 0.2903,
      "step": 68
    },
    {
      "epoch": 0.04478701825557809,
      "grad_norm": 0.10986174643039703,
      "learning_rate": 7e-06,
      "loss": 0.3093,
      "step": 69
    },
    {
      "epoch": 0.04543610547667343,
      "grad_norm": 0.09558993577957153,
      "learning_rate": 7e-06,
      "loss": 0.3086,
      "step": 70
    },
    {
      "epoch": 0.04608519269776876,
      "grad_norm": 0.13920257985591888,
      "learning_rate": 7e-06,
      "loss": 0.3049,
      "step": 71
    },
    {
      "epoch": 0.0467342799188641,
      "grad_norm": 0.1563066989183426,
      "learning_rate": 7e-06,
      "loss": 0.249,
      "step": 72
    },
    {
      "epoch": 0.04738336713995943,
      "grad_norm": 0.21394313871860504,
      "learning_rate": 7e-06,
      "loss": 0.3705,
      "step": 73
    },
    {
      "epoch": 0.048032454361054765,
      "grad_norm": 0.11275743693113327,
      "learning_rate": 7e-06,
      "loss": 0.3034,
      "step": 74
    },
    {
      "epoch": 0.0486815415821501,
      "grad_norm": 0.10393211245536804,
      "learning_rate": 7e-06,
      "loss": 0.3149,
      "step": 75
    },
    {
      "epoch": 0.04933062880324544,
      "grad_norm": 0.1534319818019867,
      "learning_rate": 7e-06,
      "loss": 0.3588,
      "step": 76
    },
    {
      "epoch": 0.04997971602434077,
      "grad_norm": 0.09811252355575562,
      "learning_rate": 7e-06,
      "loss": 0.3007,
      "step": 77
    },
    {
      "epoch": 0.05062880324543611,
      "grad_norm": 0.12849706411361694,
      "learning_rate": 7e-06,
      "loss": 0.3388,
      "step": 78
    },
    {
      "epoch": 0.05127789046653144,
      "grad_norm": 0.13834285736083984,
      "learning_rate": 7e-06,
      "loss": 0.3386,
      "step": 79
    },
    {
      "epoch": 0.051926977687626774,
      "grad_norm": 0.1048542931675911,
      "learning_rate": 7e-06,
      "loss": 0.3033,
      "step": 80
    },
    {
      "epoch": 0.05257606490872211,
      "grad_norm": 0.09314683079719543,
      "learning_rate": 7e-06,
      "loss": 0.308,
      "step": 81
    },
    {
      "epoch": 0.053225152129817446,
      "grad_norm": 0.11881392449140549,
      "learning_rate": 7e-06,
      "loss": 0.3469,
      "step": 82
    },
    {
      "epoch": 0.05387423935091278,
      "grad_norm": 0.1190212219953537,
      "learning_rate": 7e-06,
      "loss": 0.3266,
      "step": 83
    },
    {
      "epoch": 0.05452332657200811,
      "grad_norm": 0.11753913015127182,
      "learning_rate": 7e-06,
      "loss": 0.3152,
      "step": 84
    },
    {
      "epoch": 0.05517241379310345,
      "grad_norm": 0.15811170637607574,
      "learning_rate": 7e-06,
      "loss": 0.3658,
      "step": 85
    },
    {
      "epoch": 0.055821501014198784,
      "grad_norm": 0.14433743059635162,
      "learning_rate": 7e-06,
      "loss": 0.3266,
      "step": 86
    },
    {
      "epoch": 0.05647058823529412,
      "grad_norm": 0.11464518308639526,
      "learning_rate": 7e-06,
      "loss": 0.2743,
      "step": 87
    },
    {
      "epoch": 0.057119675456389456,
      "grad_norm": 0.1384597271680832,
      "learning_rate": 7e-06,
      "loss": 0.3297,
      "step": 88
    },
    {
      "epoch": 0.057768762677484785,
      "grad_norm": 0.15001173317432404,
      "learning_rate": 7e-06,
      "loss": 0.3301,
      "step": 89
    },
    {
      "epoch": 0.05841784989858012,
      "grad_norm": 0.10919518023729324,
      "learning_rate": 7e-06,
      "loss": 0.3166,
      "step": 90
    },
    {
      "epoch": 0.05906693711967546,
      "grad_norm": 0.144393190741539,
      "learning_rate": 7e-06,
      "loss": 0.3497,
      "step": 91
    },
    {
      "epoch": 0.05971602434077079,
      "grad_norm": 0.2069811075925827,
      "learning_rate": 7e-06,
      "loss": 0.34,
      "step": 92
    },
    {
      "epoch": 0.06036511156186613,
      "grad_norm": 0.1933463215827942,
      "learning_rate": 7e-06,
      "loss": 0.3629,
      "step": 93
    },
    {
      "epoch": 0.06101419878296146,
      "grad_norm": 0.12894108891487122,
      "learning_rate": 7e-06,
      "loss": 0.3296,
      "step": 94
    },
    {
      "epoch": 0.061663286004056794,
      "grad_norm": 0.12639354169368744,
      "learning_rate": 7e-06,
      "loss": 0.3151,
      "step": 95
    },
    {
      "epoch": 0.06231237322515213,
      "grad_norm": 0.22299544513225555,
      "learning_rate": 7e-06,
      "loss": 0.2762,
      "step": 96
    },
    {
      "epoch": 0.06296146044624747,
      "grad_norm": 0.17379900813102722,
      "learning_rate": 7e-06,
      "loss": 0.2921,
      "step": 97
    },
    {
      "epoch": 0.0636105476673428,
      "grad_norm": 0.1413554698228836,
      "learning_rate": 7e-06,
      "loss": 0.3024,
      "step": 98
    },
    {
      "epoch": 0.06425963488843814,
      "grad_norm": 0.10786271095275879,
      "learning_rate": 7e-06,
      "loss": 0.3024,
      "step": 99
    },
    {
      "epoch": 0.06490872210953347,
      "grad_norm": 0.09833195060491562,
      "learning_rate": 7e-06,
      "loss": 0.2787,
      "step": 100
    },
    {
      "epoch": 0.06490872210953347,
      "eval_correct_accuracy": 0.6632739609838847,
      "eval_error_accuracy": 0.3971184151283206,
      "eval_f1": 0.4967940360860014,
      "eval_loss": 0.39497673511505127,
      "eval_runtime": 35.1463,
      "eval_samples_per_second": 96.738,
      "eval_steps_per_second": 6.06,
      "step": 100
    },
    {
      "epoch": 0.0655578093306288,
      "grad_norm": 0.15995395183563232,
      "learning_rate": 7e-06,
      "loss": 0.292,
      "step": 101
    },
    {
      "epoch": 0.06620689655172414,
      "grad_norm": 0.24531637132167816,
      "learning_rate": 7e-06,
      "loss": 0.3407,
      "step": 102
    },
    {
      "epoch": 0.06685598377281947,
      "grad_norm": 0.19325831532478333,
      "learning_rate": 7e-06,
      "loss": 0.3295,
      "step": 103
    },
    {
      "epoch": 0.06750507099391481,
      "grad_norm": 0.11924800276756287,
      "learning_rate": 7e-06,
      "loss": 0.2777,
      "step": 104
    },
    {
      "epoch": 0.06815415821501014,
      "grad_norm": 0.20181912183761597,
      "learning_rate": 7e-06,
      "loss": 0.2433,
      "step": 105
    },
    {
      "epoch": 0.06880324543610547,
      "grad_norm": 0.11877916008234024,
      "learning_rate": 7e-06,
      "loss": 0.2894,
      "step": 106
    },
    {
      "epoch": 0.06945233265720081,
      "grad_norm": 0.20285864174365997,
      "learning_rate": 7e-06,
      "loss": 0.2685,
      "step": 107
    },
    {
      "epoch": 0.07010141987829614,
      "grad_norm": 0.13427376747131348,
      "learning_rate": 7e-06,
      "loss": 0.2626,
      "step": 108
    },
    {
      "epoch": 0.07075050709939149,
      "grad_norm": 0.09942203015089035,
      "learning_rate": 7e-06,
      "loss": 0.2387,
      "step": 109
    },
    {
      "epoch": 0.07139959432048681,
      "grad_norm": 0.14841444790363312,
      "learning_rate": 7e-06,
      "loss": 0.2582,
      "step": 110
    },
    {
      "epoch": 0.07204868154158214,
      "grad_norm": 0.1889454573392868,
      "learning_rate": 7e-06,
      "loss": 0.3129,
      "step": 111
    },
    {
      "epoch": 0.07269776876267749,
      "grad_norm": 0.16890235245227814,
      "learning_rate": 7e-06,
      "loss": 0.302,
      "step": 112
    },
    {
      "epoch": 0.07334685598377282,
      "grad_norm": 0.18279609084129333,
      "learning_rate": 7e-06,
      "loss": 0.2915,
      "step": 113
    },
    {
      "epoch": 0.07399594320486816,
      "grad_norm": 0.12783527374267578,
      "learning_rate": 7e-06,
      "loss": 0.2863,
      "step": 114
    },
    {
      "epoch": 0.07464503042596349,
      "grad_norm": 0.13676981627941132,
      "learning_rate": 7e-06,
      "loss": 0.2755,
      "step": 115
    },
    {
      "epoch": 0.07529411764705882,
      "grad_norm": 0.15773960947990417,
      "learning_rate": 7e-06,
      "loss": 0.3527,
      "step": 116
    },
    {
      "epoch": 0.07594320486815416,
      "grad_norm": 0.17917655408382416,
      "learning_rate": 7e-06,
      "loss": 0.2399,
      "step": 117
    },
    {
      "epoch": 0.07659229208924949,
      "grad_norm": 0.1808365285396576,
      "learning_rate": 7e-06,
      "loss": 0.3001,
      "step": 118
    },
    {
      "epoch": 0.07724137931034483,
      "grad_norm": 0.09630057960748672,
      "learning_rate": 7e-06,
      "loss": 0.2831,
      "step": 119
    },
    {
      "epoch": 0.07789046653144016,
      "grad_norm": 0.1493607759475708,
      "learning_rate": 7e-06,
      "loss": 0.3036,
      "step": 120
    },
    {
      "epoch": 0.07853955375253549,
      "grad_norm": 0.13922396302223206,
      "learning_rate": 7e-06,
      "loss": 0.2355,
      "step": 121
    },
    {
      "epoch": 0.07918864097363083,
      "grad_norm": 0.10402022302150726,
      "learning_rate": 7e-06,
      "loss": 0.2708,
      "step": 122
    },
    {
      "epoch": 0.07983772819472616,
      "grad_norm": 0.09860780090093613,
      "learning_rate": 7e-06,
      "loss": 0.2586,
      "step": 123
    },
    {
      "epoch": 0.0804868154158215,
      "grad_norm": 0.13742424547672272,
      "learning_rate": 7e-06,
      "loss": 0.2938,
      "step": 124
    },
    {
      "epoch": 0.08113590263691683,
      "grad_norm": 0.15696093440055847,
      "learning_rate": 7e-06,
      "loss": 0.2808,
      "step": 125
    },
    {
      "epoch": 0.08178498985801216,
      "grad_norm": 0.15960349142551422,
      "learning_rate": 7e-06,
      "loss": 0.2745,
      "step": 126
    },
    {
      "epoch": 0.0824340770791075,
      "grad_norm": 0.13861128687858582,
      "learning_rate": 7e-06,
      "loss": 0.3214,
      "step": 127
    },
    {
      "epoch": 0.08308316430020284,
      "grad_norm": 0.20256835222244263,
      "learning_rate": 7e-06,
      "loss": 0.3061,
      "step": 128
    },
    {
      "epoch": 0.08373225152129818,
      "grad_norm": 0.1353987157344818,
      "learning_rate": 7e-06,
      "loss": 0.3345,
      "step": 129
    },
    {
      "epoch": 0.08438133874239351,
      "grad_norm": 0.08944071829319,
      "learning_rate": 7e-06,
      "loss": 0.2479,
      "step": 130
    },
    {
      "epoch": 0.08503042596348884,
      "grad_norm": 0.10355153679847717,
      "learning_rate": 7e-06,
      "loss": 0.3009,
      "step": 131
    },
    {
      "epoch": 0.08567951318458418,
      "grad_norm": 0.1323573887348175,
      "learning_rate": 7e-06,
      "loss": 0.2916,
      "step": 132
    },
    {
      "epoch": 0.08632860040567951,
      "grad_norm": 0.14798720180988312,
      "learning_rate": 7e-06,
      "loss": 0.2031,
      "step": 133
    },
    {
      "epoch": 0.08697768762677485,
      "grad_norm": 0.13328224420547485,
      "learning_rate": 7e-06,
      "loss": 0.2665,
      "step": 134
    },
    {
      "epoch": 0.08762677484787018,
      "grad_norm": 0.16856026649475098,
      "learning_rate": 7e-06,
      "loss": 0.3128,
      "step": 135
    },
    {
      "epoch": 0.08827586206896551,
      "grad_norm": 0.1447562724351883,
      "learning_rate": 7e-06,
      "loss": 0.2956,
      "step": 136
    },
    {
      "epoch": 0.08892494929006085,
      "grad_norm": 0.1801261603832245,
      "learning_rate": 7e-06,
      "loss": 0.2595,
      "step": 137
    },
    {
      "epoch": 0.08957403651115618,
      "grad_norm": 0.1363699585199356,
      "learning_rate": 7e-06,
      "loss": 0.2775,
      "step": 138
    },
    {
      "epoch": 0.09022312373225153,
      "grad_norm": 0.10482609272003174,
      "learning_rate": 7e-06,
      "loss": 0.2859,
      "step": 139
    },
    {
      "epoch": 0.09087221095334685,
      "grad_norm": 0.1143878698348999,
      "learning_rate": 7e-06,
      "loss": 0.2973,
      "step": 140
    },
    {
      "epoch": 0.09152129817444218,
      "grad_norm": 0.14794325828552246,
      "learning_rate": 7e-06,
      "loss": 0.2402,
      "step": 141
    },
    {
      "epoch": 0.09217038539553753,
      "grad_norm": 0.12533071637153625,
      "learning_rate": 7e-06,
      "loss": 0.3207,
      "step": 142
    },
    {
      "epoch": 0.09281947261663286,
      "grad_norm": 0.1534649282693863,
      "learning_rate": 7e-06,
      "loss": 0.3033,
      "step": 143
    },
    {
      "epoch": 0.0934685598377282,
      "grad_norm": 0.09753341227769852,
      "learning_rate": 7e-06,
      "loss": 0.2371,
      "step": 144
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.14989688992500305,
      "learning_rate": 7e-06,
      "loss": 0.2567,
      "step": 145
    },
    {
      "epoch": 0.09476673427991886,
      "grad_norm": 0.11998281627893448,
      "learning_rate": 7e-06,
      "loss": 0.2344,
      "step": 146
    },
    {
      "epoch": 0.0954158215010142,
      "grad_norm": 0.16198904812335968,
      "learning_rate": 7e-06,
      "loss": 0.2589,
      "step": 147
    },
    {
      "epoch": 0.09606490872210953,
      "grad_norm": 0.1523151844739914,
      "learning_rate": 7e-06,
      "loss": 0.3376,
      "step": 148
    },
    {
      "epoch": 0.09671399594320487,
      "grad_norm": 0.09760883450508118,
      "learning_rate": 7e-06,
      "loss": 0.2567,
      "step": 149
    },
    {
      "epoch": 0.0973630831643002,
      "grad_norm": 0.19058220088481903,
      "learning_rate": 7e-06,
      "loss": 0.29,
      "step": 150
    },
    {
      "epoch": 0.09801217038539553,
      "grad_norm": 0.16542483866214752,
      "learning_rate": 7e-06,
      "loss": 0.5147,
      "step": 151
    },
    {
      "epoch": 0.09866125760649087,
      "grad_norm": 0.1427602916955948,
      "learning_rate": 7e-06,
      "loss": 0.3064,
      "step": 152
    },
    {
      "epoch": 0.0993103448275862,
      "grad_norm": 0.12821495532989502,
      "learning_rate": 7e-06,
      "loss": 0.2621,
      "step": 153
    },
    {
      "epoch": 0.09995943204868155,
      "grad_norm": 0.13976949453353882,
      "learning_rate": 7e-06,
      "loss": 0.2266,
      "step": 154
    },
    {
      "epoch": 0.10060851926977687,
      "grad_norm": 0.0917961448431015,
      "learning_rate": 7e-06,
      "loss": 0.3365,
      "step": 155
    },
    {
      "epoch": 0.10125760649087222,
      "grad_norm": 0.12663206458091736,
      "learning_rate": 7e-06,
      "loss": 0.2606,
      "step": 156
    },
    {
      "epoch": 0.10190669371196755,
      "grad_norm": 0.10375673323869705,
      "learning_rate": 7e-06,
      "loss": 0.2808,
      "step": 157
    },
    {
      "epoch": 0.10255578093306288,
      "grad_norm": 0.17907507717609406,
      "learning_rate": 7e-06,
      "loss": 0.2281,
      "step": 158
    },
    {
      "epoch": 0.10320486815415822,
      "grad_norm": 0.10987372696399689,
      "learning_rate": 7e-06,
      "loss": 0.2443,
      "step": 159
    },
    {
      "epoch": 0.10385395537525355,
      "grad_norm": 0.2377939224243164,
      "learning_rate": 7e-06,
      "loss": 0.2902,
      "step": 160
    },
    {
      "epoch": 0.10450304259634889,
      "grad_norm": 0.14829187095165253,
      "learning_rate": 7e-06,
      "loss": 0.2823,
      "step": 161
    },
    {
      "epoch": 0.10515212981744422,
      "grad_norm": 0.1994808167219162,
      "learning_rate": 7e-06,
      "loss": 0.2771,
      "step": 162
    },
    {
      "epoch": 0.10580121703853955,
      "grad_norm": 0.2217777818441391,
      "learning_rate": 7e-06,
      "loss": 0.2785,
      "step": 163
    },
    {
      "epoch": 0.10645030425963489,
      "grad_norm": 0.13546733558177948,
      "learning_rate": 7e-06,
      "loss": 0.2709,
      "step": 164
    },
    {
      "epoch": 0.10709939148073022,
      "grad_norm": 0.1280691772699356,
      "learning_rate": 7e-06,
      "loss": 0.2512,
      "step": 165
    },
    {
      "epoch": 0.10774847870182556,
      "grad_norm": 0.1384226679801941,
      "learning_rate": 7e-06,
      "loss": 0.254,
      "step": 166
    },
    {
      "epoch": 0.1083975659229209,
      "grad_norm": 0.15670539438724518,
      "learning_rate": 7e-06,
      "loss": 0.2642,
      "step": 167
    },
    {
      "epoch": 0.10904665314401622,
      "grad_norm": 0.12967081367969513,
      "learning_rate": 7e-06,
      "loss": 0.2583,
      "step": 168
    },
    {
      "epoch": 0.10969574036511157,
      "grad_norm": 0.15979881584644318,
      "learning_rate": 7e-06,
      "loss": 0.2705,
      "step": 169
    },
    {
      "epoch": 0.1103448275862069,
      "grad_norm": 0.14831869304180145,
      "learning_rate": 7e-06,
      "loss": 0.2804,
      "step": 170
    },
    {
      "epoch": 0.11099391480730224,
      "grad_norm": 0.11665844172239304,
      "learning_rate": 7e-06,
      "loss": 0.2365,
      "step": 171
    },
    {
      "epoch": 0.11164300202839757,
      "grad_norm": 0.21699249744415283,
      "learning_rate": 7e-06,
      "loss": 0.2991,
      "step": 172
    },
    {
      "epoch": 0.1122920892494929,
      "grad_norm": 0.12228582799434662,
      "learning_rate": 7e-06,
      "loss": 0.2584,
      "step": 173
    },
    {
      "epoch": 0.11294117647058824,
      "grad_norm": 0.12846054136753082,
      "learning_rate": 7e-06,
      "loss": 0.2398,
      "step": 174
    },
    {
      "epoch": 0.11359026369168357,
      "grad_norm": 0.12618054449558258,
      "learning_rate": 7e-06,
      "loss": 0.2631,
      "step": 175
    },
    {
      "epoch": 0.11423935091277891,
      "grad_norm": 0.09687444567680359,
      "learning_rate": 7e-06,
      "loss": 0.2449,
      "step": 176
    },
    {
      "epoch": 0.11488843813387424,
      "grad_norm": 0.17391951382160187,
      "learning_rate": 7e-06,
      "loss": 0.2511,
      "step": 177
    },
    {
      "epoch": 0.11553752535496957,
      "grad_norm": 0.10200081020593643,
      "learning_rate": 7e-06,
      "loss": 0.2668,
      "step": 178
    },
    {
      "epoch": 0.11618661257606491,
      "grad_norm": 0.09662250429391861,
      "learning_rate": 7e-06,
      "loss": 0.2648,
      "step": 179
    },
    {
      "epoch": 0.11683569979716024,
      "grad_norm": 0.18751277029514313,
      "learning_rate": 7e-06,
      "loss": 0.3034,
      "step": 180
    },
    {
      "epoch": 0.11748478701825558,
      "grad_norm": 0.14103098213672638,
      "learning_rate": 7e-06,
      "loss": 0.33,
      "step": 181
    },
    {
      "epoch": 0.11813387423935091,
      "grad_norm": 0.10554314404726028,
      "learning_rate": 7e-06,
      "loss": 0.2762,
      "step": 182
    },
    {
      "epoch": 0.11878296146044624,
      "grad_norm": 0.12038284540176392,
      "learning_rate": 7e-06,
      "loss": 0.1937,
      "step": 183
    },
    {
      "epoch": 0.11943204868154159,
      "grad_norm": 0.10246861726045609,
      "learning_rate": 7e-06,
      "loss": 0.233,
      "step": 184
    },
    {
      "epoch": 0.12008113590263692,
      "grad_norm": 0.13546913862228394,
      "learning_rate": 7e-06,
      "loss": 0.2907,
      "step": 185
    },
    {
      "epoch": 0.12073022312373226,
      "grad_norm": 0.12862010300159454,
      "learning_rate": 7e-06,
      "loss": 0.1794,
      "step": 186
    },
    {
      "epoch": 0.12137931034482759,
      "grad_norm": 0.3141404092311859,
      "learning_rate": 7e-06,
      "loss": 0.317,
      "step": 187
    },
    {
      "epoch": 0.12202839756592292,
      "grad_norm": 0.17216050624847412,
      "learning_rate": 7e-06,
      "loss": 0.28,
      "step": 188
    },
    {
      "epoch": 0.12267748478701826,
      "grad_norm": 0.12216184288263321,
      "learning_rate": 7e-06,
      "loss": 0.2268,
      "step": 189
    },
    {
      "epoch": 0.12332657200811359,
      "grad_norm": 0.18691058456897736,
      "learning_rate": 7e-06,
      "loss": 0.2391,
      "step": 190
    },
    {
      "epoch": 0.12397565922920893,
      "grad_norm": 0.22162745893001556,
      "learning_rate": 7e-06,
      "loss": 0.2641,
      "step": 191
    },
    {
      "epoch": 0.12462474645030426,
      "grad_norm": 0.10477813333272934,
      "learning_rate": 7e-06,
      "loss": 0.2454,
      "step": 192
    },
    {
      "epoch": 0.1252738336713996,
      "grad_norm": 0.1289271116256714,
      "learning_rate": 7e-06,
      "loss": 0.2304,
      "step": 193
    },
    {
      "epoch": 0.12592292089249493,
      "grad_norm": 0.10394863039255142,
      "learning_rate": 7e-06,
      "loss": 0.2578,
      "step": 194
    },
    {
      "epoch": 0.12657200811359026,
      "grad_norm": 0.1417291760444641,
      "learning_rate": 7e-06,
      "loss": 0.2637,
      "step": 195
    },
    {
      "epoch": 0.1272210953346856,
      "grad_norm": 0.20843861997127533,
      "learning_rate": 7e-06,
      "loss": 0.2785,
      "step": 196
    },
    {
      "epoch": 0.12787018255578092,
      "grad_norm": 0.13714921474456787,
      "learning_rate": 7e-06,
      "loss": 0.2687,
      "step": 197
    },
    {
      "epoch": 0.12851926977687628,
      "grad_norm": 0.1900320053100586,
      "learning_rate": 7e-06,
      "loss": 0.2604,
      "step": 198
    },
    {
      "epoch": 0.1291683569979716,
      "grad_norm": 0.12290951609611511,
      "learning_rate": 7e-06,
      "loss": 0.2229,
      "step": 199
    },
    {
      "epoch": 0.12981744421906694,
      "grad_norm": 0.1371142566204071,
      "learning_rate": 7e-06,
      "loss": 0.2773,
      "step": 200
    },
    {
      "epoch": 0.12981744421906694,
      "eval_correct_accuracy": 0.6242578456318915,
      "eval_error_accuracy": 0.4655560558307069,
      "eval_f1": 0.5333516484671705,
      "eval_loss": 0.3919190466403961,
      "eval_runtime": 35.0288,
      "eval_samples_per_second": 97.063,
      "eval_steps_per_second": 6.081,
      "step": 200
    },
    {
      "epoch": 0.13046653144016226,
      "grad_norm": 0.12129559367895126,
      "learning_rate": 7e-06,
      "loss": 0.2442,
      "step": 201
    },
    {
      "epoch": 0.1311156186612576,
      "grad_norm": 0.15711937844753265,
      "learning_rate": 7e-06,
      "loss": 0.2217,
      "step": 202
    },
    {
      "epoch": 0.13176470588235295,
      "grad_norm": 0.13760608434677124,
      "learning_rate": 7e-06,
      "loss": 0.2943,
      "step": 203
    },
    {
      "epoch": 0.13241379310344828,
      "grad_norm": 0.1321796476840973,
      "learning_rate": 7e-06,
      "loss": 0.2354,
      "step": 204
    },
    {
      "epoch": 0.1330628803245436,
      "grad_norm": 0.21664661169052124,
      "learning_rate": 7e-06,
      "loss": 0.2984,
      "step": 205
    },
    {
      "epoch": 0.13371196754563894,
      "grad_norm": 0.07987571507692337,
      "learning_rate": 7e-06,
      "loss": 0.2122,
      "step": 206
    },
    {
      "epoch": 0.13436105476673427,
      "grad_norm": 0.07909967005252838,
      "learning_rate": 7e-06,
      "loss": 0.2006,
      "step": 207
    },
    {
      "epoch": 0.13501014198782962,
      "grad_norm": 0.203807532787323,
      "learning_rate": 7e-06,
      "loss": 0.2877,
      "step": 208
    },
    {
      "epoch": 0.13565922920892495,
      "grad_norm": 0.11568247526884079,
      "learning_rate": 7e-06,
      "loss": 0.2328,
      "step": 209
    },
    {
      "epoch": 0.13630831643002028,
      "grad_norm": 0.1349884569644928,
      "learning_rate": 7e-06,
      "loss": 0.2392,
      "step": 210
    },
    {
      "epoch": 0.1369574036511156,
      "grad_norm": 0.14622704684734344,
      "learning_rate": 7e-06,
      "loss": 0.2756,
      "step": 211
    },
    {
      "epoch": 0.13760649087221094,
      "grad_norm": 0.10050090402364731,
      "learning_rate": 7e-06,
      "loss": 0.2546,
      "step": 212
    },
    {
      "epoch": 0.1382555780933063,
      "grad_norm": 0.14070256054401398,
      "learning_rate": 7e-06,
      "loss": 0.2625,
      "step": 213
    },
    {
      "epoch": 0.13890466531440163,
      "grad_norm": 0.10955073684453964,
      "learning_rate": 7e-06,
      "loss": 0.2245,
      "step": 214
    },
    {
      "epoch": 0.13955375253549696,
      "grad_norm": 0.11297724395990372,
      "learning_rate": 7e-06,
      "loss": 0.2467,
      "step": 215
    },
    {
      "epoch": 0.14020283975659228,
      "grad_norm": 0.13519620895385742,
      "learning_rate": 7e-06,
      "loss": 0.2244,
      "step": 216
    },
    {
      "epoch": 0.1408519269776876,
      "grad_norm": 0.12607978284358978,
      "learning_rate": 7e-06,
      "loss": 0.289,
      "step": 217
    },
    {
      "epoch": 0.14150101419878297,
      "grad_norm": 0.10905851423740387,
      "learning_rate": 7e-06,
      "loss": 0.2349,
      "step": 218
    },
    {
      "epoch": 0.1421501014198783,
      "grad_norm": 0.09633960574865341,
      "learning_rate": 7e-06,
      "loss": 0.197,
      "step": 219
    },
    {
      "epoch": 0.14279918864097363,
      "grad_norm": 0.13185693323612213,
      "learning_rate": 7e-06,
      "loss": 0.2425,
      "step": 220
    },
    {
      "epoch": 0.14344827586206896,
      "grad_norm": 0.1569773554801941,
      "learning_rate": 7e-06,
      "loss": 0.2875,
      "step": 221
    },
    {
      "epoch": 0.1440973630831643,
      "grad_norm": 0.14905628561973572,
      "learning_rate": 7e-06,
      "loss": 0.218,
      "step": 222
    },
    {
      "epoch": 0.14474645030425964,
      "grad_norm": 0.15708011388778687,
      "learning_rate": 7e-06,
      "loss": 0.2776,
      "step": 223
    },
    {
      "epoch": 0.14539553752535497,
      "grad_norm": 0.12294436246156693,
      "learning_rate": 7e-06,
      "loss": 0.2578,
      "step": 224
    },
    {
      "epoch": 0.1460446247464503,
      "grad_norm": 0.12113978713750839,
      "learning_rate": 7e-06,
      "loss": 0.2713,
      "step": 225
    },
    {
      "epoch": 0.14669371196754563,
      "grad_norm": 0.11322671920061111,
      "learning_rate": 7e-06,
      "loss": 0.2374,
      "step": 226
    },
    {
      "epoch": 0.14734279918864096,
      "grad_norm": 0.14585842192173004,
      "learning_rate": 7e-06,
      "loss": 0.2624,
      "step": 227
    },
    {
      "epoch": 0.14799188640973632,
      "grad_norm": 0.10896655172109604,
      "learning_rate": 7e-06,
      "loss": 0.2516,
      "step": 228
    },
    {
      "epoch": 0.14864097363083165,
      "grad_norm": 0.09082011878490448,
      "learning_rate": 7e-06,
      "loss": 0.209,
      "step": 229
    },
    {
      "epoch": 0.14929006085192698,
      "grad_norm": 0.1508411020040512,
      "learning_rate": 7e-06,
      "loss": 0.2156,
      "step": 230
    },
    {
      "epoch": 0.1499391480730223,
      "grad_norm": 0.15678022801876068,
      "learning_rate": 7e-06,
      "loss": 0.2368,
      "step": 231
    },
    {
      "epoch": 0.15058823529411763,
      "grad_norm": 0.15668921172618866,
      "learning_rate": 7e-06,
      "loss": 0.2423,
      "step": 232
    },
    {
      "epoch": 0.151237322515213,
      "grad_norm": 0.10186024010181427,
      "learning_rate": 7e-06,
      "loss": 0.2577,
      "step": 233
    },
    {
      "epoch": 0.15188640973630832,
      "grad_norm": 0.1859818547964096,
      "learning_rate": 7e-06,
      "loss": 0.2559,
      "step": 234
    },
    {
      "epoch": 0.15253549695740365,
      "grad_norm": 0.20006772875785828,
      "learning_rate": 7e-06,
      "loss": 0.2042,
      "step": 235
    },
    {
      "epoch": 0.15318458417849898,
      "grad_norm": 0.13926419615745544,
      "learning_rate": 7e-06,
      "loss": 0.2749,
      "step": 236
    },
    {
      "epoch": 0.1538336713995943,
      "grad_norm": 0.09763505309820175,
      "learning_rate": 7e-06,
      "loss": 0.2755,
      "step": 237
    },
    {
      "epoch": 0.15448275862068966,
      "grad_norm": 0.16450068354606628,
      "learning_rate": 7e-06,
      "loss": 0.369,
      "step": 238
    },
    {
      "epoch": 0.155131845841785,
      "grad_norm": 0.16841815412044525,
      "learning_rate": 7e-06,
      "loss": 0.2438,
      "step": 239
    },
    {
      "epoch": 0.15578093306288032,
      "grad_norm": 0.1305510252714157,
      "learning_rate": 7e-06,
      "loss": 0.2205,
      "step": 240
    },
    {
      "epoch": 0.15643002028397565,
      "grad_norm": 0.1448666900396347,
      "learning_rate": 7e-06,
      "loss": 0.262,
      "step": 241
    },
    {
      "epoch": 0.15707910750507098,
      "grad_norm": 0.10042058676481247,
      "learning_rate": 7e-06,
      "loss": 0.2365,
      "step": 242
    },
    {
      "epoch": 0.15772819472616634,
      "grad_norm": 0.09971918165683746,
      "learning_rate": 7e-06,
      "loss": 0.2458,
      "step": 243
    },
    {
      "epoch": 0.15837728194726167,
      "grad_norm": 0.16545331478118896,
      "learning_rate": 7e-06,
      "loss": 0.2299,
      "step": 244
    },
    {
      "epoch": 0.159026369168357,
      "grad_norm": 0.09911689907312393,
      "learning_rate": 7e-06,
      "loss": 0.241,
      "step": 245
    },
    {
      "epoch": 0.15967545638945232,
      "grad_norm": 0.11439679563045502,
      "learning_rate": 7e-06,
      "loss": 0.2683,
      "step": 246
    },
    {
      "epoch": 0.16032454361054765,
      "grad_norm": 0.09213147312402725,
      "learning_rate": 7e-06,
      "loss": 0.1842,
      "step": 247
    },
    {
      "epoch": 0.160973630831643,
      "grad_norm": 0.1683698147535324,
      "learning_rate": 7e-06,
      "loss": 0.2455,
      "step": 248
    },
    {
      "epoch": 0.16162271805273834,
      "grad_norm": 0.14097467064857483,
      "learning_rate": 7e-06,
      "loss": 0.2429,
      "step": 249
    },
    {
      "epoch": 0.16227180527383367,
      "grad_norm": 0.1128353476524353,
      "learning_rate": 7e-06,
      "loss": 0.2812,
      "step": 250
    },
    {
      "epoch": 0.162920892494929,
      "grad_norm": 0.1045866534113884,
      "learning_rate": 7e-06,
      "loss": 0.2365,
      "step": 251
    },
    {
      "epoch": 0.16356997971602433,
      "grad_norm": 0.08610460162162781,
      "learning_rate": 7e-06,
      "loss": 0.4523,
      "step": 252
    },
    {
      "epoch": 0.16421906693711968,
      "grad_norm": 0.15569978952407837,
      "learning_rate": 7e-06,
      "loss": 0.2304,
      "step": 253
    },
    {
      "epoch": 0.164868154158215,
      "grad_norm": 0.16581496596336365,
      "learning_rate": 7e-06,
      "loss": 0.3649,
      "step": 254
    },
    {
      "epoch": 0.16551724137931034,
      "grad_norm": 0.1171705350279808,
      "learning_rate": 7e-06,
      "loss": 0.2719,
      "step": 255
    },
    {
      "epoch": 0.16616632860040567,
      "grad_norm": 0.1534133106470108,
      "learning_rate": 7e-06,
      "loss": 0.2355,
      "step": 256
    },
    {
      "epoch": 0.166815415821501,
      "grad_norm": 0.12336218357086182,
      "learning_rate": 7e-06,
      "loss": 0.4723,
      "step": 257
    },
    {
      "epoch": 0.16746450304259636,
      "grad_norm": 0.15371279418468475,
      "learning_rate": 7e-06,
      "loss": 0.3992,
      "step": 258
    },
    {
      "epoch": 0.1681135902636917,
      "grad_norm": 0.22105465829372406,
      "learning_rate": 7e-06,
      "loss": 0.304,
      "step": 259
    },
    {
      "epoch": 0.16876267748478702,
      "grad_norm": 0.1112341657280922,
      "learning_rate": 7e-06,
      "loss": 0.2022,
      "step": 260
    },
    {
      "epoch": 0.16941176470588235,
      "grad_norm": 0.09052049368619919,
      "learning_rate": 7e-06,
      "loss": 0.238,
      "step": 261
    },
    {
      "epoch": 0.17006085192697767,
      "grad_norm": 0.09566039592027664,
      "learning_rate": 7e-06,
      "loss": 0.1814,
      "step": 262
    },
    {
      "epoch": 0.17070993914807303,
      "grad_norm": 0.10019491612911224,
      "learning_rate": 7e-06,
      "loss": 0.2578,
      "step": 263
    },
    {
      "epoch": 0.17135902636916836,
      "grad_norm": 0.21348124742507935,
      "learning_rate": 7e-06,
      "loss": 0.2084,
      "step": 264
    },
    {
      "epoch": 0.1720081135902637,
      "grad_norm": 0.10550300776958466,
      "learning_rate": 7e-06,
      "loss": 0.2005,
      "step": 265
    },
    {
      "epoch": 0.17265720081135902,
      "grad_norm": 0.11737056821584702,
      "learning_rate": 7e-06,
      "loss": 0.2326,
      "step": 266
    },
    {
      "epoch": 0.17330628803245435,
      "grad_norm": 0.20776107907295227,
      "learning_rate": 7e-06,
      "loss": 0.3248,
      "step": 267
    },
    {
      "epoch": 0.1739553752535497,
      "grad_norm": 0.22339636087417603,
      "learning_rate": 7e-06,
      "loss": 0.2436,
      "step": 268
    },
    {
      "epoch": 0.17460446247464503,
      "grad_norm": 0.15657320618629456,
      "learning_rate": 7e-06,
      "loss": 0.5287,
      "step": 269
    },
    {
      "epoch": 0.17525354969574036,
      "grad_norm": 0.12337369471788406,
      "learning_rate": 7e-06,
      "loss": 0.2224,
      "step": 270
    },
    {
      "epoch": 0.1759026369168357,
      "grad_norm": 0.12230188399553299,
      "learning_rate": 7e-06,
      "loss": 0.2561,
      "step": 271
    },
    {
      "epoch": 0.17655172413793102,
      "grad_norm": 0.13091178238391876,
      "learning_rate": 7e-06,
      "loss": 0.2187,
      "step": 272
    },
    {
      "epoch": 0.17720081135902638,
      "grad_norm": 0.1275922656059265,
      "learning_rate": 7e-06,
      "loss": 0.1924,
      "step": 273
    },
    {
      "epoch": 0.1778498985801217,
      "grad_norm": 0.17138446867465973,
      "learning_rate": 7e-06,
      "loss": 0.227,
      "step": 274
    },
    {
      "epoch": 0.17849898580121704,
      "grad_norm": 0.21689331531524658,
      "learning_rate": 7e-06,
      "loss": 0.2948,
      "step": 275
    },
    {
      "epoch": 0.17914807302231237,
      "grad_norm": 0.16428537666797638,
      "learning_rate": 7e-06,
      "loss": 0.2759,
      "step": 276
    },
    {
      "epoch": 0.1797971602434077,
      "grad_norm": 0.18788424134254456,
      "learning_rate": 7e-06,
      "loss": 0.2204,
      "step": 277
    },
    {
      "epoch": 0.18044624746450305,
      "grad_norm": 0.08331163227558136,
      "learning_rate": 7e-06,
      "loss": 0.2048,
      "step": 278
    },
    {
      "epoch": 0.18109533468559838,
      "grad_norm": 0.10176994651556015,
      "learning_rate": 7e-06,
      "loss": 0.2237,
      "step": 279
    },
    {
      "epoch": 0.1817444219066937,
      "grad_norm": 0.1618790477514267,
      "learning_rate": 7e-06,
      "loss": 0.2363,
      "step": 280
    },
    {
      "epoch": 0.18239350912778904,
      "grad_norm": 0.09633233398199081,
      "learning_rate": 7e-06,
      "loss": 0.463,
      "step": 281
    },
    {
      "epoch": 0.18304259634888437,
      "grad_norm": 0.10011264681816101,
      "learning_rate": 7e-06,
      "loss": 0.2107,
      "step": 282
    },
    {
      "epoch": 0.18369168356997972,
      "grad_norm": 0.11124041676521301,
      "learning_rate": 7e-06,
      "loss": 0.2297,
      "step": 283
    },
    {
      "epoch": 0.18434077079107505,
      "grad_norm": 0.13320429623126984,
      "learning_rate": 7e-06,
      "loss": 0.2809,
      "step": 284
    },
    {
      "epoch": 0.18498985801217038,
      "grad_norm": 0.1482834815979004,
      "learning_rate": 7e-06,
      "loss": 0.2574,
      "step": 285
    },
    {
      "epoch": 0.1856389452332657,
      "grad_norm": 0.14794503152370453,
      "learning_rate": 7e-06,
      "loss": 0.2546,
      "step": 286
    },
    {
      "epoch": 0.18628803245436104,
      "grad_norm": 0.17715878784656525,
      "learning_rate": 7e-06,
      "loss": 0.2782,
      "step": 287
    },
    {
      "epoch": 0.1869371196754564,
      "grad_norm": 0.1998974084854126,
      "learning_rate": 7e-06,
      "loss": 0.2103,
      "step": 288
    },
    {
      "epoch": 0.18758620689655173,
      "grad_norm": 0.13205166161060333,
      "learning_rate": 7e-06,
      "loss": 0.1852,
      "step": 289
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.10181520879268646,
      "learning_rate": 7e-06,
      "loss": 0.2475,
      "step": 290
    },
    {
      "epoch": 0.18888438133874239,
      "grad_norm": 0.12155479937791824,
      "learning_rate": 7e-06,
      "loss": 0.2279,
      "step": 291
    },
    {
      "epoch": 0.18953346855983771,
      "grad_norm": 0.1704024076461792,
      "learning_rate": 7e-06,
      "loss": 0.2139,
      "step": 292
    },
    {
      "epoch": 0.19018255578093307,
      "grad_norm": 0.1121644377708435,
      "learning_rate": 7e-06,
      "loss": 0.2428,
      "step": 293
    },
    {
      "epoch": 0.1908316430020284,
      "grad_norm": 0.16926288604736328,
      "learning_rate": 7e-06,
      "loss": 0.3298,
      "step": 294
    },
    {
      "epoch": 0.19148073022312373,
      "grad_norm": 0.11276428401470184,
      "learning_rate": 7e-06,
      "loss": 0.2044,
      "step": 295
    },
    {
      "epoch": 0.19212981744421906,
      "grad_norm": 0.0800459235906601,
      "learning_rate": 7e-06,
      "loss": 0.1896,
      "step": 296
    },
    {
      "epoch": 0.1927789046653144,
      "grad_norm": 0.12247651815414429,
      "learning_rate": 7e-06,
      "loss": 0.3732,
      "step": 297
    },
    {
      "epoch": 0.19342799188640974,
      "grad_norm": 0.10372534394264221,
      "learning_rate": 7e-06,
      "loss": 0.208,
      "step": 298
    },
    {
      "epoch": 0.19407707910750507,
      "grad_norm": 0.13438674807548523,
      "learning_rate": 7e-06,
      "loss": 0.2513,
      "step": 299
    },
    {
      "epoch": 0.1947261663286004,
      "grad_norm": 0.11250044405460358,
      "learning_rate": 7e-06,
      "loss": 0.1896,
      "step": 300
    },
    {
      "epoch": 0.1947261663286004,
      "eval_correct_accuracy": 0.7031382527565734,
      "eval_error_accuracy": 0.4606033318325079,
      "eval_f1": 0.5565974890773091,
      "eval_loss": 0.3419213891029358,
      "eval_runtime": 35.1405,
      "eval_samples_per_second": 96.755,
      "eval_steps_per_second": 6.061,
      "step": 300
    },
    {
      "epoch": 0.19537525354969573,
      "grad_norm": 0.10717342048883438,
      "learning_rate": 7e-06,
      "loss": 0.2012,
      "step": 301
    },
    {
      "epoch": 0.19602434077079106,
      "grad_norm": 0.2569890022277832,
      "learning_rate": 7e-06,
      "loss": 0.2673,
      "step": 302
    },
    {
      "epoch": 0.19667342799188642,
      "grad_norm": 0.20772649347782135,
      "learning_rate": 7e-06,
      "loss": 0.24,
      "step": 303
    },
    {
      "epoch": 0.19732251521298175,
      "grad_norm": 0.1774294227361679,
      "learning_rate": 7e-06,
      "loss": 0.2777,
      "step": 304
    },
    {
      "epoch": 0.19797160243407708,
      "grad_norm": 0.14435642957687378,
      "learning_rate": 7e-06,
      "loss": 0.2312,
      "step": 305
    },
    {
      "epoch": 0.1986206896551724,
      "grad_norm": 0.15979962050914764,
      "learning_rate": 7e-06,
      "loss": 0.2077,
      "step": 306
    },
    {
      "epoch": 0.19926977687626773,
      "grad_norm": 0.1432703584432602,
      "learning_rate": 7e-06,
      "loss": 0.2507,
      "step": 307
    },
    {
      "epoch": 0.1999188640973631,
      "grad_norm": 0.19193200767040253,
      "learning_rate": 7e-06,
      "loss": 0.256,
      "step": 308
    },
    {
      "epoch": 0.20056795131845842,
      "grad_norm": 0.23390762507915497,
      "learning_rate": 7e-06,
      "loss": 0.2629,
      "step": 309
    },
    {
      "epoch": 0.20121703853955375,
      "grad_norm": 0.11642121523618698,
      "learning_rate": 7e-06,
      "loss": 0.1731,
      "step": 310
    },
    {
      "epoch": 0.20186612576064908,
      "grad_norm": 0.2587537169456482,
      "learning_rate": 7e-06,
      "loss": 0.25,
      "step": 311
    },
    {
      "epoch": 0.20251521298174444,
      "grad_norm": 0.12986834347248077,
      "learning_rate": 7e-06,
      "loss": 0.2752,
      "step": 312
    },
    {
      "epoch": 0.20316430020283976,
      "grad_norm": 0.11632047593593597,
      "learning_rate": 7e-06,
      "loss": 0.1787,
      "step": 313
    },
    {
      "epoch": 0.2038133874239351,
      "grad_norm": 0.07658582925796509,
      "learning_rate": 7e-06,
      "loss": 0.1975,
      "step": 314
    },
    {
      "epoch": 0.20446247464503042,
      "grad_norm": 0.14220090210437775,
      "learning_rate": 7e-06,
      "loss": 0.2388,
      "step": 315
    },
    {
      "epoch": 0.20511156186612575,
      "grad_norm": 0.145846426486969,
      "learning_rate": 7e-06,
      "loss": 0.2433,
      "step": 316
    },
    {
      "epoch": 0.2057606490872211,
      "grad_norm": 0.1160382404923439,
      "learning_rate": 7e-06,
      "loss": 0.2009,
      "step": 317
    },
    {
      "epoch": 0.20640973630831644,
      "grad_norm": 0.17509780824184418,
      "learning_rate": 7e-06,
      "loss": 0.2356,
      "step": 318
    },
    {
      "epoch": 0.20705882352941177,
      "grad_norm": 0.15723848342895508,
      "learning_rate": 7e-06,
      "loss": 0.2573,
      "step": 319
    },
    {
      "epoch": 0.2077079107505071,
      "grad_norm": 0.08188269287347794,
      "learning_rate": 7e-06,
      "loss": 0.1977,
      "step": 320
    },
    {
      "epoch": 0.20835699797160243,
      "grad_norm": 0.1716584712266922,
      "learning_rate": 7e-06,
      "loss": 0.2433,
      "step": 321
    },
    {
      "epoch": 0.20900608519269778,
      "grad_norm": 0.22345879673957825,
      "learning_rate": 7e-06,
      "loss": 0.2319,
      "step": 322
    },
    {
      "epoch": 0.2096551724137931,
      "grad_norm": 0.18166278302669525,
      "learning_rate": 7e-06,
      "loss": 0.2424,
      "step": 323
    },
    {
      "epoch": 0.21030425963488844,
      "grad_norm": 0.12026850879192352,
      "learning_rate": 7e-06,
      "loss": 0.2235,
      "step": 324
    },
    {
      "epoch": 0.21095334685598377,
      "grad_norm": 0.0901852697134018,
      "learning_rate": 7e-06,
      "loss": 0.2078,
      "step": 325
    },
    {
      "epoch": 0.2116024340770791,
      "grad_norm": 0.17702724039554596,
      "learning_rate": 7e-06,
      "loss": 0.2541,
      "step": 326
    },
    {
      "epoch": 0.21225152129817446,
      "grad_norm": 0.1806965172290802,
      "learning_rate": 7e-06,
      "loss": 0.2866,
      "step": 327
    },
    {
      "epoch": 0.21290060851926979,
      "grad_norm": 0.20773416757583618,
      "learning_rate": 7e-06,
      "loss": 0.2598,
      "step": 328
    },
    {
      "epoch": 0.21354969574036511,
      "grad_norm": 0.08722809702157974,
      "learning_rate": 7e-06,
      "loss": 0.1883,
      "step": 329
    },
    {
      "epoch": 0.21419878296146044,
      "grad_norm": 0.1598522663116455,
      "learning_rate": 7e-06,
      "loss": 0.2704,
      "step": 330
    },
    {
      "epoch": 0.21484787018255577,
      "grad_norm": 0.1151135265827179,
      "learning_rate": 7e-06,
      "loss": 0.4344,
      "step": 331
    },
    {
      "epoch": 0.21549695740365113,
      "grad_norm": 0.12036848068237305,
      "learning_rate": 7e-06,
      "loss": 0.2258,
      "step": 332
    },
    {
      "epoch": 0.21614604462474646,
      "grad_norm": 0.11035505682229996,
      "learning_rate": 7e-06,
      "loss": 0.2218,
      "step": 333
    },
    {
      "epoch": 0.2167951318458418,
      "grad_norm": 0.17271532118320465,
      "learning_rate": 7e-06,
      "loss": 0.2113,
      "step": 334
    },
    {
      "epoch": 0.21744421906693712,
      "grad_norm": 0.13392633199691772,
      "learning_rate": 7e-06,
      "loss": 0.3789,
      "step": 335
    },
    {
      "epoch": 0.21809330628803245,
      "grad_norm": 0.18040144443511963,
      "learning_rate": 7e-06,
      "loss": 0.2555,
      "step": 336
    },
    {
      "epoch": 0.2187423935091278,
      "grad_norm": 0.11267904937267303,
      "learning_rate": 7e-06,
      "loss": 0.201,
      "step": 337
    },
    {
      "epoch": 0.21939148073022313,
      "grad_norm": 0.0886501744389534,
      "learning_rate": 7e-06,
      "loss": 0.2154,
      "step": 338
    },
    {
      "epoch": 0.22004056795131846,
      "grad_norm": 0.1626102179288864,
      "learning_rate": 7e-06,
      "loss": 0.2775,
      "step": 339
    },
    {
      "epoch": 0.2206896551724138,
      "grad_norm": 0.17113429307937622,
      "learning_rate": 7e-06,
      "loss": 0.2587,
      "step": 340
    },
    {
      "epoch": 0.22133874239350912,
      "grad_norm": 0.15111511945724487,
      "learning_rate": 7e-06,
      "loss": 0.2829,
      "step": 341
    },
    {
      "epoch": 0.22198782961460448,
      "grad_norm": 0.13170167803764343,
      "learning_rate": 7e-06,
      "loss": 0.2128,
      "step": 342
    },
    {
      "epoch": 0.2226369168356998,
      "grad_norm": 0.0901579037308693,
      "learning_rate": 7e-06,
      "loss": 0.2065,
      "step": 343
    },
    {
      "epoch": 0.22328600405679513,
      "grad_norm": 0.12922360002994537,
      "learning_rate": 7e-06,
      "loss": 0.2374,
      "step": 344
    },
    {
      "epoch": 0.22393509127789046,
      "grad_norm": 0.14101530611515045,
      "learning_rate": 7e-06,
      "loss": 0.4119,
      "step": 345
    },
    {
      "epoch": 0.2245841784989858,
      "grad_norm": 0.15251903235912323,
      "learning_rate": 7e-06,
      "loss": 0.2329,
      "step": 346
    },
    {
      "epoch": 0.22523326572008115,
      "grad_norm": 0.10889409482479095,
      "learning_rate": 7e-06,
      "loss": 0.2251,
      "step": 347
    },
    {
      "epoch": 0.22588235294117648,
      "grad_norm": 0.11647622287273407,
      "learning_rate": 7e-06,
      "loss": 0.1982,
      "step": 348
    },
    {
      "epoch": 0.2265314401622718,
      "grad_norm": 0.12197374552488327,
      "learning_rate": 7e-06,
      "loss": 0.216,
      "step": 349
    },
    {
      "epoch": 0.22718052738336714,
      "grad_norm": 0.22269268333911896,
      "learning_rate": 7e-06,
      "loss": 0.434,
      "step": 350
    },
    {
      "epoch": 0.22782961460446247,
      "grad_norm": 0.12320459634065628,
      "learning_rate": 7e-06,
      "loss": 0.2169,
      "step": 351
    },
    {
      "epoch": 0.22847870182555782,
      "grad_norm": 0.1404983401298523,
      "learning_rate": 7e-06,
      "loss": 0.2785,
      "step": 352
    },
    {
      "epoch": 0.22912778904665315,
      "grad_norm": 0.12836822867393494,
      "learning_rate": 7e-06,
      "loss": 0.2097,
      "step": 353
    },
    {
      "epoch": 0.22977687626774848,
      "grad_norm": 0.09178731590509415,
      "learning_rate": 7e-06,
      "loss": 0.2073,
      "step": 354
    },
    {
      "epoch": 0.2304259634888438,
      "grad_norm": 0.1373235285282135,
      "learning_rate": 7e-06,
      "loss": 0.3208,
      "step": 355
    },
    {
      "epoch": 0.23107505070993914,
      "grad_norm": 0.07911817729473114,
      "learning_rate": 7e-06,
      "loss": 0.1809,
      "step": 356
    },
    {
      "epoch": 0.2317241379310345,
      "grad_norm": 0.08543137460947037,
      "learning_rate": 7e-06,
      "loss": 0.1858,
      "step": 357
    },
    {
      "epoch": 0.23237322515212983,
      "grad_norm": 0.10857584327459335,
      "learning_rate": 7e-06,
      "loss": 0.2467,
      "step": 358
    },
    {
      "epoch": 0.23302231237322515,
      "grad_norm": 0.20167776942253113,
      "learning_rate": 7e-06,
      "loss": 0.2335,
      "step": 359
    },
    {
      "epoch": 0.23367139959432048,
      "grad_norm": 0.15652884542942047,
      "learning_rate": 7e-06,
      "loss": 0.2434,
      "step": 360
    },
    {
      "epoch": 0.2343204868154158,
      "grad_norm": 0.0922442227602005,
      "learning_rate": 7e-06,
      "loss": 0.2134,
      "step": 361
    },
    {
      "epoch": 0.23496957403651117,
      "grad_norm": 0.1085292398929596,
      "learning_rate": 7e-06,
      "loss": 0.239,
      "step": 362
    },
    {
      "epoch": 0.2356186612576065,
      "grad_norm": 0.11852728575468063,
      "learning_rate": 7e-06,
      "loss": 0.2464,
      "step": 363
    },
    {
      "epoch": 0.23626774847870183,
      "grad_norm": 0.10871320217847824,
      "learning_rate": 7e-06,
      "loss": 0.2048,
      "step": 364
    },
    {
      "epoch": 0.23691683569979716,
      "grad_norm": 0.11753065139055252,
      "learning_rate": 7e-06,
      "loss": 0.2177,
      "step": 365
    },
    {
      "epoch": 0.23756592292089249,
      "grad_norm": 0.11931062489748001,
      "learning_rate": 7e-06,
      "loss": 0.2695,
      "step": 366
    },
    {
      "epoch": 0.23821501014198784,
      "grad_norm": 0.12056926637887955,
      "learning_rate": 7e-06,
      "loss": 0.1847,
      "step": 367
    },
    {
      "epoch": 0.23886409736308317,
      "grad_norm": 0.09704778343439102,
      "learning_rate": 7e-06,
      "loss": 0.2038,
      "step": 368
    },
    {
      "epoch": 0.2395131845841785,
      "grad_norm": 0.11950325220823288,
      "learning_rate": 7e-06,
      "loss": 0.2467,
      "step": 369
    },
    {
      "epoch": 0.24016227180527383,
      "grad_norm": 0.14411963522434235,
      "learning_rate": 7e-06,
      "loss": 0.2961,
      "step": 370
    },
    {
      "epoch": 0.24081135902636916,
      "grad_norm": 0.11896799504756927,
      "learning_rate": 7e-06,
      "loss": 0.2643,
      "step": 371
    },
    {
      "epoch": 0.24146044624746452,
      "grad_norm": 0.11972973495721817,
      "learning_rate": 7e-06,
      "loss": 0.2075,
      "step": 372
    },
    {
      "epoch": 0.24210953346855985,
      "grad_norm": 0.0893210843205452,
      "learning_rate": 7e-06,
      "loss": 0.1979,
      "step": 373
    },
    {
      "epoch": 0.24275862068965517,
      "grad_norm": 0.12623219192028046,
      "learning_rate": 7e-06,
      "loss": 0.2462,
      "step": 374
    },
    {
      "epoch": 0.2434077079107505,
      "grad_norm": 0.11793241649866104,
      "learning_rate": 7e-06,
      "loss": 0.2131,
      "step": 375
    },
    {
      "epoch": 0.24405679513184583,
      "grad_norm": 0.11450588703155518,
      "learning_rate": 7e-06,
      "loss": 0.1853,
      "step": 376
    },
    {
      "epoch": 0.2447058823529412,
      "grad_norm": 0.1901654303073883,
      "learning_rate": 7e-06,
      "loss": 0.1834,
      "step": 377
    },
    {
      "epoch": 0.24535496957403652,
      "grad_norm": 0.1130252480506897,
      "learning_rate": 7e-06,
      "loss": 0.2037,
      "step": 378
    },
    {
      "epoch": 0.24600405679513185,
      "grad_norm": 0.12222326546907425,
      "learning_rate": 7e-06,
      "loss": 0.2486,
      "step": 379
    },
    {
      "epoch": 0.24665314401622718,
      "grad_norm": 0.1483820527791977,
      "learning_rate": 7e-06,
      "loss": 0.2001,
      "step": 380
    },
    {
      "epoch": 0.2473022312373225,
      "grad_norm": 0.12757565081119537,
      "learning_rate": 7e-06,
      "loss": 0.2963,
      "step": 381
    },
    {
      "epoch": 0.24795131845841786,
      "grad_norm": 0.11470641940832138,
      "learning_rate": 7e-06,
      "loss": 0.2213,
      "step": 382
    },
    {
      "epoch": 0.2486004056795132,
      "grad_norm": 0.18159417808055878,
      "learning_rate": 7e-06,
      "loss": 0.2249,
      "step": 383
    },
    {
      "epoch": 0.24924949290060852,
      "grad_norm": 0.10142480581998825,
      "learning_rate": 7e-06,
      "loss": 0.1861,
      "step": 384
    },
    {
      "epoch": 0.24989858012170385,
      "grad_norm": 0.14223940670490265,
      "learning_rate": 7e-06,
      "loss": 0.2479,
      "step": 385
    },
    {
      "epoch": 0.2505476673427992,
      "grad_norm": 0.11674941331148148,
      "learning_rate": 7e-06,
      "loss": 0.236,
      "step": 386
    },
    {
      "epoch": 0.2511967545638945,
      "grad_norm": 0.13325904309749603,
      "learning_rate": 7e-06,
      "loss": 0.1588,
      "step": 387
    },
    {
      "epoch": 0.25184584178498987,
      "grad_norm": 0.09147018194198608,
      "learning_rate": 7e-06,
      "loss": 0.1684,
      "step": 388
    },
    {
      "epoch": 0.25249492900608517,
      "grad_norm": 0.14787423610687256,
      "learning_rate": 7e-06,
      "loss": 0.2007,
      "step": 389
    },
    {
      "epoch": 0.2531440162271805,
      "grad_norm": 0.08513084799051285,
      "learning_rate": 7e-06,
      "loss": 0.1975,
      "step": 390
    },
    {
      "epoch": 0.2537931034482759,
      "grad_norm": 0.13974198698997498,
      "learning_rate": 7e-06,
      "loss": 0.2127,
      "step": 391
    },
    {
      "epoch": 0.2544421906693712,
      "grad_norm": 0.14657065272331238,
      "learning_rate": 7e-06,
      "loss": 0.2163,
      "step": 392
    },
    {
      "epoch": 0.25509127789046654,
      "grad_norm": 0.18590159714221954,
      "learning_rate": 7e-06,
      "loss": 0.2585,
      "step": 393
    },
    {
      "epoch": 0.25574036511156184,
      "grad_norm": 0.10617897659540176,
      "learning_rate": 7e-06,
      "loss": 0.1871,
      "step": 394
    },
    {
      "epoch": 0.2563894523326572,
      "grad_norm": 0.3051954209804535,
      "learning_rate": 7e-06,
      "loss": 0.2572,
      "step": 395
    },
    {
      "epoch": 0.25703853955375255,
      "grad_norm": 0.11470337957143784,
      "learning_rate": 7e-06,
      "loss": 0.2349,
      "step": 396
    },
    {
      "epoch": 0.25768762677484786,
      "grad_norm": 0.12153269350528717,
      "learning_rate": 7e-06,
      "loss": 0.1818,
      "step": 397
    },
    {
      "epoch": 0.2583367139959432,
      "grad_norm": 0.12874765694141388,
      "learning_rate": 7e-06,
      "loss": 0.2243,
      "step": 398
    },
    {
      "epoch": 0.2589858012170385,
      "grad_norm": 0.13288410007953644,
      "learning_rate": 7e-06,
      "loss": 0.2915,
      "step": 399
    },
    {
      "epoch": 0.25963488843813387,
      "grad_norm": 0.1211925745010376,
      "learning_rate": 7e-06,
      "loss": 0.2068,
      "step": 400
    },
    {
      "epoch": 0.25963488843813387,
      "eval_correct_accuracy": 0.6785411365564037,
      "eval_error_accuracy": 0.4894191805493021,
      "eval_f1": 0.5686683736744995,
      "eval_loss": 0.3530837595462799,
      "eval_runtime": 35.0641,
      "eval_samples_per_second": 96.965,
      "eval_steps_per_second": 6.075,
      "step": 400
    },
    {
      "epoch": 0.2602839756592292,
      "grad_norm": 0.1313861906528473,
      "learning_rate": 7e-06,
      "loss": 0.2493,
      "step": 401
    },
    {
      "epoch": 0.26093306288032453,
      "grad_norm": 0.10416091233491898,
      "learning_rate": 7e-06,
      "loss": 0.196,
      "step": 402
    },
    {
      "epoch": 0.2615821501014199,
      "grad_norm": 0.09398356825113297,
      "learning_rate": 7e-06,
      "loss": 0.1977,
      "step": 403
    },
    {
      "epoch": 0.2622312373225152,
      "grad_norm": 0.14636275172233582,
      "learning_rate": 7e-06,
      "loss": 0.2142,
      "step": 404
    },
    {
      "epoch": 0.26288032454361054,
      "grad_norm": 0.0946781188249588,
      "learning_rate": 7e-06,
      "loss": 0.1783,
      "step": 405
    },
    {
      "epoch": 0.2635294117647059,
      "grad_norm": 0.1385267972946167,
      "learning_rate": 7e-06,
      "loss": 0.1807,
      "step": 406
    },
    {
      "epoch": 0.2641784989858012,
      "grad_norm": 0.07015523314476013,
      "learning_rate": 7e-06,
      "loss": 0.1696,
      "step": 407
    },
    {
      "epoch": 0.26482758620689656,
      "grad_norm": 0.14063435792922974,
      "learning_rate": 7e-06,
      "loss": 0.2808,
      "step": 408
    },
    {
      "epoch": 0.26547667342799186,
      "grad_norm": 0.16979968547821045,
      "learning_rate": 7e-06,
      "loss": 0.2394,
      "step": 409
    },
    {
      "epoch": 0.2661257606490872,
      "grad_norm": 0.09540793299674988,
      "learning_rate": 7e-06,
      "loss": 0.2229,
      "step": 410
    },
    {
      "epoch": 0.2667748478701826,
      "grad_norm": 0.10836261510848999,
      "learning_rate": 7e-06,
      "loss": 0.1722,
      "step": 411
    },
    {
      "epoch": 0.2674239350912779,
      "grad_norm": 0.19047099351882935,
      "learning_rate": 7e-06,
      "loss": 0.3911,
      "step": 412
    },
    {
      "epoch": 0.26807302231237323,
      "grad_norm": 0.13189999759197235,
      "learning_rate": 7e-06,
      "loss": 0.2169,
      "step": 413
    },
    {
      "epoch": 0.26872210953346853,
      "grad_norm": 0.18633174896240234,
      "learning_rate": 7e-06,
      "loss": 0.2147,
      "step": 414
    },
    {
      "epoch": 0.2693711967545639,
      "grad_norm": 0.17415189743041992,
      "learning_rate": 7e-06,
      "loss": 0.1998,
      "step": 415
    },
    {
      "epoch": 0.27002028397565925,
      "grad_norm": 0.10358814895153046,
      "learning_rate": 7e-06,
      "loss": 0.1979,
      "step": 416
    },
    {
      "epoch": 0.27066937119675455,
      "grad_norm": 0.11192916333675385,
      "learning_rate": 7e-06,
      "loss": 0.2052,
      "step": 417
    },
    {
      "epoch": 0.2713184584178499,
      "grad_norm": 0.18328338861465454,
      "learning_rate": 7e-06,
      "loss": 0.2104,
      "step": 418
    },
    {
      "epoch": 0.2719675456389452,
      "grad_norm": 0.0829685851931572,
      "learning_rate": 7e-06,
      "loss": 0.2097,
      "step": 419
    },
    {
      "epoch": 0.27261663286004056,
      "grad_norm": 0.16202427446842194,
      "learning_rate": 7e-06,
      "loss": 0.2564,
      "step": 420
    },
    {
      "epoch": 0.2732657200811359,
      "grad_norm": 0.14075079560279846,
      "learning_rate": 7e-06,
      "loss": 0.2287,
      "step": 421
    },
    {
      "epoch": 0.2739148073022312,
      "grad_norm": 0.10330383479595184,
      "learning_rate": 7e-06,
      "loss": 0.2014,
      "step": 422
    },
    {
      "epoch": 0.2745638945233266,
      "grad_norm": 0.1322251409292221,
      "learning_rate": 7e-06,
      "loss": 0.2159,
      "step": 423
    },
    {
      "epoch": 0.2752129817444219,
      "grad_norm": 0.08153083175420761,
      "learning_rate": 7e-06,
      "loss": 0.2446,
      "step": 424
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.09463037550449371,
      "learning_rate": 7e-06,
      "loss": 0.2349,
      "step": 425
    },
    {
      "epoch": 0.2765111561866126,
      "grad_norm": 0.12230438739061356,
      "learning_rate": 7e-06,
      "loss": 0.2383,
      "step": 426
    },
    {
      "epoch": 0.2771602434077079,
      "grad_norm": 0.18993087112903595,
      "learning_rate": 7e-06,
      "loss": 0.1822,
      "step": 427
    },
    {
      "epoch": 0.27780933062880325,
      "grad_norm": 0.08638976514339447,
      "learning_rate": 7e-06,
      "loss": 0.2144,
      "step": 428
    },
    {
      "epoch": 0.27845841784989855,
      "grad_norm": 0.11883678287267685,
      "learning_rate": 7e-06,
      "loss": 0.2019,
      "step": 429
    },
    {
      "epoch": 0.2791075050709939,
      "grad_norm": 0.12375818192958832,
      "learning_rate": 7e-06,
      "loss": 0.1959,
      "step": 430
    },
    {
      "epoch": 0.27975659229208927,
      "grad_norm": 0.09421627968549728,
      "learning_rate": 7e-06,
      "loss": 0.2058,
      "step": 431
    },
    {
      "epoch": 0.28040567951318457,
      "grad_norm": 0.09423483908176422,
      "learning_rate": 7e-06,
      "loss": 0.198,
      "step": 432
    },
    {
      "epoch": 0.2810547667342799,
      "grad_norm": 0.09047956019639969,
      "learning_rate": 7e-06,
      "loss": 0.1973,
      "step": 433
    },
    {
      "epoch": 0.2817038539553752,
      "grad_norm": 0.11135584861040115,
      "learning_rate": 7e-06,
      "loss": 0.2189,
      "step": 434
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.13883145153522491,
      "learning_rate": 7e-06,
      "loss": 0.2197,
      "step": 435
    },
    {
      "epoch": 0.28300202839756594,
      "grad_norm": 0.07159408181905746,
      "learning_rate": 7e-06,
      "loss": 0.183,
      "step": 436
    },
    {
      "epoch": 0.28365111561866124,
      "grad_norm": 0.12622317671775818,
      "learning_rate": 7e-06,
      "loss": 0.1936,
      "step": 437
    },
    {
      "epoch": 0.2843002028397566,
      "grad_norm": 0.14061273634433746,
      "learning_rate": 7e-06,
      "loss": 0.2051,
      "step": 438
    },
    {
      "epoch": 0.2849492900608519,
      "grad_norm": 0.10680039972066879,
      "learning_rate": 7e-06,
      "loss": 0.2268,
      "step": 439
    },
    {
      "epoch": 0.28559837728194726,
      "grad_norm": 0.11113894730806351,
      "learning_rate": 7e-06,
      "loss": 0.2057,
      "step": 440
    },
    {
      "epoch": 0.2862474645030426,
      "grad_norm": 0.22445617616176605,
      "learning_rate": 7e-06,
      "loss": 0.2591,
      "step": 441
    },
    {
      "epoch": 0.2868965517241379,
      "grad_norm": 0.1547282338142395,
      "learning_rate": 7e-06,
      "loss": 0.2578,
      "step": 442
    },
    {
      "epoch": 0.2875456389452333,
      "grad_norm": 0.10131862014532089,
      "learning_rate": 7e-06,
      "loss": 0.1852,
      "step": 443
    },
    {
      "epoch": 0.2881947261663286,
      "grad_norm": 0.17750045657157898,
      "learning_rate": 7e-06,
      "loss": 0.1901,
      "step": 444
    },
    {
      "epoch": 0.28884381338742393,
      "grad_norm": 0.17255273461341858,
      "learning_rate": 7e-06,
      "loss": 0.2353,
      "step": 445
    },
    {
      "epoch": 0.2894929006085193,
      "grad_norm": 0.14208172261714935,
      "learning_rate": 7e-06,
      "loss": 0.2904,
      "step": 446
    },
    {
      "epoch": 0.2901419878296146,
      "grad_norm": 0.11851240694522858,
      "learning_rate": 7e-06,
      "loss": 0.2358,
      "step": 447
    },
    {
      "epoch": 0.29079107505070995,
      "grad_norm": 0.11408327519893646,
      "learning_rate": 7e-06,
      "loss": 0.1928,
      "step": 448
    },
    {
      "epoch": 0.29144016227180525,
      "grad_norm": 0.09905464202165604,
      "learning_rate": 7e-06,
      "loss": 0.2041,
      "step": 449
    },
    {
      "epoch": 0.2920892494929006,
      "grad_norm": 0.08636341243982315,
      "learning_rate": 7e-06,
      "loss": 0.2185,
      "step": 450
    },
    {
      "epoch": 0.29273833671399596,
      "grad_norm": 0.1443682312965393,
      "learning_rate": 7e-06,
      "loss": 0.2452,
      "step": 451
    },
    {
      "epoch": 0.29338742393509126,
      "grad_norm": 0.11559905111789703,
      "learning_rate": 7e-06,
      "loss": 0.2445,
      "step": 452
    },
    {
      "epoch": 0.2940365111561866,
      "grad_norm": 0.09847108274698257,
      "learning_rate": 7e-06,
      "loss": 0.236,
      "step": 453
    },
    {
      "epoch": 0.2946855983772819,
      "grad_norm": 0.09635252505540848,
      "learning_rate": 7e-06,
      "loss": 0.1955,
      "step": 454
    },
    {
      "epoch": 0.2953346855983773,
      "grad_norm": 0.07106154412031174,
      "learning_rate": 7e-06,
      "loss": 0.1924,
      "step": 455
    },
    {
      "epoch": 0.29598377281947263,
      "grad_norm": 0.13688132166862488,
      "learning_rate": 7e-06,
      "loss": 0.2473,
      "step": 456
    },
    {
      "epoch": 0.29663286004056794,
      "grad_norm": 0.0991993397474289,
      "learning_rate": 7e-06,
      "loss": 0.1806,
      "step": 457
    },
    {
      "epoch": 0.2972819472616633,
      "grad_norm": 0.0754428580403328,
      "learning_rate": 7e-06,
      "loss": 0.1872,
      "step": 458
    },
    {
      "epoch": 0.2979310344827586,
      "grad_norm": 0.07847192138433456,
      "learning_rate": 7e-06,
      "loss": 0.2,
      "step": 459
    },
    {
      "epoch": 0.29858012170385395,
      "grad_norm": 0.11095184087753296,
      "learning_rate": 7e-06,
      "loss": 0.1935,
      "step": 460
    },
    {
      "epoch": 0.2992292089249493,
      "grad_norm": 0.07411079108715057,
      "learning_rate": 7e-06,
      "loss": 0.2479,
      "step": 461
    },
    {
      "epoch": 0.2998782961460446,
      "grad_norm": 0.08933519572019577,
      "learning_rate": 7e-06,
      "loss": 0.1983,
      "step": 462
    },
    {
      "epoch": 0.30052738336713997,
      "grad_norm": 0.10530879348516464,
      "learning_rate": 7e-06,
      "loss": 0.1917,
      "step": 463
    },
    {
      "epoch": 0.30117647058823527,
      "grad_norm": 0.1515498012304306,
      "learning_rate": 7e-06,
      "loss": 0.2521,
      "step": 464
    },
    {
      "epoch": 0.3018255578093306,
      "grad_norm": 0.08229900896549225,
      "learning_rate": 7e-06,
      "loss": 0.1765,
      "step": 465
    },
    {
      "epoch": 0.302474645030426,
      "grad_norm": 0.06459085643291473,
      "learning_rate": 7e-06,
      "loss": 0.1782,
      "step": 466
    },
    {
      "epoch": 0.3031237322515213,
      "grad_norm": 0.10680925101041794,
      "learning_rate": 7e-06,
      "loss": 0.2292,
      "step": 467
    },
    {
      "epoch": 0.30377281947261664,
      "grad_norm": 0.12443409860134125,
      "learning_rate": 7e-06,
      "loss": 0.1692,
      "step": 468
    },
    {
      "epoch": 0.30442190669371194,
      "grad_norm": 0.08525492995977402,
      "learning_rate": 7e-06,
      "loss": 0.1921,
      "step": 469
    },
    {
      "epoch": 0.3050709939148073,
      "grad_norm": 0.16101187467575073,
      "learning_rate": 7e-06,
      "loss": 0.2093,
      "step": 470
    },
    {
      "epoch": 0.30572008113590265,
      "grad_norm": 0.192356139421463,
      "learning_rate": 7e-06,
      "loss": 0.1954,
      "step": 471
    },
    {
      "epoch": 0.30636916835699796,
      "grad_norm": 0.11866607517004013,
      "learning_rate": 7e-06,
      "loss": 0.2975,
      "step": 472
    },
    {
      "epoch": 0.3070182555780933,
      "grad_norm": 0.14733244478702545,
      "learning_rate": 7e-06,
      "loss": 0.1909,
      "step": 473
    },
    {
      "epoch": 0.3076673427991886,
      "grad_norm": 0.1148371696472168,
      "learning_rate": 7e-06,
      "loss": 0.2586,
      "step": 474
    },
    {
      "epoch": 0.30831643002028397,
      "grad_norm": 0.11955201625823975,
      "learning_rate": 7e-06,
      "loss": 0.1921,
      "step": 475
    },
    {
      "epoch": 0.30896551724137933,
      "grad_norm": 0.08049837499856949,
      "learning_rate": 7e-06,
      "loss": 0.2112,
      "step": 476
    },
    {
      "epoch": 0.30961460446247463,
      "grad_norm": 0.08945102244615555,
      "learning_rate": 7e-06,
      "loss": 0.1884,
      "step": 477
    },
    {
      "epoch": 0.31026369168357,
      "grad_norm": 0.09706919640302658,
      "learning_rate": 7e-06,
      "loss": 0.2088,
      "step": 478
    },
    {
      "epoch": 0.3109127789046653,
      "grad_norm": 0.06510096788406372,
      "learning_rate": 7e-06,
      "loss": 0.1746,
      "step": 479
    },
    {
      "epoch": 0.31156186612576064,
      "grad_norm": 0.1526442915201187,
      "learning_rate": 7e-06,
      "loss": 0.2062,
      "step": 480
    },
    {
      "epoch": 0.312210953346856,
      "grad_norm": 0.13854192197322845,
      "learning_rate": 7e-06,
      "loss": 0.2385,
      "step": 481
    },
    {
      "epoch": 0.3128600405679513,
      "grad_norm": 0.08473121374845505,
      "learning_rate": 7e-06,
      "loss": 0.1695,
      "step": 482
    },
    {
      "epoch": 0.31350912778904666,
      "grad_norm": 0.08180587738752365,
      "learning_rate": 7e-06,
      "loss": 0.202,
      "step": 483
    },
    {
      "epoch": 0.31415821501014196,
      "grad_norm": 0.12073936313390732,
      "learning_rate": 7e-06,
      "loss": 0.191,
      "step": 484
    },
    {
      "epoch": 0.3148073022312373,
      "grad_norm": 0.09808100014925003,
      "learning_rate": 7e-06,
      "loss": 0.1837,
      "step": 485
    },
    {
      "epoch": 0.3154563894523327,
      "grad_norm": 0.1339402049779892,
      "learning_rate": 7e-06,
      "loss": 0.1739,
      "step": 486
    },
    {
      "epoch": 0.316105476673428,
      "grad_norm": 0.11535376310348511,
      "learning_rate": 7e-06,
      "loss": 0.2254,
      "step": 487
    },
    {
      "epoch": 0.31675456389452333,
      "grad_norm": 0.07179940491914749,
      "learning_rate": 7e-06,
      "loss": 0.1653,
      "step": 488
    },
    {
      "epoch": 0.31740365111561863,
      "grad_norm": 0.10805362462997437,
      "learning_rate": 7e-06,
      "loss": 0.2063,
      "step": 489
    },
    {
      "epoch": 0.318052738336714,
      "grad_norm": 0.13579556345939636,
      "learning_rate": 7e-06,
      "loss": 0.1649,
      "step": 490
    },
    {
      "epoch": 0.31870182555780935,
      "grad_norm": 0.10424883663654327,
      "learning_rate": 7e-06,
      "loss": 0.1995,
      "step": 491
    },
    {
      "epoch": 0.31935091277890465,
      "grad_norm": 0.16089186072349548,
      "learning_rate": 7e-06,
      "loss": 0.2203,
      "step": 492
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.08450519293546677,
      "learning_rate": 7e-06,
      "loss": 0.2069,
      "step": 493
    },
    {
      "epoch": 0.3206490872210953,
      "grad_norm": 0.1669895201921463,
      "learning_rate": 7e-06,
      "loss": 0.2292,
      "step": 494
    },
    {
      "epoch": 0.32129817444219066,
      "grad_norm": 0.12925489246845245,
      "learning_rate": 7e-06,
      "loss": 0.1908,
      "step": 495
    },
    {
      "epoch": 0.321947261663286,
      "grad_norm": 0.25120022892951965,
      "learning_rate": 7e-06,
      "loss": 0.2258,
      "step": 496
    },
    {
      "epoch": 0.3225963488843813,
      "grad_norm": 0.25403451919555664,
      "learning_rate": 7e-06,
      "loss": 0.1991,
      "step": 497
    },
    {
      "epoch": 0.3232454361054767,
      "grad_norm": 0.20550493896007538,
      "learning_rate": 7e-06,
      "loss": 0.2385,
      "step": 498
    },
    {
      "epoch": 0.323894523326572,
      "grad_norm": 0.12534649670124054,
      "learning_rate": 7e-06,
      "loss": 0.2059,
      "step": 499
    },
    {
      "epoch": 0.32454361054766734,
      "grad_norm": 0.21964408457279205,
      "learning_rate": 7e-06,
      "loss": 0.2609,
      "step": 500
    },
    {
      "epoch": 0.32454361054766734,
      "eval_correct_accuracy": 0.6573367260390162,
      "eval_error_accuracy": 0.47816298964430437,
      "eval_f1": 0.5536136905796885,
      "eval_loss": 0.34870651364326477,
      "eval_runtime": 35.1817,
      "eval_samples_per_second": 96.641,
      "eval_steps_per_second": 6.054,
      "step": 500
    },
    {
      "epoch": 0.3251926977687627,
      "grad_norm": 0.09992553293704987,
      "learning_rate": 7e-06,
      "loss": 0.1951,
      "step": 501
    },
    {
      "epoch": 0.325841784989858,
      "grad_norm": 0.18163709342479706,
      "learning_rate": 7e-06,
      "loss": 0.1839,
      "step": 502
    },
    {
      "epoch": 0.32649087221095335,
      "grad_norm": 0.13127198815345764,
      "learning_rate": 7e-06,
      "loss": 0.283,
      "step": 503
    },
    {
      "epoch": 0.32713995943204865,
      "grad_norm": 0.1965264528989792,
      "learning_rate": 7e-06,
      "loss": 0.1996,
      "step": 504
    },
    {
      "epoch": 0.327789046653144,
      "grad_norm": 0.15156516432762146,
      "learning_rate": 7e-06,
      "loss": 0.2076,
      "step": 505
    },
    {
      "epoch": 0.32843813387423937,
      "grad_norm": 0.1189945638179779,
      "learning_rate": 7e-06,
      "loss": 0.184,
      "step": 506
    },
    {
      "epoch": 0.32908722109533467,
      "grad_norm": 0.09533478319644928,
      "learning_rate": 7e-06,
      "loss": 0.1999,
      "step": 507
    },
    {
      "epoch": 0.32973630831643,
      "grad_norm": 0.10704994201660156,
      "learning_rate": 7e-06,
      "loss": 0.2022,
      "step": 508
    },
    {
      "epoch": 0.33038539553752533,
      "grad_norm": 0.18821118772029877,
      "learning_rate": 7e-06,
      "loss": 0.2303,
      "step": 509
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 0.09983609616756439,
      "learning_rate": 7e-06,
      "loss": 0.2791,
      "step": 510
    },
    {
      "epoch": 0.33168356997971604,
      "grad_norm": 0.09815315157175064,
      "learning_rate": 7e-06,
      "loss": 0.1924,
      "step": 511
    },
    {
      "epoch": 0.33233265720081134,
      "grad_norm": 0.1628694236278534,
      "learning_rate": 7e-06,
      "loss": 0.1889,
      "step": 512
    },
    {
      "epoch": 0.3329817444219067,
      "grad_norm": 0.14107106626033783,
      "learning_rate": 7e-06,
      "loss": 0.2161,
      "step": 513
    },
    {
      "epoch": 0.333630831643002,
      "grad_norm": 0.08608640730381012,
      "learning_rate": 7e-06,
      "loss": 0.1889,
      "step": 514
    },
    {
      "epoch": 0.33427991886409736,
      "grad_norm": 0.13827469944953918,
      "learning_rate": 7e-06,
      "loss": 0.1789,
      "step": 515
    },
    {
      "epoch": 0.3349290060851927,
      "grad_norm": 0.13642115890979767,
      "learning_rate": 7e-06,
      "loss": 0.2158,
      "step": 516
    },
    {
      "epoch": 0.335578093306288,
      "grad_norm": 0.12292160838842392,
      "learning_rate": 7e-06,
      "loss": 0.203,
      "step": 517
    },
    {
      "epoch": 0.3362271805273834,
      "grad_norm": 0.15577326714992523,
      "learning_rate": 7e-06,
      "loss": 0.2203,
      "step": 518
    },
    {
      "epoch": 0.3368762677484787,
      "grad_norm": 0.1868695318698883,
      "learning_rate": 7e-06,
      "loss": 0.2543,
      "step": 519
    },
    {
      "epoch": 0.33752535496957403,
      "grad_norm": 0.08295390009880066,
      "learning_rate": 7e-06,
      "loss": 0.2616,
      "step": 520
    },
    {
      "epoch": 0.3381744421906694,
      "grad_norm": 0.10710783302783966,
      "learning_rate": 7e-06,
      "loss": 0.19,
      "step": 521
    },
    {
      "epoch": 0.3388235294117647,
      "grad_norm": 0.17388997972011566,
      "learning_rate": 7e-06,
      "loss": 0.223,
      "step": 522
    },
    {
      "epoch": 0.33947261663286005,
      "grad_norm": 0.08709853142499924,
      "learning_rate": 7e-06,
      "loss": 0.1715,
      "step": 523
    },
    {
      "epoch": 0.34012170385395535,
      "grad_norm": 0.24570000171661377,
      "learning_rate": 7e-06,
      "loss": 0.3727,
      "step": 524
    },
    {
      "epoch": 0.3407707910750507,
      "grad_norm": 0.08102115988731384,
      "learning_rate": 7e-06,
      "loss": 0.1778,
      "step": 525
    },
    {
      "epoch": 0.34141987829614606,
      "grad_norm": 0.07547146081924438,
      "learning_rate": 7e-06,
      "loss": 0.1821,
      "step": 526
    },
    {
      "epoch": 0.34206896551724136,
      "grad_norm": 0.14134980738162994,
      "learning_rate": 7e-06,
      "loss": 0.2052,
      "step": 527
    },
    {
      "epoch": 0.3427180527383367,
      "grad_norm": 0.13734713196754456,
      "learning_rate": 7e-06,
      "loss": 0.2892,
      "step": 528
    },
    {
      "epoch": 0.343367139959432,
      "grad_norm": 0.11005227267742157,
      "learning_rate": 7e-06,
      "loss": 0.2057,
      "step": 529
    },
    {
      "epoch": 0.3440162271805274,
      "grad_norm": 0.13696400821208954,
      "learning_rate": 7e-06,
      "loss": 0.2529,
      "step": 530
    },
    {
      "epoch": 0.34466531440162274,
      "grad_norm": 0.06845694035291672,
      "learning_rate": 7e-06,
      "loss": 0.1642,
      "step": 531
    },
    {
      "epoch": 0.34531440162271804,
      "grad_norm": 0.11955948919057846,
      "learning_rate": 7e-06,
      "loss": 0.1787,
      "step": 532
    },
    {
      "epoch": 0.3459634888438134,
      "grad_norm": 0.11736974120140076,
      "learning_rate": 7e-06,
      "loss": 0.3614,
      "step": 533
    },
    {
      "epoch": 0.3466125760649087,
      "grad_norm": 0.08205635845661163,
      "learning_rate": 7e-06,
      "loss": 0.1971,
      "step": 534
    },
    {
      "epoch": 0.34726166328600405,
      "grad_norm": 0.09197887033224106,
      "learning_rate": 7e-06,
      "loss": 0.1981,
      "step": 535
    },
    {
      "epoch": 0.3479107505070994,
      "grad_norm": 0.15764737129211426,
      "learning_rate": 7e-06,
      "loss": 0.23,
      "step": 536
    },
    {
      "epoch": 0.3485598377281947,
      "grad_norm": 0.11870811879634857,
      "learning_rate": 7e-06,
      "loss": 0.1904,
      "step": 537
    },
    {
      "epoch": 0.34920892494929007,
      "grad_norm": 0.14244960248470306,
      "learning_rate": 7e-06,
      "loss": 0.194,
      "step": 538
    },
    {
      "epoch": 0.34985801217038537,
      "grad_norm": 0.12418539822101593,
      "learning_rate": 7e-06,
      "loss": 0.2169,
      "step": 539
    },
    {
      "epoch": 0.3505070993914807,
      "grad_norm": 0.11288055777549744,
      "learning_rate": 7e-06,
      "loss": 0.1948,
      "step": 540
    },
    {
      "epoch": 0.3511561866125761,
      "grad_norm": 0.10281267762184143,
      "learning_rate": 7e-06,
      "loss": 0.1925,
      "step": 541
    },
    {
      "epoch": 0.3518052738336714,
      "grad_norm": 0.11577431112527847,
      "learning_rate": 7e-06,
      "loss": 0.2243,
      "step": 542
    },
    {
      "epoch": 0.35245436105476674,
      "grad_norm": 0.2195972353219986,
      "learning_rate": 7e-06,
      "loss": 0.2085,
      "step": 543
    },
    {
      "epoch": 0.35310344827586204,
      "grad_norm": 0.12375497072935104,
      "learning_rate": 7e-06,
      "loss": 0.2248,
      "step": 544
    },
    {
      "epoch": 0.3537525354969574,
      "grad_norm": 0.18055009841918945,
      "learning_rate": 7e-06,
      "loss": 0.215,
      "step": 545
    },
    {
      "epoch": 0.35440162271805276,
      "grad_norm": 0.0915975570678711,
      "learning_rate": 7e-06,
      "loss": 0.2629,
      "step": 546
    },
    {
      "epoch": 0.35505070993914806,
      "grad_norm": 0.16360366344451904,
      "learning_rate": 7e-06,
      "loss": 0.2133,
      "step": 547
    },
    {
      "epoch": 0.3556997971602434,
      "grad_norm": 0.07756488025188446,
      "learning_rate": 7e-06,
      "loss": 0.1692,
      "step": 548
    },
    {
      "epoch": 0.3563488843813387,
      "grad_norm": 0.11848773807287216,
      "learning_rate": 7e-06,
      "loss": 0.2115,
      "step": 549
    },
    {
      "epoch": 0.35699797160243407,
      "grad_norm": 0.12601244449615479,
      "learning_rate": 7e-06,
      "loss": 0.2365,
      "step": 550
    },
    {
      "epoch": 0.35764705882352943,
      "grad_norm": 0.12363476306200027,
      "learning_rate": 7e-06,
      "loss": 0.1909,
      "step": 551
    },
    {
      "epoch": 0.35829614604462473,
      "grad_norm": 0.0678907111287117,
      "learning_rate": 7e-06,
      "loss": 0.1771,
      "step": 552
    },
    {
      "epoch": 0.3589452332657201,
      "grad_norm": 0.1932508796453476,
      "learning_rate": 7e-06,
      "loss": 0.2564,
      "step": 553
    },
    {
      "epoch": 0.3595943204868154,
      "grad_norm": 0.07168705761432648,
      "learning_rate": 7e-06,
      "loss": 0.1922,
      "step": 554
    },
    {
      "epoch": 0.36024340770791075,
      "grad_norm": 0.07102219015359879,
      "learning_rate": 7e-06,
      "loss": 0.1927,
      "step": 555
    },
    {
      "epoch": 0.3608924949290061,
      "grad_norm": 0.07950545102357864,
      "learning_rate": 7e-06,
      "loss": 0.197,
      "step": 556
    },
    {
      "epoch": 0.3615415821501014,
      "grad_norm": 0.12928640842437744,
      "learning_rate": 7e-06,
      "loss": 0.2042,
      "step": 557
    },
    {
      "epoch": 0.36219066937119676,
      "grad_norm": 0.08679815381765366,
      "learning_rate": 7e-06,
      "loss": 0.204,
      "step": 558
    },
    {
      "epoch": 0.36283975659229206,
      "grad_norm": 0.08651508390903473,
      "learning_rate": 7e-06,
      "loss": 0.1931,
      "step": 559
    },
    {
      "epoch": 0.3634888438133874,
      "grad_norm": 0.10118532925844193,
      "learning_rate": 7e-06,
      "loss": 0.1997,
      "step": 560
    },
    {
      "epoch": 0.3641379310344828,
      "grad_norm": 0.12476924061775208,
      "learning_rate": 7e-06,
      "loss": 0.1916,
      "step": 561
    },
    {
      "epoch": 0.3647870182555781,
      "grad_norm": 0.10071681439876556,
      "learning_rate": 7e-06,
      "loss": 0.1769,
      "step": 562
    },
    {
      "epoch": 0.36543610547667343,
      "grad_norm": 0.09774439036846161,
      "learning_rate": 7e-06,
      "loss": 0.2085,
      "step": 563
    },
    {
      "epoch": 0.36608519269776874,
      "grad_norm": 0.11157066375017166,
      "learning_rate": 7e-06,
      "loss": 0.1908,
      "step": 564
    },
    {
      "epoch": 0.3667342799188641,
      "grad_norm": 0.10839667916297913,
      "learning_rate": 7e-06,
      "loss": 0.1886,
      "step": 565
    },
    {
      "epoch": 0.36738336713995945,
      "grad_norm": 0.07834111899137497,
      "learning_rate": 7e-06,
      "loss": 0.1944,
      "step": 566
    },
    {
      "epoch": 0.36803245436105475,
      "grad_norm": 0.07881376147270203,
      "learning_rate": 7e-06,
      "loss": 0.1925,
      "step": 567
    },
    {
      "epoch": 0.3686815415821501,
      "grad_norm": 0.09273166954517365,
      "learning_rate": 7e-06,
      "loss": 0.2063,
      "step": 568
    },
    {
      "epoch": 0.3693306288032454,
      "grad_norm": 0.12124530225992203,
      "learning_rate": 7e-06,
      "loss": 0.2068,
      "step": 569
    },
    {
      "epoch": 0.36997971602434077,
      "grad_norm": 0.13046006858348846,
      "learning_rate": 7e-06,
      "loss": 0.2527,
      "step": 570
    },
    {
      "epoch": 0.3706288032454361,
      "grad_norm": 0.0876038521528244,
      "learning_rate": 7e-06,
      "loss": 0.1737,
      "step": 571
    },
    {
      "epoch": 0.3712778904665314,
      "grad_norm": 0.10886076092720032,
      "learning_rate": 7e-06,
      "loss": 0.1981,
      "step": 572
    },
    {
      "epoch": 0.3719269776876268,
      "grad_norm": 0.12242408096790314,
      "learning_rate": 7e-06,
      "loss": 0.1949,
      "step": 573
    },
    {
      "epoch": 0.3725760649087221,
      "grad_norm": 0.07582924515008926,
      "learning_rate": 7e-06,
      "loss": 0.1717,
      "step": 574
    },
    {
      "epoch": 0.37322515212981744,
      "grad_norm": 0.07823781669139862,
      "learning_rate": 7e-06,
      "loss": 0.3328,
      "step": 575
    },
    {
      "epoch": 0.3738742393509128,
      "grad_norm": 0.095790795981884,
      "learning_rate": 7e-06,
      "loss": 0.1873,
      "step": 576
    },
    {
      "epoch": 0.3745233265720081,
      "grad_norm": 0.0986112579703331,
      "learning_rate": 7e-06,
      "loss": 0.2097,
      "step": 577
    },
    {
      "epoch": 0.37517241379310345,
      "grad_norm": 0.09565339237451553,
      "learning_rate": 7e-06,
      "loss": 0.2119,
      "step": 578
    },
    {
      "epoch": 0.37582150101419876,
      "grad_norm": 0.10886640101671219,
      "learning_rate": 7e-06,
      "loss": 0.2347,
      "step": 579
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.10140598565340042,
      "learning_rate": 7e-06,
      "loss": 0.2336,
      "step": 580
    },
    {
      "epoch": 0.37711967545638947,
      "grad_norm": 0.12961223721504211,
      "learning_rate": 7e-06,
      "loss": 0.4248,
      "step": 581
    },
    {
      "epoch": 0.37776876267748477,
      "grad_norm": 0.07052242010831833,
      "learning_rate": 7e-06,
      "loss": 0.1872,
      "step": 582
    },
    {
      "epoch": 0.3784178498985801,
      "grad_norm": 0.10490433126688004,
      "learning_rate": 7e-06,
      "loss": 0.1853,
      "step": 583
    },
    {
      "epoch": 0.37906693711967543,
      "grad_norm": 0.09426899999380112,
      "learning_rate": 7e-06,
      "loss": 0.2191,
      "step": 584
    },
    {
      "epoch": 0.3797160243407708,
      "grad_norm": 0.1251821517944336,
      "learning_rate": 7e-06,
      "loss": 0.2271,
      "step": 585
    },
    {
      "epoch": 0.38036511156186614,
      "grad_norm": 0.09315302968025208,
      "learning_rate": 7e-06,
      "loss": 0.2028,
      "step": 586
    },
    {
      "epoch": 0.38101419878296144,
      "grad_norm": 0.12801644206047058,
      "learning_rate": 7e-06,
      "loss": 0.1859,
      "step": 587
    },
    {
      "epoch": 0.3816632860040568,
      "grad_norm": 0.05587161332368851,
      "learning_rate": 7e-06,
      "loss": 0.1675,
      "step": 588
    },
    {
      "epoch": 0.3823123732251521,
      "grad_norm": 0.06031392887234688,
      "learning_rate": 7e-06,
      "loss": 0.155,
      "step": 589
    },
    {
      "epoch": 0.38296146044624746,
      "grad_norm": 0.12475478649139404,
      "learning_rate": 7e-06,
      "loss": 0.1967,
      "step": 590
    },
    {
      "epoch": 0.3836105476673428,
      "grad_norm": 0.10604110360145569,
      "learning_rate": 7e-06,
      "loss": 0.2148,
      "step": 591
    },
    {
      "epoch": 0.3842596348884381,
      "grad_norm": 0.08813691139221191,
      "learning_rate": 7e-06,
      "loss": 0.2121,
      "step": 592
    },
    {
      "epoch": 0.3849087221095335,
      "grad_norm": 0.1167176142334938,
      "learning_rate": 7e-06,
      "loss": 0.2076,
      "step": 593
    },
    {
      "epoch": 0.3855578093306288,
      "grad_norm": 0.09978288412094116,
      "learning_rate": 7e-06,
      "loss": 0.177,
      "step": 594
    },
    {
      "epoch": 0.38620689655172413,
      "grad_norm": 0.10563702881336212,
      "learning_rate": 7e-06,
      "loss": 0.1877,
      "step": 595
    },
    {
      "epoch": 0.3868559837728195,
      "grad_norm": 0.08122760057449341,
      "learning_rate": 7e-06,
      "loss": 0.1857,
      "step": 596
    },
    {
      "epoch": 0.3875050709939148,
      "grad_norm": 0.08920778334140778,
      "learning_rate": 7e-06,
      "loss": 0.2291,
      "step": 597
    },
    {
      "epoch": 0.38815415821501015,
      "grad_norm": 0.10444041341543198,
      "learning_rate": 7e-06,
      "loss": 0.183,
      "step": 598
    },
    {
      "epoch": 0.38880324543610545,
      "grad_norm": 0.2296033352613449,
      "learning_rate": 7e-06,
      "loss": 0.1522,
      "step": 599
    },
    {
      "epoch": 0.3894523326572008,
      "grad_norm": 0.14563967287540436,
      "learning_rate": 7e-06,
      "loss": 0.2106,
      "step": 600
    },
    {
      "epoch": 0.3894523326572008,
      "eval_correct_accuracy": 0.6556403731976251,
      "eval_error_accuracy": 0.5015758667266997,
      "eval_f1": 0.5683525292889439,
      "eval_loss": 0.3721383213996887,
      "eval_runtime": 35.3516,
      "eval_samples_per_second": 96.177,
      "eval_steps_per_second": 6.025,
      "step": 600
    },
    {
      "epoch": 0.39010141987829616,
      "grad_norm": 0.07153713703155518,
      "learning_rate": 7e-06,
      "loss": 0.1923,
      "step": 601
    },
    {
      "epoch": 0.39075050709939146,
      "grad_norm": 0.07804547995328903,
      "learning_rate": 7e-06,
      "loss": 0.2029,
      "step": 602
    },
    {
      "epoch": 0.3913995943204868,
      "grad_norm": 0.11078830063343048,
      "learning_rate": 7e-06,
      "loss": 0.1878,
      "step": 603
    },
    {
      "epoch": 0.3920486815415821,
      "grad_norm": 0.0691380500793457,
      "learning_rate": 7e-06,
      "loss": 0.1895,
      "step": 604
    },
    {
      "epoch": 0.3926977687626775,
      "grad_norm": 0.06876414269208908,
      "learning_rate": 7e-06,
      "loss": 0.1656,
      "step": 605
    },
    {
      "epoch": 0.39334685598377284,
      "grad_norm": 0.08713028579950333,
      "learning_rate": 7e-06,
      "loss": 0.2295,
      "step": 606
    },
    {
      "epoch": 0.39399594320486814,
      "grad_norm": 0.07250560075044632,
      "learning_rate": 7e-06,
      "loss": 0.1697,
      "step": 607
    },
    {
      "epoch": 0.3946450304259635,
      "grad_norm": 0.16338257491588593,
      "learning_rate": 7e-06,
      "loss": 0.3056,
      "step": 608
    },
    {
      "epoch": 0.3952941176470588,
      "grad_norm": 0.10265594720840454,
      "learning_rate": 7e-06,
      "loss": 0.1892,
      "step": 609
    },
    {
      "epoch": 0.39594320486815415,
      "grad_norm": 0.08299802988767624,
      "learning_rate": 7e-06,
      "loss": 0.2214,
      "step": 610
    },
    {
      "epoch": 0.3965922920892495,
      "grad_norm": 0.12102089822292328,
      "learning_rate": 7e-06,
      "loss": 0.2139,
      "step": 611
    },
    {
      "epoch": 0.3972413793103448,
      "grad_norm": 0.16628195345401764,
      "learning_rate": 7e-06,
      "loss": 0.2382,
      "step": 612
    },
    {
      "epoch": 0.39789046653144017,
      "grad_norm": 0.09264989197254181,
      "learning_rate": 7e-06,
      "loss": 0.1774,
      "step": 613
    },
    {
      "epoch": 0.39853955375253547,
      "grad_norm": 0.10601548105478287,
      "learning_rate": 7e-06,
      "loss": 0.3461,
      "step": 614
    },
    {
      "epoch": 0.3991886409736308,
      "grad_norm": 0.29625287652015686,
      "learning_rate": 7e-06,
      "loss": 0.1908,
      "step": 615
    },
    {
      "epoch": 0.3998377281947262,
      "grad_norm": 0.08462506532669067,
      "learning_rate": 7e-06,
      "loss": 0.2074,
      "step": 616
    },
    {
      "epoch": 0.4004868154158215,
      "grad_norm": 0.0705549493432045,
      "learning_rate": 7e-06,
      "loss": 0.2036,
      "step": 617
    },
    {
      "epoch": 0.40113590263691684,
      "grad_norm": 0.10002121329307556,
      "learning_rate": 7e-06,
      "loss": 0.1615,
      "step": 618
    },
    {
      "epoch": 0.4017849898580122,
      "grad_norm": 0.11986624449491501,
      "learning_rate": 7e-06,
      "loss": 0.1902,
      "step": 619
    },
    {
      "epoch": 0.4024340770791075,
      "grad_norm": 0.4402817189693451,
      "learning_rate": 7e-06,
      "loss": 0.2609,
      "step": 620
    },
    {
      "epoch": 0.40308316430020286,
      "grad_norm": 0.12506885826587677,
      "learning_rate": 7e-06,
      "loss": 0.2,
      "step": 621
    },
    {
      "epoch": 0.40373225152129816,
      "grad_norm": 0.1072239950299263,
      "learning_rate": 7e-06,
      "loss": 0.2277,
      "step": 622
    },
    {
      "epoch": 0.4043813387423935,
      "grad_norm": 0.16495779156684875,
      "learning_rate": 7e-06,
      "loss": 0.2189,
      "step": 623
    },
    {
      "epoch": 0.40503042596348887,
      "grad_norm": 0.09068227559328079,
      "learning_rate": 7e-06,
      "loss": 0.2915,
      "step": 624
    },
    {
      "epoch": 0.4056795131845842,
      "grad_norm": 0.1521327942609787,
      "learning_rate": 7e-06,
      "loss": 0.2421,
      "step": 625
    },
    {
      "epoch": 0.40632860040567953,
      "grad_norm": 0.17417506873607635,
      "learning_rate": 7e-06,
      "loss": 0.2117,
      "step": 626
    },
    {
      "epoch": 0.40697768762677483,
      "grad_norm": 0.18474262952804565,
      "learning_rate": 7e-06,
      "loss": 0.2069,
      "step": 627
    },
    {
      "epoch": 0.4076267748478702,
      "grad_norm": 0.07663752883672714,
      "learning_rate": 7e-06,
      "loss": 0.22,
      "step": 628
    },
    {
      "epoch": 0.40827586206896554,
      "grad_norm": 0.08460376411676407,
      "learning_rate": 7e-06,
      "loss": 0.182,
      "step": 629
    },
    {
      "epoch": 0.40892494929006085,
      "grad_norm": 0.1088784858584404,
      "learning_rate": 7e-06,
      "loss": 0.2191,
      "step": 630
    },
    {
      "epoch": 0.4095740365111562,
      "grad_norm": 0.17458195984363556,
      "learning_rate": 7e-06,
      "loss": 0.1873,
      "step": 631
    },
    {
      "epoch": 0.4102231237322515,
      "grad_norm": 0.12634965777397156,
      "learning_rate": 7e-06,
      "loss": 0.2244,
      "step": 632
    },
    {
      "epoch": 0.41087221095334686,
      "grad_norm": 0.16512618958950043,
      "learning_rate": 7e-06,
      "loss": 0.1774,
      "step": 633
    },
    {
      "epoch": 0.4115212981744422,
      "grad_norm": 0.0795673057436943,
      "learning_rate": 7e-06,
      "loss": 0.1786,
      "step": 634
    },
    {
      "epoch": 0.4121703853955375,
      "grad_norm": 0.06733974814414978,
      "learning_rate": 7e-06,
      "loss": 0.1912,
      "step": 635
    },
    {
      "epoch": 0.4128194726166329,
      "grad_norm": 0.08562178909778595,
      "learning_rate": 7e-06,
      "loss": 0.1823,
      "step": 636
    },
    {
      "epoch": 0.4134685598377282,
      "grad_norm": 0.15826581418514252,
      "learning_rate": 7e-06,
      "loss": 0.1829,
      "step": 637
    },
    {
      "epoch": 0.41411764705882353,
      "grad_norm": 0.08639402687549591,
      "learning_rate": 7e-06,
      "loss": 0.1736,
      "step": 638
    },
    {
      "epoch": 0.4147667342799189,
      "grad_norm": 0.11472704261541367,
      "learning_rate": 7e-06,
      "loss": 0.196,
      "step": 639
    },
    {
      "epoch": 0.4154158215010142,
      "grad_norm": 0.06684121489524841,
      "learning_rate": 7e-06,
      "loss": 0.141,
      "step": 640
    },
    {
      "epoch": 0.41606490872210955,
      "grad_norm": 0.09874467551708221,
      "learning_rate": 7e-06,
      "loss": 0.2435,
      "step": 641
    },
    {
      "epoch": 0.41671399594320485,
      "grad_norm": 0.10944344103336334,
      "learning_rate": 7e-06,
      "loss": 0.2264,
      "step": 642
    },
    {
      "epoch": 0.4173630831643002,
      "grad_norm": 0.09378840029239655,
      "learning_rate": 7e-06,
      "loss": 0.2305,
      "step": 643
    },
    {
      "epoch": 0.41801217038539557,
      "grad_norm": 0.08979783952236176,
      "learning_rate": 7e-06,
      "loss": 0.206,
      "step": 644
    },
    {
      "epoch": 0.41866125760649087,
      "grad_norm": 0.1309386044740677,
      "learning_rate": 7e-06,
      "loss": 0.2251,
      "step": 645
    },
    {
      "epoch": 0.4193103448275862,
      "grad_norm": 0.07289421558380127,
      "learning_rate": 7e-06,
      "loss": 0.248,
      "step": 646
    },
    {
      "epoch": 0.4199594320486815,
      "grad_norm": 0.0951872169971466,
      "learning_rate": 7e-06,
      "loss": 0.1851,
      "step": 647
    },
    {
      "epoch": 0.4206085192697769,
      "grad_norm": 0.1082032322883606,
      "learning_rate": 7e-06,
      "loss": 0.2349,
      "step": 648
    },
    {
      "epoch": 0.42125760649087224,
      "grad_norm": 0.08437170833349228,
      "learning_rate": 7e-06,
      "loss": 0.2011,
      "step": 649
    },
    {
      "epoch": 0.42190669371196754,
      "grad_norm": 0.08519117534160614,
      "learning_rate": 7e-06,
      "loss": 0.199,
      "step": 650
    },
    {
      "epoch": 0.4225557809330629,
      "grad_norm": 0.08078327029943466,
      "learning_rate": 7e-06,
      "loss": 0.2026,
      "step": 651
    },
    {
      "epoch": 0.4232048681541582,
      "grad_norm": 0.14362947642803192,
      "learning_rate": 7e-06,
      "loss": 0.1912,
      "step": 652
    },
    {
      "epoch": 0.42385395537525355,
      "grad_norm": 0.12132386863231659,
      "learning_rate": 7e-06,
      "loss": 0.2321,
      "step": 653
    },
    {
      "epoch": 0.4245030425963489,
      "grad_norm": 0.10531847178936005,
      "learning_rate": 7e-06,
      "loss": 0.1467,
      "step": 654
    },
    {
      "epoch": 0.4251521298174442,
      "grad_norm": 0.10905103385448456,
      "learning_rate": 7e-06,
      "loss": 0.1692,
      "step": 655
    },
    {
      "epoch": 0.42580121703853957,
      "grad_norm": 0.10729187726974487,
      "learning_rate": 7e-06,
      "loss": 0.2228,
      "step": 656
    },
    {
      "epoch": 0.42645030425963487,
      "grad_norm": 0.10271120816469193,
      "learning_rate": 7e-06,
      "loss": 0.1863,
      "step": 657
    },
    {
      "epoch": 0.42709939148073023,
      "grad_norm": 0.05799393728375435,
      "learning_rate": 7e-06,
      "loss": 0.1447,
      "step": 658
    },
    {
      "epoch": 0.4277484787018256,
      "grad_norm": 0.15353858470916748,
      "learning_rate": 7e-06,
      "loss": 0.2078,
      "step": 659
    },
    {
      "epoch": 0.4283975659229209,
      "grad_norm": 0.10132794082164764,
      "learning_rate": 7e-06,
      "loss": 0.1596,
      "step": 660
    },
    {
      "epoch": 0.42904665314401624,
      "grad_norm": 0.06386853754520416,
      "learning_rate": 7e-06,
      "loss": 0.153,
      "step": 661
    },
    {
      "epoch": 0.42969574036511154,
      "grad_norm": 0.0759631097316742,
      "learning_rate": 7e-06,
      "loss": 0.1806,
      "step": 662
    },
    {
      "epoch": 0.4303448275862069,
      "grad_norm": 0.0948052704334259,
      "learning_rate": 7e-06,
      "loss": 0.2387,
      "step": 663
    },
    {
      "epoch": 0.43099391480730226,
      "grad_norm": 0.18104346096515656,
      "learning_rate": 7e-06,
      "loss": 0.2232,
      "step": 664
    },
    {
      "epoch": 0.43164300202839756,
      "grad_norm": 0.14162711799144745,
      "learning_rate": 7e-06,
      "loss": 0.2115,
      "step": 665
    },
    {
      "epoch": 0.4322920892494929,
      "grad_norm": 0.10143130272626877,
      "learning_rate": 7e-06,
      "loss": 0.1544,
      "step": 666
    },
    {
      "epoch": 0.4329411764705882,
      "grad_norm": 0.07446250319480896,
      "learning_rate": 7e-06,
      "loss": 0.1739,
      "step": 667
    },
    {
      "epoch": 0.4335902636916836,
      "grad_norm": 0.0652833953499794,
      "learning_rate": 7e-06,
      "loss": 0.1508,
      "step": 668
    },
    {
      "epoch": 0.43423935091277893,
      "grad_norm": 0.13196003437042236,
      "learning_rate": 7e-06,
      "loss": 0.2476,
      "step": 669
    },
    {
      "epoch": 0.43488843813387423,
      "grad_norm": 0.06971034407615662,
      "learning_rate": 7e-06,
      "loss": 0.2137,
      "step": 670
    },
    {
      "epoch": 0.4355375253549696,
      "grad_norm": 0.06069733574986458,
      "learning_rate": 7e-06,
      "loss": 0.1558,
      "step": 671
    },
    {
      "epoch": 0.4361866125760649,
      "grad_norm": 0.15604910254478455,
      "learning_rate": 7e-06,
      "loss": 0.1874,
      "step": 672
    },
    {
      "epoch": 0.43683569979716025,
      "grad_norm": 0.08152856677770615,
      "learning_rate": 7e-06,
      "loss": 0.1488,
      "step": 673
    },
    {
      "epoch": 0.4374847870182556,
      "grad_norm": 0.12127961963415146,
      "learning_rate": 7e-06,
      "loss": 0.202,
      "step": 674
    },
    {
      "epoch": 0.4381338742393509,
      "grad_norm": 0.10285872966051102,
      "learning_rate": 7e-06,
      "loss": 0.649,
      "step": 675
    },
    {
      "epoch": 0.43878296146044626,
      "grad_norm": 0.1510424166917801,
      "learning_rate": 7e-06,
      "loss": 0.2769,
      "step": 676
    },
    {
      "epoch": 0.43943204868154156,
      "grad_norm": 0.10512597113847733,
      "learning_rate": 7e-06,
      "loss": 0.2062,
      "step": 677
    },
    {
      "epoch": 0.4400811359026369,
      "grad_norm": 0.13170289993286133,
      "learning_rate": 7e-06,
      "loss": 0.2031,
      "step": 678
    },
    {
      "epoch": 0.4407302231237323,
      "grad_norm": 0.11077514290809631,
      "learning_rate": 7e-06,
      "loss": 0.2035,
      "step": 679
    },
    {
      "epoch": 0.4413793103448276,
      "grad_norm": 0.12480034679174423,
      "learning_rate": 7e-06,
      "loss": 0.181,
      "step": 680
    },
    {
      "epoch": 0.44202839756592294,
      "grad_norm": 0.10529381036758423,
      "learning_rate": 7e-06,
      "loss": 0.2416,
      "step": 681
    },
    {
      "epoch": 0.44267748478701824,
      "grad_norm": 0.10327468812465668,
      "learning_rate": 7e-06,
      "loss": 0.2034,
      "step": 682
    },
    {
      "epoch": 0.4433265720081136,
      "grad_norm": 0.08385145664215088,
      "learning_rate": 7e-06,
      "loss": 0.1988,
      "step": 683
    },
    {
      "epoch": 0.44397565922920895,
      "grad_norm": 0.10325571894645691,
      "learning_rate": 7e-06,
      "loss": 0.1852,
      "step": 684
    },
    {
      "epoch": 0.44462474645030425,
      "grad_norm": 0.12049216032028198,
      "learning_rate": 7e-06,
      "loss": 0.2072,
      "step": 685
    },
    {
      "epoch": 0.4452738336713996,
      "grad_norm": 0.08923596888780594,
      "learning_rate": 7e-06,
      "loss": 0.1981,
      "step": 686
    },
    {
      "epoch": 0.4459229208924949,
      "grad_norm": 0.1037791445851326,
      "learning_rate": 7e-06,
      "loss": 0.185,
      "step": 687
    },
    {
      "epoch": 0.44657200811359027,
      "grad_norm": 0.0843873918056488,
      "learning_rate": 7e-06,
      "loss": 0.2073,
      "step": 688
    },
    {
      "epoch": 0.4472210953346856,
      "grad_norm": 0.14069949090480804,
      "learning_rate": 7e-06,
      "loss": 0.2336,
      "step": 689
    },
    {
      "epoch": 0.4478701825557809,
      "grad_norm": 0.1185181736946106,
      "learning_rate": 7e-06,
      "loss": 0.2153,
      "step": 690
    },
    {
      "epoch": 0.4485192697768763,
      "grad_norm": 0.06658674776554108,
      "learning_rate": 7e-06,
      "loss": 0.1793,
      "step": 691
    },
    {
      "epoch": 0.4491683569979716,
      "grad_norm": 0.08426418900489807,
      "learning_rate": 7e-06,
      "loss": 0.194,
      "step": 692
    },
    {
      "epoch": 0.44981744421906694,
      "grad_norm": 0.08903374522924423,
      "learning_rate": 7e-06,
      "loss": 0.1638,
      "step": 693
    },
    {
      "epoch": 0.4504665314401623,
      "grad_norm": 0.07060875743627548,
      "learning_rate": 7e-06,
      "loss": 0.1745,
      "step": 694
    },
    {
      "epoch": 0.4511156186612576,
      "grad_norm": 0.16352969408035278,
      "learning_rate": 7e-06,
      "loss": 0.1957,
      "step": 695
    },
    {
      "epoch": 0.45176470588235296,
      "grad_norm": 0.08656806498765945,
      "learning_rate": 7e-06,
      "loss": 0.1828,
      "step": 696
    },
    {
      "epoch": 0.45241379310344826,
      "grad_norm": 0.10093386471271515,
      "learning_rate": 7e-06,
      "loss": 0.1859,
      "step": 697
    },
    {
      "epoch": 0.4530628803245436,
      "grad_norm": 0.20284637808799744,
      "learning_rate": 7e-06,
      "loss": 0.1817,
      "step": 698
    },
    {
      "epoch": 0.45371196754563897,
      "grad_norm": 0.12196527421474457,
      "learning_rate": 7e-06,
      "loss": 0.2742,
      "step": 699
    },
    {
      "epoch": 0.4543610547667343,
      "grad_norm": 0.19494572281837463,
      "learning_rate": 7e-06,
      "loss": 0.2155,
      "step": 700
    },
    {
      "epoch": 0.4543610547667343,
      "eval_correct_accuracy": 0.7073791348600509,
      "eval_error_accuracy": 0.465105808194507,
      "eval_f1": 0.5612117173324005,
      "eval_loss": 0.3553255796432495,
      "eval_runtime": 35.1312,
      "eval_samples_per_second": 96.78,
      "eval_steps_per_second": 6.063,
      "step": 700
    },
    {
      "epoch": 0.45501014198782963,
      "grad_norm": 0.12152343988418579,
      "learning_rate": 7e-06,
      "loss": 0.1977,
      "step": 701
    },
    {
      "epoch": 0.45565922920892493,
      "grad_norm": 0.08255361765623093,
      "learning_rate": 7e-06,
      "loss": 0.1775,
      "step": 702
    },
    {
      "epoch": 0.4563083164300203,
      "grad_norm": 0.12483001500368118,
      "learning_rate": 7e-06,
      "loss": 0.1639,
      "step": 703
    },
    {
      "epoch": 0.45695740365111565,
      "grad_norm": 0.13598322868347168,
      "learning_rate": 7e-06,
      "loss": 0.1932,
      "step": 704
    },
    {
      "epoch": 0.45760649087221095,
      "grad_norm": 0.14067009091377258,
      "learning_rate": 7e-06,
      "loss": 0.1967,
      "step": 705
    },
    {
      "epoch": 0.4582555780933063,
      "grad_norm": 0.1968710869550705,
      "learning_rate": 7e-06,
      "loss": 0.2906,
      "step": 706
    },
    {
      "epoch": 0.4589046653144016,
      "grad_norm": 0.2505093514919281,
      "learning_rate": 7e-06,
      "loss": 0.3089,
      "step": 707
    },
    {
      "epoch": 0.45955375253549696,
      "grad_norm": 0.12645353376865387,
      "learning_rate": 7e-06,
      "loss": 0.2161,
      "step": 708
    },
    {
      "epoch": 0.4602028397565923,
      "grad_norm": 0.07556287944316864,
      "learning_rate": 7e-06,
      "loss": 0.1608,
      "step": 709
    },
    {
      "epoch": 0.4608519269776876,
      "grad_norm": 0.18457825481891632,
      "learning_rate": 7e-06,
      "loss": 0.2371,
      "step": 710
    },
    {
      "epoch": 0.461501014198783,
      "grad_norm": 0.07243886590003967,
      "learning_rate": 7e-06,
      "loss": 0.1829,
      "step": 711
    },
    {
      "epoch": 0.4621501014198783,
      "grad_norm": 0.11358308792114258,
      "learning_rate": 7e-06,
      "loss": 0.1858,
      "step": 712
    },
    {
      "epoch": 0.46279918864097364,
      "grad_norm": 0.10195986181497574,
      "learning_rate": 7e-06,
      "loss": 0.1908,
      "step": 713
    },
    {
      "epoch": 0.463448275862069,
      "grad_norm": 0.09241017699241638,
      "learning_rate": 7e-06,
      "loss": 0.1732,
      "step": 714
    },
    {
      "epoch": 0.4640973630831643,
      "grad_norm": 0.20151405036449432,
      "learning_rate": 7e-06,
      "loss": 0.2044,
      "step": 715
    },
    {
      "epoch": 0.46474645030425965,
      "grad_norm": 0.11214257776737213,
      "learning_rate": 7e-06,
      "loss": 0.1754,
      "step": 716
    },
    {
      "epoch": 0.46539553752535495,
      "grad_norm": 0.08307798951864243,
      "learning_rate": 7e-06,
      "loss": 0.1626,
      "step": 717
    },
    {
      "epoch": 0.4660446247464503,
      "grad_norm": 0.08797349780797958,
      "learning_rate": 7e-06,
      "loss": 0.2238,
      "step": 718
    },
    {
      "epoch": 0.46669371196754567,
      "grad_norm": 0.1508927345275879,
      "learning_rate": 7e-06,
      "loss": 0.194,
      "step": 719
    },
    {
      "epoch": 0.46734279918864097,
      "grad_norm": 0.21975985169410706,
      "learning_rate": 7e-06,
      "loss": 0.2343,
      "step": 720
    },
    {
      "epoch": 0.4679918864097363,
      "grad_norm": 0.12118788063526154,
      "learning_rate": 7e-06,
      "loss": 0.2023,
      "step": 721
    },
    {
      "epoch": 0.4686409736308316,
      "grad_norm": 0.1447582095861435,
      "learning_rate": 7e-06,
      "loss": 0.1681,
      "step": 722
    },
    {
      "epoch": 0.469290060851927,
      "grad_norm": 0.06311909854412079,
      "learning_rate": 7e-06,
      "loss": 0.1575,
      "step": 723
    },
    {
      "epoch": 0.46993914807302234,
      "grad_norm": 0.1167735606431961,
      "learning_rate": 7e-06,
      "loss": 0.2169,
      "step": 724
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.07715723663568497,
      "learning_rate": 7e-06,
      "loss": 0.2038,
      "step": 725
    },
    {
      "epoch": 0.471237322515213,
      "grad_norm": 0.10446905344724655,
      "learning_rate": 7e-06,
      "loss": 0.2256,
      "step": 726
    },
    {
      "epoch": 0.4718864097363083,
      "grad_norm": 0.11108936369419098,
      "learning_rate": 7e-06,
      "loss": 0.2787,
      "step": 727
    },
    {
      "epoch": 0.47253549695740366,
      "grad_norm": 0.23579511046409607,
      "learning_rate": 7e-06,
      "loss": 0.2168,
      "step": 728
    },
    {
      "epoch": 0.473184584178499,
      "grad_norm": 0.11473851650953293,
      "learning_rate": 7e-06,
      "loss": 0.237,
      "step": 729
    },
    {
      "epoch": 0.4738336713995943,
      "grad_norm": 0.08642309159040451,
      "learning_rate": 7e-06,
      "loss": 0.165,
      "step": 730
    },
    {
      "epoch": 0.47448275862068967,
      "grad_norm": 0.1072726920247078,
      "learning_rate": 7e-06,
      "loss": 0.1961,
      "step": 731
    },
    {
      "epoch": 0.47513184584178497,
      "grad_norm": 0.10566612333059311,
      "learning_rate": 7e-06,
      "loss": 0.2141,
      "step": 732
    },
    {
      "epoch": 0.47578093306288033,
      "grad_norm": 0.12592172622680664,
      "learning_rate": 7e-06,
      "loss": 0.245,
      "step": 733
    },
    {
      "epoch": 0.4764300202839757,
      "grad_norm": 0.10161009430885315,
      "learning_rate": 7e-06,
      "loss": 0.1865,
      "step": 734
    },
    {
      "epoch": 0.477079107505071,
      "grad_norm": 0.1838059276342392,
      "learning_rate": 7e-06,
      "loss": 0.4349,
      "step": 735
    },
    {
      "epoch": 0.47772819472616634,
      "grad_norm": 0.10085088759660721,
      "learning_rate": 7e-06,
      "loss": 0.2316,
      "step": 736
    },
    {
      "epoch": 0.47837728194726165,
      "grad_norm": 0.0999818667769432,
      "learning_rate": 7e-06,
      "loss": 0.2007,
      "step": 737
    },
    {
      "epoch": 0.479026369168357,
      "grad_norm": 0.11231537163257599,
      "learning_rate": 7e-06,
      "loss": 0.1653,
      "step": 738
    },
    {
      "epoch": 0.47967545638945236,
      "grad_norm": 0.09104875475168228,
      "learning_rate": 7e-06,
      "loss": 0.1896,
      "step": 739
    },
    {
      "epoch": 0.48032454361054766,
      "grad_norm": 0.13571256399154663,
      "learning_rate": 7e-06,
      "loss": 0.2398,
      "step": 740
    },
    {
      "epoch": 0.480973630831643,
      "grad_norm": 0.0783463716506958,
      "learning_rate": 7e-06,
      "loss": 0.1762,
      "step": 741
    },
    {
      "epoch": 0.4816227180527383,
      "grad_norm": 0.13551665842533112,
      "learning_rate": 7e-06,
      "loss": 0.2343,
      "step": 742
    },
    {
      "epoch": 0.4822718052738337,
      "grad_norm": 0.07081679999828339,
      "learning_rate": 7e-06,
      "loss": 0.2753,
      "step": 743
    },
    {
      "epoch": 0.48292089249492903,
      "grad_norm": 0.11201386153697968,
      "learning_rate": 7e-06,
      "loss": 0.2087,
      "step": 744
    },
    {
      "epoch": 0.48356997971602433,
      "grad_norm": 0.1405518352985382,
      "learning_rate": 7e-06,
      "loss": 0.3303,
      "step": 745
    },
    {
      "epoch": 0.4842190669371197,
      "grad_norm": 0.07173644751310349,
      "learning_rate": 7e-06,
      "loss": 0.159,
      "step": 746
    },
    {
      "epoch": 0.484868154158215,
      "grad_norm": 0.20204587280750275,
      "learning_rate": 7e-06,
      "loss": 0.205,
      "step": 747
    },
    {
      "epoch": 0.48551724137931035,
      "grad_norm": 0.06936550885438919,
      "learning_rate": 7e-06,
      "loss": 0.179,
      "step": 748
    },
    {
      "epoch": 0.4861663286004057,
      "grad_norm": 0.06757465749979019,
      "learning_rate": 7e-06,
      "loss": 0.1802,
      "step": 749
    },
    {
      "epoch": 0.486815415821501,
      "grad_norm": 0.10669063031673431,
      "learning_rate": 7e-06,
      "loss": 0.1665,
      "step": 750
    },
    {
      "epoch": 0.48746450304259636,
      "grad_norm": 0.18585270643234253,
      "learning_rate": 7e-06,
      "loss": 0.1579,
      "step": 751
    },
    {
      "epoch": 0.48811359026369167,
      "grad_norm": 0.09203337132930756,
      "learning_rate": 7e-06,
      "loss": 0.2139,
      "step": 752
    },
    {
      "epoch": 0.488762677484787,
      "grad_norm": 0.12100082635879517,
      "learning_rate": 7e-06,
      "loss": 0.2464,
      "step": 753
    },
    {
      "epoch": 0.4894117647058824,
      "grad_norm": 0.16897863149642944,
      "learning_rate": 7e-06,
      "loss": 0.1921,
      "step": 754
    },
    {
      "epoch": 0.4900608519269777,
      "grad_norm": 0.0945892184972763,
      "learning_rate": 7e-06,
      "loss": 0.1656,
      "step": 755
    },
    {
      "epoch": 0.49070993914807304,
      "grad_norm": 0.10539981722831726,
      "learning_rate": 7e-06,
      "loss": 0.187,
      "step": 756
    },
    {
      "epoch": 0.49135902636916834,
      "grad_norm": 0.08753205090761185,
      "learning_rate": 7e-06,
      "loss": 0.2055,
      "step": 757
    },
    {
      "epoch": 0.4920081135902637,
      "grad_norm": 0.08646341413259506,
      "learning_rate": 7e-06,
      "loss": 0.1829,
      "step": 758
    },
    {
      "epoch": 0.49265720081135905,
      "grad_norm": 0.1714838296175003,
      "learning_rate": 7e-06,
      "loss": 0.2026,
      "step": 759
    },
    {
      "epoch": 0.49330628803245435,
      "grad_norm": 0.10450273752212524,
      "learning_rate": 7e-06,
      "loss": 0.1931,
      "step": 760
    },
    {
      "epoch": 0.4939553752535497,
      "grad_norm": 0.11428748071193695,
      "learning_rate": 7e-06,
      "loss": 0.2021,
      "step": 761
    },
    {
      "epoch": 0.494604462474645,
      "grad_norm": 0.11454441398382187,
      "learning_rate": 7e-06,
      "loss": 0.1838,
      "step": 762
    },
    {
      "epoch": 0.49525354969574037,
      "grad_norm": 0.1353677213191986,
      "learning_rate": 7e-06,
      "loss": 0.1919,
      "step": 763
    },
    {
      "epoch": 0.4959026369168357,
      "grad_norm": 0.12237711250782013,
      "learning_rate": 7e-06,
      "loss": 0.1975,
      "step": 764
    },
    {
      "epoch": 0.496551724137931,
      "grad_norm": 0.08232047408819199,
      "learning_rate": 7e-06,
      "loss": 0.1719,
      "step": 765
    },
    {
      "epoch": 0.4972008113590264,
      "grad_norm": 0.09806603193283081,
      "learning_rate": 7e-06,
      "loss": 0.1777,
      "step": 766
    },
    {
      "epoch": 0.4978498985801217,
      "grad_norm": 0.07119269669055939,
      "learning_rate": 7e-06,
      "loss": 0.2101,
      "step": 767
    },
    {
      "epoch": 0.49849898580121704,
      "grad_norm": 0.16902369260787964,
      "learning_rate": 7e-06,
      "loss": 0.2095,
      "step": 768
    },
    {
      "epoch": 0.4991480730223124,
      "grad_norm": 0.06549739837646484,
      "learning_rate": 7e-06,
      "loss": 0.1946,
      "step": 769
    },
    {
      "epoch": 0.4997971602434077,
      "grad_norm": 0.11798711866140366,
      "learning_rate": 7e-06,
      "loss": 0.1942,
      "step": 770
    },
    {
      "epoch": 0.5004462474645031,
      "grad_norm": 0.06907515972852707,
      "learning_rate": 7e-06,
      "loss": 0.1915,
      "step": 771
    },
    {
      "epoch": 0.5010953346855984,
      "grad_norm": 0.09585484117269516,
      "learning_rate": 7e-06,
      "loss": 0.1974,
      "step": 772
    },
    {
      "epoch": 0.5017444219066937,
      "grad_norm": 0.07553306221961975,
      "learning_rate": 7e-06,
      "loss": 0.2116,
      "step": 773
    },
    {
      "epoch": 0.502393509127789,
      "grad_norm": 0.24496304988861084,
      "learning_rate": 7e-06,
      "loss": 0.2353,
      "step": 774
    },
    {
      "epoch": 0.5030425963488844,
      "grad_norm": 0.11755312979221344,
      "learning_rate": 7e-06,
      "loss": 0.1966,
      "step": 775
    },
    {
      "epoch": 0.5036916835699797,
      "grad_norm": 0.05773234739899635,
      "learning_rate": 7e-06,
      "loss": 0.1445,
      "step": 776
    },
    {
      "epoch": 0.5043407707910751,
      "grad_norm": 0.10324512422084808,
      "learning_rate": 7e-06,
      "loss": 0.2195,
      "step": 777
    },
    {
      "epoch": 0.5049898580121703,
      "grad_norm": 0.059167712926864624,
      "learning_rate": 7e-06,
      "loss": 0.2113,
      "step": 778
    },
    {
      "epoch": 0.5056389452332657,
      "grad_norm": 0.05929498374462128,
      "learning_rate": 7e-06,
      "loss": 0.1518,
      "step": 779
    },
    {
      "epoch": 0.506288032454361,
      "grad_norm": 0.11269595474004745,
      "learning_rate": 7e-06,
      "loss": 0.3327,
      "step": 780
    },
    {
      "epoch": 0.5069371196754564,
      "grad_norm": 0.057261865586042404,
      "learning_rate": 7e-06,
      "loss": 0.1494,
      "step": 781
    },
    {
      "epoch": 0.5075862068965518,
      "grad_norm": 0.07903514802455902,
      "learning_rate": 7e-06,
      "loss": 0.2656,
      "step": 782
    },
    {
      "epoch": 0.508235294117647,
      "grad_norm": 0.10096956044435501,
      "learning_rate": 7e-06,
      "loss": 0.2179,
      "step": 783
    },
    {
      "epoch": 0.5088843813387424,
      "grad_norm": 0.06734982132911682,
      "learning_rate": 7e-06,
      "loss": 0.1607,
      "step": 784
    },
    {
      "epoch": 0.5095334685598377,
      "grad_norm": 0.14338278770446777,
      "learning_rate": 7e-06,
      "loss": 0.1922,
      "step": 785
    },
    {
      "epoch": 0.5101825557809331,
      "grad_norm": 0.07605274021625519,
      "learning_rate": 7e-06,
      "loss": 0.2026,
      "step": 786
    },
    {
      "epoch": 0.5108316430020284,
      "grad_norm": 0.08174657076597214,
      "learning_rate": 7e-06,
      "loss": 0.348,
      "step": 787
    },
    {
      "epoch": 0.5114807302231237,
      "grad_norm": 0.12587834894657135,
      "learning_rate": 7e-06,
      "loss": 0.2303,
      "step": 788
    },
    {
      "epoch": 0.512129817444219,
      "grad_norm": 0.10480666905641556,
      "learning_rate": 7e-06,
      "loss": 0.2664,
      "step": 789
    },
    {
      "epoch": 0.5127789046653144,
      "grad_norm": 0.15568993985652924,
      "learning_rate": 7e-06,
      "loss": 0.1838,
      "step": 790
    },
    {
      "epoch": 0.5134279918864098,
      "grad_norm": 0.05867374688386917,
      "learning_rate": 7e-06,
      "loss": 0.3914,
      "step": 791
    },
    {
      "epoch": 0.5140770791075051,
      "grad_norm": 0.10745963454246521,
      "learning_rate": 7e-06,
      "loss": 0.2006,
      "step": 792
    },
    {
      "epoch": 0.5147261663286004,
      "grad_norm": 0.09333666414022446,
      "learning_rate": 7e-06,
      "loss": 0.1947,
      "step": 793
    },
    {
      "epoch": 0.5153752535496957,
      "grad_norm": 0.09703367203474045,
      "learning_rate": 7e-06,
      "loss": 0.2596,
      "step": 794
    },
    {
      "epoch": 0.5160243407707911,
      "grad_norm": 0.2527128756046295,
      "learning_rate": 7e-06,
      "loss": 0.2245,
      "step": 795
    },
    {
      "epoch": 0.5166734279918864,
      "grad_norm": 0.08284487575292587,
      "learning_rate": 7e-06,
      "loss": 0.1917,
      "step": 796
    },
    {
      "epoch": 0.5173225152129818,
      "grad_norm": 0.0650293231010437,
      "learning_rate": 7e-06,
      "loss": 0.1553,
      "step": 797
    },
    {
      "epoch": 0.517971602434077,
      "grad_norm": 0.27173325419425964,
      "learning_rate": 7e-06,
      "loss": 0.2362,
      "step": 798
    },
    {
      "epoch": 0.5186206896551724,
      "grad_norm": 0.0754721462726593,
      "learning_rate": 7e-06,
      "loss": 0.1634,
      "step": 799
    },
    {
      "epoch": 0.5192697768762677,
      "grad_norm": 0.07573726028203964,
      "learning_rate": 7e-06,
      "loss": 0.1608,
      "step": 800
    },
    {
      "epoch": 0.5192697768762677,
      "eval_correct_accuracy": 0.6675148430873622,
      "eval_error_accuracy": 0.434939216569113,
      "eval_f1": 0.5266947504209619,
      "eval_loss": 0.36480075120925903,
      "eval_runtime": 35.3535,
      "eval_samples_per_second": 96.171,
      "eval_steps_per_second": 6.025,
      "step": 800
    },
    {
      "epoch": 0.5199188640973631,
      "grad_norm": 0.10522062331438065,
      "learning_rate": 7e-06,
      "loss": 0.2195,
      "step": 801
    },
    {
      "epoch": 0.5205679513184585,
      "grad_norm": 0.07117393612861633,
      "learning_rate": 7e-06,
      "loss": 0.1837,
      "step": 802
    },
    {
      "epoch": 0.5212170385395537,
      "grad_norm": 0.1519741415977478,
      "learning_rate": 7e-06,
      "loss": 0.2169,
      "step": 803
    },
    {
      "epoch": 0.5218661257606491,
      "grad_norm": 0.10370130091905594,
      "learning_rate": 7e-06,
      "loss": 0.239,
      "step": 804
    },
    {
      "epoch": 0.5225152129817444,
      "grad_norm": 0.08987028151750565,
      "learning_rate": 7e-06,
      "loss": 0.2151,
      "step": 805
    },
    {
      "epoch": 0.5231643002028398,
      "grad_norm": 0.1218324825167656,
      "learning_rate": 7e-06,
      "loss": 0.2096,
      "step": 806
    },
    {
      "epoch": 0.5238133874239351,
      "grad_norm": 0.07435064017772675,
      "learning_rate": 7e-06,
      "loss": 0.1567,
      "step": 807
    },
    {
      "epoch": 0.5244624746450304,
      "grad_norm": 0.14976023137569427,
      "learning_rate": 7e-06,
      "loss": 0.2152,
      "step": 808
    },
    {
      "epoch": 0.5251115618661257,
      "grad_norm": 0.13672269880771637,
      "learning_rate": 7e-06,
      "loss": 0.2261,
      "step": 809
    },
    {
      "epoch": 0.5257606490872211,
      "grad_norm": 0.13780897855758667,
      "learning_rate": 7e-06,
      "loss": 0.1851,
      "step": 810
    },
    {
      "epoch": 0.5264097363083164,
      "grad_norm": 0.0974685400724411,
      "learning_rate": 7e-06,
      "loss": 0.1884,
      "step": 811
    },
    {
      "epoch": 0.5270588235294118,
      "grad_norm": 0.09794414043426514,
      "learning_rate": 7e-06,
      "loss": 0.2098,
      "step": 812
    },
    {
      "epoch": 0.527707910750507,
      "grad_norm": 0.07658419758081436,
      "learning_rate": 7e-06,
      "loss": 0.1839,
      "step": 813
    },
    {
      "epoch": 0.5283569979716024,
      "grad_norm": 0.13434024155139923,
      "learning_rate": 7e-06,
      "loss": 0.4131,
      "step": 814
    },
    {
      "epoch": 0.5290060851926978,
      "grad_norm": 0.09188194572925568,
      "learning_rate": 7e-06,
      "loss": 0.1697,
      "step": 815
    },
    {
      "epoch": 0.5296551724137931,
      "grad_norm": 0.08181243389844894,
      "learning_rate": 7e-06,
      "loss": 0.6132,
      "step": 816
    },
    {
      "epoch": 0.5303042596348885,
      "grad_norm": 0.09274433553218842,
      "learning_rate": 7e-06,
      "loss": 0.1729,
      "step": 817
    },
    {
      "epoch": 0.5309533468559837,
      "grad_norm": 0.06261304020881653,
      "learning_rate": 7e-06,
      "loss": 0.1682,
      "step": 818
    },
    {
      "epoch": 0.5316024340770791,
      "grad_norm": 0.07073164731264114,
      "learning_rate": 7e-06,
      "loss": 0.1537,
      "step": 819
    },
    {
      "epoch": 0.5322515212981744,
      "grad_norm": 0.10692471265792847,
      "learning_rate": 7e-06,
      "loss": 0.1937,
      "step": 820
    },
    {
      "epoch": 0.5329006085192698,
      "grad_norm": 0.08477950096130371,
      "learning_rate": 7e-06,
      "loss": 0.2078,
      "step": 821
    },
    {
      "epoch": 0.5335496957403651,
      "grad_norm": 0.08043153584003448,
      "learning_rate": 7e-06,
      "loss": 0.2572,
      "step": 822
    },
    {
      "epoch": 0.5341987829614604,
      "grad_norm": 0.21976418793201447,
      "learning_rate": 7e-06,
      "loss": 0.2665,
      "step": 823
    },
    {
      "epoch": 0.5348478701825558,
      "grad_norm": 0.12295768409967422,
      "learning_rate": 7e-06,
      "loss": 0.2344,
      "step": 824
    },
    {
      "epoch": 0.5354969574036511,
      "grad_norm": 0.09406176954507828,
      "learning_rate": 7e-06,
      "loss": 0.189,
      "step": 825
    },
    {
      "epoch": 0.5361460446247465,
      "grad_norm": 0.16274304687976837,
      "learning_rate": 7e-06,
      "loss": 0.1847,
      "step": 826
    },
    {
      "epoch": 0.5367951318458418,
      "grad_norm": 0.07163325697183609,
      "learning_rate": 7e-06,
      "loss": 0.1695,
      "step": 827
    },
    {
      "epoch": 0.5374442190669371,
      "grad_norm": 0.08059932291507721,
      "learning_rate": 7e-06,
      "loss": 0.303,
      "step": 828
    },
    {
      "epoch": 0.5380933062880324,
      "grad_norm": 0.08247779309749603,
      "learning_rate": 7e-06,
      "loss": 0.1797,
      "step": 829
    },
    {
      "epoch": 0.5387423935091278,
      "grad_norm": 0.09076128900051117,
      "learning_rate": 7e-06,
      "loss": 0.1818,
      "step": 830
    },
    {
      "epoch": 0.5393914807302231,
      "grad_norm": 0.06933623552322388,
      "learning_rate": 7e-06,
      "loss": 0.1769,
      "step": 831
    },
    {
      "epoch": 0.5400405679513185,
      "grad_norm": 0.28921735286712646,
      "learning_rate": 7e-06,
      "loss": 0.2011,
      "step": 832
    },
    {
      "epoch": 0.5406896551724137,
      "grad_norm": 0.08880368620157242,
      "learning_rate": 7e-06,
      "loss": 0.188,
      "step": 833
    },
    {
      "epoch": 0.5413387423935091,
      "grad_norm": 0.11891625076532364,
      "learning_rate": 7e-06,
      "loss": 0.286,
      "step": 834
    },
    {
      "epoch": 0.5419878296146045,
      "grad_norm": 0.11199948936700821,
      "learning_rate": 7e-06,
      "loss": 0.2055,
      "step": 835
    },
    {
      "epoch": 0.5426369168356998,
      "grad_norm": 0.09655672311782837,
      "learning_rate": 7e-06,
      "loss": 0.1572,
      "step": 836
    },
    {
      "epoch": 0.5432860040567952,
      "grad_norm": 0.10141126811504364,
      "learning_rate": 7e-06,
      "loss": 0.1736,
      "step": 837
    },
    {
      "epoch": 0.5439350912778904,
      "grad_norm": 0.18265491724014282,
      "learning_rate": 7e-06,
      "loss": 0.1577,
      "step": 838
    },
    {
      "epoch": 0.5445841784989858,
      "grad_norm": 0.10191596299409866,
      "learning_rate": 7e-06,
      "loss": 0.2068,
      "step": 839
    },
    {
      "epoch": 0.5452332657200811,
      "grad_norm": 0.13882945477962494,
      "learning_rate": 7e-06,
      "loss": 0.2377,
      "step": 840
    },
    {
      "epoch": 0.5458823529411765,
      "grad_norm": 0.14269676804542542,
      "learning_rate": 7e-06,
      "loss": 0.2011,
      "step": 841
    },
    {
      "epoch": 0.5465314401622718,
      "grad_norm": 0.0904797688126564,
      "learning_rate": 7e-06,
      "loss": 0.3503,
      "step": 842
    },
    {
      "epoch": 0.5471805273833671,
      "grad_norm": 0.09778595715761185,
      "learning_rate": 7e-06,
      "loss": 0.244,
      "step": 843
    },
    {
      "epoch": 0.5478296146044624,
      "grad_norm": 0.10927332192659378,
      "learning_rate": 7e-06,
      "loss": 0.1782,
      "step": 844
    },
    {
      "epoch": 0.5484787018255578,
      "grad_norm": 0.07220890372991562,
      "learning_rate": 7e-06,
      "loss": 0.1506,
      "step": 845
    },
    {
      "epoch": 0.5491277890466532,
      "grad_norm": 0.1226007416844368,
      "learning_rate": 7e-06,
      "loss": 0.2477,
      "step": 846
    },
    {
      "epoch": 0.5497768762677485,
      "grad_norm": 0.1008262112736702,
      "learning_rate": 7e-06,
      "loss": 0.1866,
      "step": 847
    },
    {
      "epoch": 0.5504259634888438,
      "grad_norm": 0.10449330508708954,
      "learning_rate": 7e-06,
      "loss": 0.1732,
      "step": 848
    },
    {
      "epoch": 0.5510750507099391,
      "grad_norm": 0.09610404819250107,
      "learning_rate": 7e-06,
      "loss": 0.172,
      "step": 849
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.10880760103464127,
      "learning_rate": 7e-06,
      "loss": 0.2702,
      "step": 850
    },
    {
      "epoch": 0.5523732251521298,
      "grad_norm": 0.08277928084135056,
      "learning_rate": 7e-06,
      "loss": 0.1956,
      "step": 851
    },
    {
      "epoch": 0.5530223123732252,
      "grad_norm": 0.07881638407707214,
      "learning_rate": 7e-06,
      "loss": 0.2154,
      "step": 852
    },
    {
      "epoch": 0.5536713995943204,
      "grad_norm": 0.10088840126991272,
      "learning_rate": 7e-06,
      "loss": 0.1917,
      "step": 853
    },
    {
      "epoch": 0.5543204868154158,
      "grad_norm": 0.1341434270143509,
      "learning_rate": 7e-06,
      "loss": 0.2636,
      "step": 854
    },
    {
      "epoch": 0.5549695740365111,
      "grad_norm": 0.121452696621418,
      "learning_rate": 7e-06,
      "loss": 0.1797,
      "step": 855
    },
    {
      "epoch": 0.5556186612576065,
      "grad_norm": 0.08463553339242935,
      "learning_rate": 7e-06,
      "loss": 0.1488,
      "step": 856
    },
    {
      "epoch": 0.5562677484787019,
      "grad_norm": 0.07704959064722061,
      "learning_rate": 7e-06,
      "loss": 0.2108,
      "step": 857
    },
    {
      "epoch": 0.5569168356997971,
      "grad_norm": 0.09983103722333908,
      "learning_rate": 7e-06,
      "loss": 0.3166,
      "step": 858
    },
    {
      "epoch": 0.5575659229208925,
      "grad_norm": 0.09335813671350479,
      "learning_rate": 7e-06,
      "loss": 0.195,
      "step": 859
    },
    {
      "epoch": 0.5582150101419878,
      "grad_norm": 0.10090874880552292,
      "learning_rate": 7e-06,
      "loss": 0.1922,
      "step": 860
    },
    {
      "epoch": 0.5588640973630832,
      "grad_norm": 0.10895328223705292,
      "learning_rate": 7e-06,
      "loss": 0.1527,
      "step": 861
    },
    {
      "epoch": 0.5595131845841785,
      "grad_norm": 0.11791693419218063,
      "learning_rate": 7e-06,
      "loss": 0.1923,
      "step": 862
    },
    {
      "epoch": 0.5601622718052738,
      "grad_norm": 0.08921172469854355,
      "learning_rate": 7e-06,
      "loss": 0.1712,
      "step": 863
    },
    {
      "epoch": 0.5608113590263691,
      "grad_norm": 0.08036008477210999,
      "learning_rate": 7e-06,
      "loss": 0.1653,
      "step": 864
    },
    {
      "epoch": 0.5614604462474645,
      "grad_norm": 0.10386878252029419,
      "learning_rate": 7e-06,
      "loss": 0.1994,
      "step": 865
    },
    {
      "epoch": 0.5621095334685599,
      "grad_norm": 0.12180779129266739,
      "learning_rate": 7e-06,
      "loss": 0.2255,
      "step": 866
    },
    {
      "epoch": 0.5627586206896552,
      "grad_norm": 0.22348037362098694,
      "learning_rate": 7e-06,
      "loss": 0.2313,
      "step": 867
    },
    {
      "epoch": 0.5634077079107505,
      "grad_norm": 0.1249099001288414,
      "learning_rate": 7e-06,
      "loss": 0.1875,
      "step": 868
    },
    {
      "epoch": 0.5640567951318458,
      "grad_norm": 0.06688498705625534,
      "learning_rate": 7e-06,
      "loss": 0.172,
      "step": 869
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.11851733922958374,
      "learning_rate": 7e-06,
      "loss": 0.2139,
      "step": 870
    },
    {
      "epoch": 0.5653549695740365,
      "grad_norm": 0.06620790809392929,
      "learning_rate": 7e-06,
      "loss": 0.2188,
      "step": 871
    },
    {
      "epoch": 0.5660040567951319,
      "grad_norm": 0.07596690207719803,
      "learning_rate": 7e-06,
      "loss": 0.1296,
      "step": 872
    },
    {
      "epoch": 0.5666531440162271,
      "grad_norm": 0.06655498594045639,
      "learning_rate": 7e-06,
      "loss": 0.1536,
      "step": 873
    },
    {
      "epoch": 0.5673022312373225,
      "grad_norm": 0.12941229343414307,
      "learning_rate": 7e-06,
      "loss": 0.1597,
      "step": 874
    },
    {
      "epoch": 0.5679513184584178,
      "grad_norm": 0.19898660480976105,
      "learning_rate": 7e-06,
      "loss": 0.2469,
      "step": 875
    },
    {
      "epoch": 0.5686004056795132,
      "grad_norm": 0.07568632066249847,
      "learning_rate": 7e-06,
      "loss": 0.1881,
      "step": 876
    },
    {
      "epoch": 0.5692494929006086,
      "grad_norm": 0.11257291585206985,
      "learning_rate": 7e-06,
      "loss": 0.212,
      "step": 877
    },
    {
      "epoch": 0.5698985801217038,
      "grad_norm": 0.0933486819267273,
      "learning_rate": 7e-06,
      "loss": 0.1991,
      "step": 878
    },
    {
      "epoch": 0.5705476673427992,
      "grad_norm": 0.09785312414169312,
      "learning_rate": 7e-06,
      "loss": 0.1798,
      "step": 879
    },
    {
      "epoch": 0.5711967545638945,
      "grad_norm": 0.1663210391998291,
      "learning_rate": 7e-06,
      "loss": 0.2502,
      "step": 880
    },
    {
      "epoch": 0.5718458417849899,
      "grad_norm": 0.07090163230895996,
      "learning_rate": 7e-06,
      "loss": 0.1776,
      "step": 881
    },
    {
      "epoch": 0.5724949290060852,
      "grad_norm": 0.10002019256353378,
      "learning_rate": 7e-06,
      "loss": 0.3947,
      "step": 882
    },
    {
      "epoch": 0.5731440162271805,
      "grad_norm": 0.12050540000200272,
      "learning_rate": 7e-06,
      "loss": 0.1713,
      "step": 883
    },
    {
      "epoch": 0.5737931034482758,
      "grad_norm": 0.06170005351305008,
      "learning_rate": 7e-06,
      "loss": 0.1838,
      "step": 884
    },
    {
      "epoch": 0.5744421906693712,
      "grad_norm": 0.1350065916776657,
      "learning_rate": 7e-06,
      "loss": 0.1835,
      "step": 885
    },
    {
      "epoch": 0.5750912778904665,
      "grad_norm": 0.10923561453819275,
      "learning_rate": 7e-06,
      "loss": 0.1705,
      "step": 886
    },
    {
      "epoch": 0.5757403651115619,
      "grad_norm": 0.06823324412107468,
      "learning_rate": 7e-06,
      "loss": 0.1746,
      "step": 887
    },
    {
      "epoch": 0.5763894523326571,
      "grad_norm": 0.10520250350236893,
      "learning_rate": 7e-06,
      "loss": 0.1999,
      "step": 888
    },
    {
      "epoch": 0.5770385395537525,
      "grad_norm": 0.05568196251988411,
      "learning_rate": 7e-06,
      "loss": 0.1953,
      "step": 889
    },
    {
      "epoch": 0.5776876267748479,
      "grad_norm": 0.07805492728948593,
      "learning_rate": 7e-06,
      "loss": 0.1845,
      "step": 890
    },
    {
      "epoch": 0.5783367139959432,
      "grad_norm": 0.09431909024715424,
      "learning_rate": 7e-06,
      "loss": 0.2483,
      "step": 891
    },
    {
      "epoch": 0.5789858012170386,
      "grad_norm": 0.12988470494747162,
      "learning_rate": 7e-06,
      "loss": 0.2209,
      "step": 892
    },
    {
      "epoch": 0.5796348884381338,
      "grad_norm": 0.09462703764438629,
      "learning_rate": 7e-06,
      "loss": 0.162,
      "step": 893
    },
    {
      "epoch": 0.5802839756592292,
      "grad_norm": 0.0691768154501915,
      "learning_rate": 7e-06,
      "loss": 0.2281,
      "step": 894
    },
    {
      "epoch": 0.5809330628803245,
      "grad_norm": 0.14616431295871735,
      "learning_rate": 7e-06,
      "loss": 0.1956,
      "step": 895
    },
    {
      "epoch": 0.5815821501014199,
      "grad_norm": 0.0813765823841095,
      "learning_rate": 7e-06,
      "loss": 0.4132,
      "step": 896
    },
    {
      "epoch": 0.5822312373225152,
      "grad_norm": 0.20757269859313965,
      "learning_rate": 7e-06,
      "loss": 0.1756,
      "step": 897
    },
    {
      "epoch": 0.5828803245436105,
      "grad_norm": 0.1379113793373108,
      "learning_rate": 7e-06,
      "loss": 0.2028,
      "step": 898
    },
    {
      "epoch": 0.5835294117647059,
      "grad_norm": 0.15152595937252045,
      "learning_rate": 7e-06,
      "loss": 0.2066,
      "step": 899
    },
    {
      "epoch": 0.5841784989858012,
      "grad_norm": 0.08288922905921936,
      "learning_rate": 7e-06,
      "loss": 0.276,
      "step": 900
    },
    {
      "epoch": 0.5841784989858012,
      "eval_correct_accuracy": 0.7031382527565734,
      "eval_error_accuracy": 0.46375506528590726,
      "eval_f1": 0.5588924390434676,
      "eval_loss": 0.34937503933906555,
      "eval_runtime": 35.1255,
      "eval_samples_per_second": 96.796,
      "eval_steps_per_second": 6.064,
      "step": 900
    },
    {
      "epoch": 0.5848275862068966,
      "grad_norm": 0.12164916843175888,
      "learning_rate": 7e-06,
      "loss": 0.1466,
      "step": 901
    },
    {
      "epoch": 0.5854766734279919,
      "grad_norm": 0.1579948216676712,
      "learning_rate": 7e-06,
      "loss": 0.2265,
      "step": 902
    },
    {
      "epoch": 0.5861257606490872,
      "grad_norm": 0.1418357640504837,
      "learning_rate": 7e-06,
      "loss": 0.1948,
      "step": 903
    },
    {
      "epoch": 0.5867748478701825,
      "grad_norm": 0.06885647773742676,
      "learning_rate": 7e-06,
      "loss": 0.1776,
      "step": 904
    },
    {
      "epoch": 0.5874239350912779,
      "grad_norm": 0.126393124461174,
      "learning_rate": 7e-06,
      "loss": 0.2047,
      "step": 905
    },
    {
      "epoch": 0.5880730223123732,
      "grad_norm": 0.10805638879537582,
      "learning_rate": 7e-06,
      "loss": 0.189,
      "step": 906
    },
    {
      "epoch": 0.5887221095334686,
      "grad_norm": 0.08207420259714127,
      "learning_rate": 7e-06,
      "loss": 0.1726,
      "step": 907
    },
    {
      "epoch": 0.5893711967545638,
      "grad_norm": 0.09940334409475327,
      "learning_rate": 7e-06,
      "loss": 0.1945,
      "step": 908
    },
    {
      "epoch": 0.5900202839756592,
      "grad_norm": 0.08650807291269302,
      "learning_rate": 7e-06,
      "loss": 0.204,
      "step": 909
    },
    {
      "epoch": 0.5906693711967546,
      "grad_norm": 0.08113309741020203,
      "learning_rate": 7e-06,
      "loss": 0.1991,
      "step": 910
    },
    {
      "epoch": 0.5913184584178499,
      "grad_norm": 0.06829234212636948,
      "learning_rate": 7e-06,
      "loss": 0.2157,
      "step": 911
    },
    {
      "epoch": 0.5919675456389453,
      "grad_norm": 0.11838626116514206,
      "learning_rate": 7e-06,
      "loss": 0.2027,
      "step": 912
    },
    {
      "epoch": 0.5926166328600405,
      "grad_norm": 0.08366552740335464,
      "learning_rate": 7e-06,
      "loss": 0.2907,
      "step": 913
    },
    {
      "epoch": 0.5932657200811359,
      "grad_norm": 0.10257062315940857,
      "learning_rate": 7e-06,
      "loss": 0.2377,
      "step": 914
    },
    {
      "epoch": 0.5939148073022312,
      "grad_norm": 0.12656860053539276,
      "learning_rate": 7e-06,
      "loss": 0.1739,
      "step": 915
    },
    {
      "epoch": 0.5945638945233266,
      "grad_norm": 0.07513012737035751,
      "learning_rate": 7e-06,
      "loss": 0.1951,
      "step": 916
    },
    {
      "epoch": 0.5952129817444219,
      "grad_norm": 0.11705049127340317,
      "learning_rate": 7e-06,
      "loss": 0.2008,
      "step": 917
    },
    {
      "epoch": 0.5958620689655172,
      "grad_norm": 0.08679664880037308,
      "learning_rate": 7e-06,
      "loss": 0.1783,
      "step": 918
    },
    {
      "epoch": 0.5965111561866125,
      "grad_norm": 0.10551495105028152,
      "learning_rate": 7e-06,
      "loss": 0.2494,
      "step": 919
    },
    {
      "epoch": 0.5971602434077079,
      "grad_norm": 0.10318238288164139,
      "learning_rate": 7e-06,
      "loss": 0.1727,
      "step": 920
    },
    {
      "epoch": 0.5978093306288033,
      "grad_norm": 0.10106849670410156,
      "learning_rate": 7e-06,
      "loss": 0.3352,
      "step": 921
    },
    {
      "epoch": 0.5984584178498986,
      "grad_norm": 0.09005557745695114,
      "learning_rate": 7e-06,
      "loss": 0.1937,
      "step": 922
    },
    {
      "epoch": 0.5991075050709939,
      "grad_norm": 0.07033547013998032,
      "learning_rate": 7e-06,
      "loss": 0.1743,
      "step": 923
    },
    {
      "epoch": 0.5997565922920892,
      "grad_norm": 0.17694073915481567,
      "learning_rate": 7e-06,
      "loss": 0.2029,
      "step": 924
    },
    {
      "epoch": 0.6004056795131846,
      "grad_norm": 0.15192002058029175,
      "learning_rate": 7e-06,
      "loss": 0.1882,
      "step": 925
    },
    {
      "epoch": 0.6010547667342799,
      "grad_norm": 0.05802560970187187,
      "learning_rate": 7e-06,
      "loss": 0.1166,
      "step": 926
    },
    {
      "epoch": 0.6017038539553753,
      "grad_norm": 0.23150600492954254,
      "learning_rate": 7e-06,
      "loss": 0.2364,
      "step": 927
    },
    {
      "epoch": 0.6023529411764705,
      "grad_norm": 0.09214530140161514,
      "learning_rate": 7e-06,
      "loss": 0.1728,
      "step": 928
    },
    {
      "epoch": 0.6030020283975659,
      "grad_norm": 0.13077262043952942,
      "learning_rate": 7e-06,
      "loss": 0.1711,
      "step": 929
    },
    {
      "epoch": 0.6036511156186612,
      "grad_norm": 0.0953122079372406,
      "learning_rate": 7e-06,
      "loss": 0.1866,
      "step": 930
    },
    {
      "epoch": 0.6043002028397566,
      "grad_norm": 0.09472522139549255,
      "learning_rate": 7e-06,
      "loss": 0.1721,
      "step": 931
    },
    {
      "epoch": 0.604949290060852,
      "grad_norm": 0.07716524600982666,
      "learning_rate": 7e-06,
      "loss": 0.1862,
      "step": 932
    },
    {
      "epoch": 0.6055983772819472,
      "grad_norm": 0.07794222980737686,
      "learning_rate": 7e-06,
      "loss": 0.1829,
      "step": 933
    },
    {
      "epoch": 0.6062474645030426,
      "grad_norm": 0.06637763977050781,
      "learning_rate": 7e-06,
      "loss": 0.1737,
      "step": 934
    },
    {
      "epoch": 0.6068965517241379,
      "grad_norm": 0.12036588788032532,
      "learning_rate": 7e-06,
      "loss": 0.4094,
      "step": 935
    },
    {
      "epoch": 0.6075456389452333,
      "grad_norm": 0.07958065718412399,
      "learning_rate": 7e-06,
      "loss": 0.1613,
      "step": 936
    },
    {
      "epoch": 0.6081947261663286,
      "grad_norm": 0.3065760135650635,
      "learning_rate": 7e-06,
      "loss": 0.1955,
      "step": 937
    },
    {
      "epoch": 0.6088438133874239,
      "grad_norm": 0.1012485921382904,
      "learning_rate": 7e-06,
      "loss": 0.2237,
      "step": 938
    },
    {
      "epoch": 0.6094929006085192,
      "grad_norm": 0.10295332223176956,
      "learning_rate": 7e-06,
      "loss": 0.2489,
      "step": 939
    },
    {
      "epoch": 0.6101419878296146,
      "grad_norm": 0.08720307052135468,
      "learning_rate": 7e-06,
      "loss": 0.1892,
      "step": 940
    },
    {
      "epoch": 0.61079107505071,
      "grad_norm": 0.14777624607086182,
      "learning_rate": 7e-06,
      "loss": 0.247,
      "step": 941
    },
    {
      "epoch": 0.6114401622718053,
      "grad_norm": 0.11211589723825455,
      "learning_rate": 7e-06,
      "loss": 0.2419,
      "step": 942
    },
    {
      "epoch": 0.6120892494929006,
      "grad_norm": 0.1007971242070198,
      "learning_rate": 7e-06,
      "loss": 0.1792,
      "step": 943
    },
    {
      "epoch": 0.6127383367139959,
      "grad_norm": 0.12282553315162659,
      "learning_rate": 7e-06,
      "loss": 0.1514,
      "step": 944
    },
    {
      "epoch": 0.6133874239350913,
      "grad_norm": 0.09605861455202103,
      "learning_rate": 7e-06,
      "loss": 0.1696,
      "step": 945
    },
    {
      "epoch": 0.6140365111561866,
      "grad_norm": 0.17086291313171387,
      "learning_rate": 7e-06,
      "loss": 0.1862,
      "step": 946
    },
    {
      "epoch": 0.614685598377282,
      "grad_norm": 0.23343786597251892,
      "learning_rate": 7e-06,
      "loss": 0.3228,
      "step": 947
    },
    {
      "epoch": 0.6153346855983772,
      "grad_norm": 0.0976041778922081,
      "learning_rate": 7e-06,
      "loss": 0.1856,
      "step": 948
    },
    {
      "epoch": 0.6159837728194726,
      "grad_norm": 0.09758379310369492,
      "learning_rate": 7e-06,
      "loss": 0.1843,
      "step": 949
    },
    {
      "epoch": 0.6166328600405679,
      "grad_norm": 0.11321861296892166,
      "learning_rate": 7e-06,
      "loss": 0.1844,
      "step": 950
    },
    {
      "epoch": 0.6172819472616633,
      "grad_norm": 0.17063231766223907,
      "learning_rate": 7e-06,
      "loss": 0.2247,
      "step": 951
    },
    {
      "epoch": 0.6179310344827587,
      "grad_norm": 0.1008564829826355,
      "learning_rate": 7e-06,
      "loss": 0.1815,
      "step": 952
    },
    {
      "epoch": 0.6185801217038539,
      "grad_norm": 0.07569026947021484,
      "learning_rate": 7e-06,
      "loss": 0.2496,
      "step": 953
    },
    {
      "epoch": 0.6192292089249493,
      "grad_norm": 0.09327735751867294,
      "learning_rate": 7e-06,
      "loss": 0.1959,
      "step": 954
    },
    {
      "epoch": 0.6198782961460446,
      "grad_norm": 0.1275831162929535,
      "learning_rate": 7e-06,
      "loss": 0.1868,
      "step": 955
    },
    {
      "epoch": 0.62052738336714,
      "grad_norm": 0.09583191573619843,
      "learning_rate": 7e-06,
      "loss": 0.2719,
      "step": 956
    },
    {
      "epoch": 0.6211764705882353,
      "grad_norm": 0.12904395163059235,
      "learning_rate": 7e-06,
      "loss": 0.1975,
      "step": 957
    },
    {
      "epoch": 0.6218255578093306,
      "grad_norm": 0.13089901208877563,
      "learning_rate": 7e-06,
      "loss": 0.251,
      "step": 958
    },
    {
      "epoch": 0.6224746450304259,
      "grad_norm": 0.11827493458986282,
      "learning_rate": 7e-06,
      "loss": 0.1958,
      "step": 959
    },
    {
      "epoch": 0.6231237322515213,
      "grad_norm": 0.07360196113586426,
      "learning_rate": 7e-06,
      "loss": 0.1723,
      "step": 960
    },
    {
      "epoch": 0.6237728194726166,
      "grad_norm": 0.1590428501367569,
      "learning_rate": 7e-06,
      "loss": 0.2054,
      "step": 961
    },
    {
      "epoch": 0.624421906693712,
      "grad_norm": 0.22759099304676056,
      "learning_rate": 7e-06,
      "loss": 0.2134,
      "step": 962
    },
    {
      "epoch": 0.6250709939148072,
      "grad_norm": 0.12990064918994904,
      "learning_rate": 7e-06,
      "loss": 0.2314,
      "step": 963
    },
    {
      "epoch": 0.6257200811359026,
      "grad_norm": 0.057168297469615936,
      "learning_rate": 7e-06,
      "loss": 0.1682,
      "step": 964
    },
    {
      "epoch": 0.626369168356998,
      "grad_norm": 0.1622982621192932,
      "learning_rate": 7e-06,
      "loss": 0.2067,
      "step": 965
    },
    {
      "epoch": 0.6270182555780933,
      "grad_norm": 0.11161521077156067,
      "learning_rate": 7e-06,
      "loss": 0.1883,
      "step": 966
    },
    {
      "epoch": 0.6276673427991887,
      "grad_norm": 0.14041657745838165,
      "learning_rate": 7e-06,
      "loss": 0.1854,
      "step": 967
    },
    {
      "epoch": 0.6283164300202839,
      "grad_norm": 0.06677643954753876,
      "learning_rate": 7e-06,
      "loss": 0.205,
      "step": 968
    },
    {
      "epoch": 0.6289655172413793,
      "grad_norm": 0.09602215141057968,
      "learning_rate": 7e-06,
      "loss": 0.2083,
      "step": 969
    },
    {
      "epoch": 0.6296146044624746,
      "grad_norm": 0.1066310778260231,
      "learning_rate": 7e-06,
      "loss": 0.2137,
      "step": 970
    },
    {
      "epoch": 0.63026369168357,
      "grad_norm": 0.10030601173639297,
      "learning_rate": 7e-06,
      "loss": 0.1905,
      "step": 971
    },
    {
      "epoch": 0.6309127789046654,
      "grad_norm": 0.18839634954929352,
      "learning_rate": 7e-06,
      "loss": 0.246,
      "step": 972
    },
    {
      "epoch": 0.6315618661257606,
      "grad_norm": 0.07028167694807053,
      "learning_rate": 7e-06,
      "loss": 0.163,
      "step": 973
    },
    {
      "epoch": 0.632210953346856,
      "grad_norm": 0.08034958690404892,
      "learning_rate": 7e-06,
      "loss": 0.229,
      "step": 974
    },
    {
      "epoch": 0.6328600405679513,
      "grad_norm": 0.19028812646865845,
      "learning_rate": 7e-06,
      "loss": 0.2203,
      "step": 975
    },
    {
      "epoch": 0.6335091277890467,
      "grad_norm": 0.09904851019382477,
      "learning_rate": 7e-06,
      "loss": 0.1731,
      "step": 976
    },
    {
      "epoch": 0.634158215010142,
      "grad_norm": 0.08040215075016022,
      "learning_rate": 7e-06,
      "loss": 0.1838,
      "step": 977
    },
    {
      "epoch": 0.6348073022312373,
      "grad_norm": 0.059158820658922195,
      "learning_rate": 7e-06,
      "loss": 0.3396,
      "step": 978
    },
    {
      "epoch": 0.6354563894523326,
      "grad_norm": 0.07221192121505737,
      "learning_rate": 7e-06,
      "loss": 0.2257,
      "step": 979
    },
    {
      "epoch": 0.636105476673428,
      "grad_norm": 0.0820135548710823,
      "learning_rate": 7e-06,
      "loss": 0.1411,
      "step": 980
    },
    {
      "epoch": 0.6367545638945233,
      "grad_norm": 0.10191687941551208,
      "learning_rate": 7e-06,
      "loss": 0.2039,
      "step": 981
    },
    {
      "epoch": 0.6374036511156187,
      "grad_norm": 0.11939878016710281,
      "learning_rate": 7e-06,
      "loss": 0.1907,
      "step": 982
    },
    {
      "epoch": 0.6380527383367139,
      "grad_norm": 0.12139187008142471,
      "learning_rate": 7e-06,
      "loss": 0.2247,
      "step": 983
    },
    {
      "epoch": 0.6387018255578093,
      "grad_norm": 0.14076274633407593,
      "learning_rate": 7e-06,
      "loss": 0.2011,
      "step": 984
    },
    {
      "epoch": 0.6393509127789047,
      "grad_norm": 0.08710716664791107,
      "learning_rate": 7e-06,
      "loss": 0.1852,
      "step": 985
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.06157274544239044,
      "learning_rate": 7e-06,
      "loss": 0.2028,
      "step": 986
    },
    {
      "epoch": 0.6406490872210954,
      "grad_norm": 0.11011948436498642,
      "learning_rate": 7e-06,
      "loss": 0.1738,
      "step": 987
    },
    {
      "epoch": 0.6412981744421906,
      "grad_norm": 0.11240904778242111,
      "learning_rate": 7e-06,
      "loss": 0.1552,
      "step": 988
    },
    {
      "epoch": 0.641947261663286,
      "grad_norm": 0.09566875547170639,
      "learning_rate": 7e-06,
      "loss": 0.1806,
      "step": 989
    },
    {
      "epoch": 0.6425963488843813,
      "grad_norm": 0.11950669437646866,
      "learning_rate": 7e-06,
      "loss": 0.1985,
      "step": 990
    },
    {
      "epoch": 0.6432454361054767,
      "grad_norm": 0.16448372602462769,
      "learning_rate": 7e-06,
      "loss": 0.2445,
      "step": 991
    },
    {
      "epoch": 0.643894523326572,
      "grad_norm": 0.13419507443904877,
      "learning_rate": 7e-06,
      "loss": 0.1541,
      "step": 992
    },
    {
      "epoch": 0.6445436105476673,
      "grad_norm": 0.07890139520168304,
      "learning_rate": 7e-06,
      "loss": 0.164,
      "step": 993
    },
    {
      "epoch": 0.6451926977687626,
      "grad_norm": 0.10416340827941895,
      "learning_rate": 7e-06,
      "loss": 0.2024,
      "step": 994
    },
    {
      "epoch": 0.645841784989858,
      "grad_norm": 0.09413444250822067,
      "learning_rate": 7e-06,
      "loss": 0.2249,
      "step": 995
    },
    {
      "epoch": 0.6464908722109534,
      "grad_norm": 0.11828941106796265,
      "learning_rate": 7e-06,
      "loss": 0.2126,
      "step": 996
    },
    {
      "epoch": 0.6471399594320487,
      "grad_norm": 0.07844394445419312,
      "learning_rate": 7e-06,
      "loss": 0.1766,
      "step": 997
    },
    {
      "epoch": 0.647789046653144,
      "grad_norm": 0.11781085282564163,
      "learning_rate": 7e-06,
      "loss": 0.1716,
      "step": 998
    },
    {
      "epoch": 0.6484381338742393,
      "grad_norm": 0.07474034279584885,
      "learning_rate": 7e-06,
      "loss": 0.167,
      "step": 999
    },
    {
      "epoch": 0.6490872210953347,
      "grad_norm": 0.09747886657714844,
      "learning_rate": 7e-06,
      "loss": 0.24,
      "step": 1000
    },
    {
      "epoch": 0.6490872210953347,
      "eval_correct_accuracy": 0.7022900763358778,
      "eval_error_accuracy": 0.4633048176497073,
      "eval_f1": 0.5582975310425765,
      "eval_loss": 0.34859511256217957,
      "eval_runtime": 35.1334,
      "eval_samples_per_second": 96.774,
      "eval_steps_per_second": 6.063,
      "step": 1000
    },
    {
      "epoch": 0.64973630831643,
      "grad_norm": 0.0995529443025589,
      "learning_rate": 7e-06,
      "loss": 0.1971,
      "step": 1001
    },
    {
      "epoch": 0.6503853955375254,
      "grad_norm": 0.084745392203331,
      "learning_rate": 7e-06,
      "loss": 0.2019,
      "step": 1002
    },
    {
      "epoch": 0.6510344827586206,
      "grad_norm": 0.0827263742685318,
      "learning_rate": 7e-06,
      "loss": 0.2074,
      "step": 1003
    },
    {
      "epoch": 0.651683569979716,
      "grad_norm": 0.10486066341400146,
      "learning_rate": 7e-06,
      "loss": 0.197,
      "step": 1004
    },
    {
      "epoch": 0.6523326572008113,
      "grad_norm": 0.09605512022972107,
      "learning_rate": 7e-06,
      "loss": 0.2247,
      "step": 1005
    },
    {
      "epoch": 0.6529817444219067,
      "grad_norm": 0.0738934874534607,
      "learning_rate": 7e-06,
      "loss": 0.175,
      "step": 1006
    },
    {
      "epoch": 0.6536308316430021,
      "grad_norm": 0.1085992231965065,
      "learning_rate": 7e-06,
      "loss": 0.1987,
      "step": 1007
    },
    {
      "epoch": 0.6542799188640973,
      "grad_norm": 0.08018339425325394,
      "learning_rate": 7e-06,
      "loss": 0.1861,
      "step": 1008
    },
    {
      "epoch": 0.6549290060851927,
      "grad_norm": 0.0749412402510643,
      "learning_rate": 7e-06,
      "loss": 0.1967,
      "step": 1009
    },
    {
      "epoch": 0.655578093306288,
      "grad_norm": 0.10364574193954468,
      "learning_rate": 7e-06,
      "loss": 0.2311,
      "step": 1010
    },
    {
      "epoch": 0.6562271805273834,
      "grad_norm": 0.1128847748041153,
      "learning_rate": 7e-06,
      "loss": 0.2341,
      "step": 1011
    },
    {
      "epoch": 0.6568762677484787,
      "grad_norm": 0.12019483000040054,
      "learning_rate": 7e-06,
      "loss": 0.2029,
      "step": 1012
    },
    {
      "epoch": 0.657525354969574,
      "grad_norm": 0.09208370745182037,
      "learning_rate": 7e-06,
      "loss": 0.1936,
      "step": 1013
    },
    {
      "epoch": 0.6581744421906693,
      "grad_norm": 0.09209991246461868,
      "learning_rate": 7e-06,
      "loss": 0.1765,
      "step": 1014
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.0682254359126091,
      "learning_rate": 7e-06,
      "loss": 0.1737,
      "step": 1015
    },
    {
      "epoch": 0.65947261663286,
      "grad_norm": 0.09653693437576294,
      "learning_rate": 7e-06,
      "loss": 0.2632,
      "step": 1016
    },
    {
      "epoch": 0.6601217038539554,
      "grad_norm": 0.07582012563943863,
      "learning_rate": 7e-06,
      "loss": 0.1901,
      "step": 1017
    },
    {
      "epoch": 0.6607707910750507,
      "grad_norm": 0.0795321837067604,
      "learning_rate": 7e-06,
      "loss": 0.2034,
      "step": 1018
    },
    {
      "epoch": 0.661419878296146,
      "grad_norm": 0.05964280292391777,
      "learning_rate": 7e-06,
      "loss": 0.1602,
      "step": 1019
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 0.084807388484478,
      "learning_rate": 7e-06,
      "loss": 0.18,
      "step": 1020
    },
    {
      "epoch": 0.6627180527383367,
      "grad_norm": 0.10723788291215897,
      "learning_rate": 7e-06,
      "loss": 0.2199,
      "step": 1021
    },
    {
      "epoch": 0.6633671399594321,
      "grad_norm": 0.06725160777568817,
      "learning_rate": 7e-06,
      "loss": 0.3656,
      "step": 1022
    },
    {
      "epoch": 0.6640162271805273,
      "grad_norm": 0.05436889827251434,
      "learning_rate": 7e-06,
      "loss": 0.1556,
      "step": 1023
    },
    {
      "epoch": 0.6646653144016227,
      "grad_norm": 0.12255845218896866,
      "learning_rate": 7e-06,
      "loss": 0.2771,
      "step": 1024
    },
    {
      "epoch": 0.665314401622718,
      "grad_norm": 0.07063890993595123,
      "learning_rate": 7e-06,
      "loss": 0.1834,
      "step": 1025
    },
    {
      "epoch": 0.6659634888438134,
      "grad_norm": 0.14149287343025208,
      "learning_rate": 7e-06,
      "loss": 0.2314,
      "step": 1026
    },
    {
      "epoch": 0.6666125760649088,
      "grad_norm": 0.1446903496980667,
      "learning_rate": 7e-06,
      "loss": 0.1719,
      "step": 1027
    },
    {
      "epoch": 0.667261663286004,
      "grad_norm": 0.12040527164936066,
      "learning_rate": 7e-06,
      "loss": 0.2365,
      "step": 1028
    },
    {
      "epoch": 0.6679107505070994,
      "grad_norm": 0.09445763379335403,
      "learning_rate": 7e-06,
      "loss": 0.1664,
      "step": 1029
    },
    {
      "epoch": 0.6685598377281947,
      "grad_norm": 0.211579367518425,
      "learning_rate": 7e-06,
      "loss": 0.1693,
      "step": 1030
    },
    {
      "epoch": 0.6692089249492901,
      "grad_norm": 0.14362666010856628,
      "learning_rate": 7e-06,
      "loss": 0.1985,
      "step": 1031
    },
    {
      "epoch": 0.6698580121703854,
      "grad_norm": 0.17482641339302063,
      "learning_rate": 7e-06,
      "loss": 0.3187,
      "step": 1032
    },
    {
      "epoch": 0.6705070993914807,
      "grad_norm": 0.08631302416324615,
      "learning_rate": 7e-06,
      "loss": 0.1917,
      "step": 1033
    },
    {
      "epoch": 0.671156186612576,
      "grad_norm": 0.09578407555818558,
      "learning_rate": 7e-06,
      "loss": 0.1825,
      "step": 1034
    },
    {
      "epoch": 0.6718052738336714,
      "grad_norm": 0.12212447822093964,
      "learning_rate": 7e-06,
      "loss": 0.2691,
      "step": 1035
    },
    {
      "epoch": 0.6724543610547667,
      "grad_norm": 0.07138083130121231,
      "learning_rate": 7e-06,
      "loss": 0.2207,
      "step": 1036
    },
    {
      "epoch": 0.6731034482758621,
      "grad_norm": 0.07442692667245865,
      "learning_rate": 7e-06,
      "loss": 0.246,
      "step": 1037
    },
    {
      "epoch": 0.6737525354969573,
      "grad_norm": 0.08352356404066086,
      "learning_rate": 7e-06,
      "loss": 0.2057,
      "step": 1038
    },
    {
      "epoch": 0.6744016227180527,
      "grad_norm": 0.135184183716774,
      "learning_rate": 7e-06,
      "loss": 0.2128,
      "step": 1039
    },
    {
      "epoch": 0.6750507099391481,
      "grad_norm": 0.1089334562420845,
      "learning_rate": 7e-06,
      "loss": 0.2013,
      "step": 1040
    },
    {
      "epoch": 0.6756997971602434,
      "grad_norm": 0.09024367481470108,
      "learning_rate": 7e-06,
      "loss": 0.1648,
      "step": 1041
    },
    {
      "epoch": 0.6763488843813388,
      "grad_norm": 0.08614169806241989,
      "learning_rate": 7e-06,
      "loss": 0.1764,
      "step": 1042
    },
    {
      "epoch": 0.676997971602434,
      "grad_norm": 0.05566355958580971,
      "learning_rate": 7e-06,
      "loss": 0.1554,
      "step": 1043
    },
    {
      "epoch": 0.6776470588235294,
      "grad_norm": 0.11599830538034439,
      "learning_rate": 7e-06,
      "loss": 0.1626,
      "step": 1044
    },
    {
      "epoch": 0.6782961460446247,
      "grad_norm": 0.07930659502744675,
      "learning_rate": 7e-06,
      "loss": 0.2324,
      "step": 1045
    },
    {
      "epoch": 0.6789452332657201,
      "grad_norm": 0.5605584383010864,
      "learning_rate": 7e-06,
      "loss": 0.2375,
      "step": 1046
    },
    {
      "epoch": 0.6795943204868155,
      "grad_norm": 0.16289754211902618,
      "learning_rate": 7e-06,
      "loss": 0.1982,
      "step": 1047
    },
    {
      "epoch": 0.6802434077079107,
      "grad_norm": 0.050798263400793076,
      "learning_rate": 7e-06,
      "loss": 0.1828,
      "step": 1048
    },
    {
      "epoch": 0.680892494929006,
      "grad_norm": 0.05825048312544823,
      "learning_rate": 7e-06,
      "loss": 0.1559,
      "step": 1049
    },
    {
      "epoch": 0.6815415821501014,
      "grad_norm": 0.1763436645269394,
      "learning_rate": 7e-06,
      "loss": 0.1752,
      "step": 1050
    },
    {
      "epoch": 0.6821906693711968,
      "grad_norm": 0.0904054120182991,
      "learning_rate": 7e-06,
      "loss": 0.1725,
      "step": 1051
    },
    {
      "epoch": 0.6828397565922921,
      "grad_norm": 0.23404686152935028,
      "learning_rate": 7e-06,
      "loss": 0.249,
      "step": 1052
    },
    {
      "epoch": 0.6834888438133874,
      "grad_norm": 0.09554760903120041,
      "learning_rate": 7e-06,
      "loss": 0.1708,
      "step": 1053
    },
    {
      "epoch": 0.6841379310344827,
      "grad_norm": 0.11450043320655823,
      "learning_rate": 7e-06,
      "loss": 0.2008,
      "step": 1054
    },
    {
      "epoch": 0.6847870182555781,
      "grad_norm": 0.12297996133565903,
      "learning_rate": 7e-06,
      "loss": 0.2162,
      "step": 1055
    },
    {
      "epoch": 0.6854361054766734,
      "grad_norm": 0.0744604766368866,
      "learning_rate": 7e-06,
      "loss": 0.1702,
      "step": 1056
    },
    {
      "epoch": 0.6860851926977688,
      "grad_norm": 0.09900418668985367,
      "learning_rate": 7e-06,
      "loss": 0.1672,
      "step": 1057
    },
    {
      "epoch": 0.686734279918864,
      "grad_norm": 0.10929972678422928,
      "learning_rate": 7e-06,
      "loss": 0.1795,
      "step": 1058
    },
    {
      "epoch": 0.6873833671399594,
      "grad_norm": 0.07683955132961273,
      "learning_rate": 7e-06,
      "loss": 0.1853,
      "step": 1059
    },
    {
      "epoch": 0.6880324543610548,
      "grad_norm": 0.04411131516098976,
      "learning_rate": 7e-06,
      "loss": 0.1432,
      "step": 1060
    },
    {
      "epoch": 0.6886815415821501,
      "grad_norm": 0.21223114430904388,
      "learning_rate": 7e-06,
      "loss": 0.1485,
      "step": 1061
    },
    {
      "epoch": 0.6893306288032455,
      "grad_norm": 0.13150209188461304,
      "learning_rate": 7e-06,
      "loss": 0.2048,
      "step": 1062
    },
    {
      "epoch": 0.6899797160243407,
      "grad_norm": 0.07157939672470093,
      "learning_rate": 7e-06,
      "loss": 0.1425,
      "step": 1063
    },
    {
      "epoch": 0.6906288032454361,
      "grad_norm": 0.20185907185077667,
      "learning_rate": 7e-06,
      "loss": 0.1869,
      "step": 1064
    },
    {
      "epoch": 0.6912778904665314,
      "grad_norm": 0.06292005628347397,
      "learning_rate": 7e-06,
      "loss": 0.174,
      "step": 1065
    },
    {
      "epoch": 0.6919269776876268,
      "grad_norm": 0.1187954768538475,
      "learning_rate": 7e-06,
      "loss": 0.1709,
      "step": 1066
    },
    {
      "epoch": 0.6925760649087221,
      "grad_norm": 0.1465369164943695,
      "learning_rate": 7e-06,
      "loss": 0.2138,
      "step": 1067
    },
    {
      "epoch": 0.6932251521298174,
      "grad_norm": 0.0650010034441948,
      "learning_rate": 7e-06,
      "loss": 0.2124,
      "step": 1068
    },
    {
      "epoch": 0.6938742393509127,
      "grad_norm": 0.08510168641805649,
      "learning_rate": 7e-06,
      "loss": 0.216,
      "step": 1069
    },
    {
      "epoch": 0.6945233265720081,
      "grad_norm": 0.06033770367503166,
      "learning_rate": 7e-06,
      "loss": 0.1879,
      "step": 1070
    },
    {
      "epoch": 0.6951724137931035,
      "grad_norm": 0.11465757340192795,
      "learning_rate": 7e-06,
      "loss": 0.1687,
      "step": 1071
    },
    {
      "epoch": 0.6958215010141988,
      "grad_norm": 0.14267218112945557,
      "learning_rate": 7e-06,
      "loss": 0.2211,
      "step": 1072
    },
    {
      "epoch": 0.6964705882352941,
      "grad_norm": 0.10564327985048294,
      "learning_rate": 7e-06,
      "loss": 0.1836,
      "step": 1073
    },
    {
      "epoch": 0.6971196754563894,
      "grad_norm": 0.12352459877729416,
      "learning_rate": 7e-06,
      "loss": 0.2285,
      "step": 1074
    },
    {
      "epoch": 0.6977687626774848,
      "grad_norm": 0.11494971811771393,
      "learning_rate": 7e-06,
      "loss": 0.1746,
      "step": 1075
    },
    {
      "epoch": 0.6984178498985801,
      "grad_norm": 0.09619060158729553,
      "learning_rate": 7e-06,
      "loss": 0.2211,
      "step": 1076
    },
    {
      "epoch": 0.6990669371196755,
      "grad_norm": 0.05975370109081268,
      "learning_rate": 7e-06,
      "loss": 0.158,
      "step": 1077
    },
    {
      "epoch": 0.6997160243407707,
      "grad_norm": 0.0893678367137909,
      "learning_rate": 7e-06,
      "loss": 0.1815,
      "step": 1078
    },
    {
      "epoch": 0.7003651115618661,
      "grad_norm": 0.10617779940366745,
      "learning_rate": 7e-06,
      "loss": 0.1654,
      "step": 1079
    },
    {
      "epoch": 0.7010141987829615,
      "grad_norm": 0.19732528924942017,
      "learning_rate": 7e-06,
      "loss": 0.2118,
      "step": 1080
    },
    {
      "epoch": 0.7016632860040568,
      "grad_norm": 0.06683685630559921,
      "learning_rate": 7e-06,
      "loss": 0.1542,
      "step": 1081
    },
    {
      "epoch": 0.7023123732251522,
      "grad_norm": 0.13068722188472748,
      "learning_rate": 7e-06,
      "loss": 0.2363,
      "step": 1082
    },
    {
      "epoch": 0.7029614604462474,
      "grad_norm": 0.07190722227096558,
      "learning_rate": 7e-06,
      "loss": 0.2104,
      "step": 1083
    },
    {
      "epoch": 0.7036105476673428,
      "grad_norm": 0.10199645161628723,
      "learning_rate": 7e-06,
      "loss": 0.1865,
      "step": 1084
    },
    {
      "epoch": 0.7042596348884381,
      "grad_norm": 0.0833023265004158,
      "learning_rate": 7e-06,
      "loss": 0.188,
      "step": 1085
    },
    {
      "epoch": 0.7049087221095335,
      "grad_norm": 0.07952020317316055,
      "learning_rate": 7e-06,
      "loss": 0.1618,
      "step": 1086
    },
    {
      "epoch": 0.7055578093306288,
      "grad_norm": 0.1277373731136322,
      "learning_rate": 7e-06,
      "loss": 0.2079,
      "step": 1087
    },
    {
      "epoch": 0.7062068965517241,
      "grad_norm": 0.05671333894133568,
      "learning_rate": 7e-06,
      "loss": 0.1441,
      "step": 1088
    },
    {
      "epoch": 0.7068559837728194,
      "grad_norm": 0.06998471170663834,
      "learning_rate": 7e-06,
      "loss": 0.1788,
      "step": 1089
    },
    {
      "epoch": 0.7075050709939148,
      "grad_norm": 0.149811789393425,
      "learning_rate": 7e-06,
      "loss": 0.2223,
      "step": 1090
    },
    {
      "epoch": 0.7081541582150102,
      "grad_norm": 0.10646600276231766,
      "learning_rate": 7e-06,
      "loss": 0.2256,
      "step": 1091
    },
    {
      "epoch": 0.7088032454361055,
      "grad_norm": 0.14048679172992706,
      "learning_rate": 7e-06,
      "loss": 0.1698,
      "step": 1092
    },
    {
      "epoch": 0.7094523326572008,
      "grad_norm": 0.1020553782582283,
      "learning_rate": 7e-06,
      "loss": 0.1736,
      "step": 1093
    },
    {
      "epoch": 0.7101014198782961,
      "grad_norm": 0.14808548986911774,
      "learning_rate": 7e-06,
      "loss": 0.2444,
      "step": 1094
    },
    {
      "epoch": 0.7107505070993915,
      "grad_norm": 0.062537781894207,
      "learning_rate": 7e-06,
      "loss": 0.1639,
      "step": 1095
    },
    {
      "epoch": 0.7113995943204868,
      "grad_norm": 0.10720967501401901,
      "learning_rate": 7e-06,
      "loss": 0.1697,
      "step": 1096
    },
    {
      "epoch": 0.7120486815415822,
      "grad_norm": 0.06508620083332062,
      "learning_rate": 7e-06,
      "loss": 0.1555,
      "step": 1097
    },
    {
      "epoch": 0.7126977687626774,
      "grad_norm": 0.08912002295255661,
      "learning_rate": 7e-06,
      "loss": 0.1408,
      "step": 1098
    },
    {
      "epoch": 0.7133468559837728,
      "grad_norm": 0.10879094898700714,
      "learning_rate": 7e-06,
      "loss": 0.2856,
      "step": 1099
    },
    {
      "epoch": 0.7139959432048681,
      "grad_norm": 0.07285185158252716,
      "learning_rate": 7e-06,
      "loss": 0.1713,
      "step": 1100
    },
    {
      "epoch": 0.7139959432048681,
      "eval_correct_accuracy": 0.6641221374045801,
      "eval_error_accuracy": 0.48086447546150385,
      "eval_f1": 0.5578279076050251,
      "eval_loss": 0.3616761267185211,
      "eval_runtime": 35.1875,
      "eval_samples_per_second": 96.625,
      "eval_steps_per_second": 6.053,
      "step": 1100
    },
    {
      "epoch": 0.7146450304259635,
      "grad_norm": 0.10783776640892029,
      "learning_rate": 7e-06,
      "loss": 0.2181,
      "step": 1101
    },
    {
      "epoch": 0.7152941176470589,
      "grad_norm": 0.06631865352392197,
      "learning_rate": 7e-06,
      "loss": 0.2098,
      "step": 1102
    },
    {
      "epoch": 0.7159432048681541,
      "grad_norm": 0.06837718933820724,
      "learning_rate": 7e-06,
      "loss": 0.2058,
      "step": 1103
    },
    {
      "epoch": 0.7165922920892495,
      "grad_norm": 0.05973653495311737,
      "learning_rate": 7e-06,
      "loss": 0.2558,
      "step": 1104
    },
    {
      "epoch": 0.7172413793103448,
      "grad_norm": 0.08559276163578033,
      "learning_rate": 7e-06,
      "loss": 0.1988,
      "step": 1105
    },
    {
      "epoch": 0.7178904665314402,
      "grad_norm": 0.08136655390262604,
      "learning_rate": 7e-06,
      "loss": 0.1869,
      "step": 1106
    },
    {
      "epoch": 0.7185395537525355,
      "grad_norm": 0.13900773227214813,
      "learning_rate": 7e-06,
      "loss": 0.1528,
      "step": 1107
    },
    {
      "epoch": 0.7191886409736308,
      "grad_norm": 0.21524566411972046,
      "learning_rate": 7e-06,
      "loss": 0.1765,
      "step": 1108
    },
    {
      "epoch": 0.7198377281947261,
      "grad_norm": 0.09298169612884521,
      "learning_rate": 7e-06,
      "loss": 0.2075,
      "step": 1109
    },
    {
      "epoch": 0.7204868154158215,
      "grad_norm": 0.10785913467407227,
      "learning_rate": 7e-06,
      "loss": 0.1919,
      "step": 1110
    },
    {
      "epoch": 0.7211359026369168,
      "grad_norm": 0.10385829955339432,
      "learning_rate": 7e-06,
      "loss": 0.189,
      "step": 1111
    },
    {
      "epoch": 0.7217849898580122,
      "grad_norm": 0.09931280463933945,
      "learning_rate": 7e-06,
      "loss": 0.2106,
      "step": 1112
    },
    {
      "epoch": 0.7224340770791075,
      "grad_norm": 0.10478830337524414,
      "learning_rate": 7e-06,
      "loss": 0.208,
      "step": 1113
    },
    {
      "epoch": 0.7230831643002028,
      "grad_norm": 0.07331147789955139,
      "learning_rate": 7e-06,
      "loss": 0.1422,
      "step": 1114
    },
    {
      "epoch": 0.7237322515212982,
      "grad_norm": 0.066261887550354,
      "learning_rate": 7e-06,
      "loss": 0.1558,
      "step": 1115
    },
    {
      "epoch": 0.7243813387423935,
      "grad_norm": 0.08744911104440689,
      "learning_rate": 7e-06,
      "loss": 0.2025,
      "step": 1116
    },
    {
      "epoch": 0.7250304259634889,
      "grad_norm": 0.07169175893068314,
      "learning_rate": 7e-06,
      "loss": 0.1989,
      "step": 1117
    },
    {
      "epoch": 0.7256795131845841,
      "grad_norm": 0.1312273144721985,
      "learning_rate": 7e-06,
      "loss": 0.2031,
      "step": 1118
    },
    {
      "epoch": 0.7263286004056795,
      "grad_norm": 0.12572427093982697,
      "learning_rate": 7e-06,
      "loss": 0.1819,
      "step": 1119
    },
    {
      "epoch": 0.7269776876267748,
      "grad_norm": 0.08495935052633286,
      "learning_rate": 7e-06,
      "loss": 0.1812,
      "step": 1120
    },
    {
      "epoch": 0.7276267748478702,
      "grad_norm": 0.11584436893463135,
      "learning_rate": 7e-06,
      "loss": 0.1815,
      "step": 1121
    },
    {
      "epoch": 0.7282758620689656,
      "grad_norm": 0.12447939813137054,
      "learning_rate": 7e-06,
      "loss": 0.1887,
      "step": 1122
    },
    {
      "epoch": 0.7289249492900608,
      "grad_norm": 0.08468896895647049,
      "learning_rate": 7e-06,
      "loss": 0.1754,
      "step": 1123
    },
    {
      "epoch": 0.7295740365111562,
      "grad_norm": 0.06781353801488876,
      "learning_rate": 7e-06,
      "loss": 0.1522,
      "step": 1124
    },
    {
      "epoch": 0.7302231237322515,
      "grad_norm": 0.09685443341732025,
      "learning_rate": 7e-06,
      "loss": 0.1751,
      "step": 1125
    },
    {
      "epoch": 0.7308722109533469,
      "grad_norm": 0.07663414627313614,
      "learning_rate": 7e-06,
      "loss": 0.1972,
      "step": 1126
    },
    {
      "epoch": 0.7315212981744422,
      "grad_norm": 0.1905982494354248,
      "learning_rate": 7e-06,
      "loss": 0.2548,
      "step": 1127
    },
    {
      "epoch": 0.7321703853955375,
      "grad_norm": 0.07491372525691986,
      "learning_rate": 7e-06,
      "loss": 0.1715,
      "step": 1128
    },
    {
      "epoch": 0.7328194726166328,
      "grad_norm": 0.10638300329446793,
      "learning_rate": 7e-06,
      "loss": 0.1623,
      "step": 1129
    },
    {
      "epoch": 0.7334685598377282,
      "grad_norm": 0.13568063080310822,
      "learning_rate": 7e-06,
      "loss": 0.1584,
      "step": 1130
    },
    {
      "epoch": 0.7341176470588235,
      "grad_norm": 0.13506126403808594,
      "learning_rate": 7e-06,
      "loss": 0.1942,
      "step": 1131
    },
    {
      "epoch": 0.7347667342799189,
      "grad_norm": 0.12319384515285492,
      "learning_rate": 7e-06,
      "loss": 0.1996,
      "step": 1132
    },
    {
      "epoch": 0.7354158215010141,
      "grad_norm": 0.10051579773426056,
      "learning_rate": 7e-06,
      "loss": 0.1699,
      "step": 1133
    },
    {
      "epoch": 0.7360649087221095,
      "grad_norm": 0.13858841359615326,
      "learning_rate": 7e-06,
      "loss": 0.2328,
      "step": 1134
    },
    {
      "epoch": 0.7367139959432049,
      "grad_norm": 0.0820593312382698,
      "learning_rate": 7e-06,
      "loss": 0.2013,
      "step": 1135
    },
    {
      "epoch": 0.7373630831643002,
      "grad_norm": 0.08596577495336533,
      "learning_rate": 7e-06,
      "loss": 0.1707,
      "step": 1136
    },
    {
      "epoch": 0.7380121703853956,
      "grad_norm": 0.09824783354997635,
      "learning_rate": 7e-06,
      "loss": 0.3642,
      "step": 1137
    },
    {
      "epoch": 0.7386612576064908,
      "grad_norm": 0.10116039961576462,
      "learning_rate": 7e-06,
      "loss": 0.1737,
      "step": 1138
    },
    {
      "epoch": 0.7393103448275862,
      "grad_norm": 0.055525440722703934,
      "learning_rate": 7e-06,
      "loss": 0.1714,
      "step": 1139
    },
    {
      "epoch": 0.7399594320486815,
      "grad_norm": 0.08208776265382767,
      "learning_rate": 7e-06,
      "loss": 0.1676,
      "step": 1140
    },
    {
      "epoch": 0.7406085192697769,
      "grad_norm": 0.06320738047361374,
      "learning_rate": 7e-06,
      "loss": 0.2689,
      "step": 1141
    },
    {
      "epoch": 0.7412576064908722,
      "grad_norm": 0.1622925102710724,
      "learning_rate": 7e-06,
      "loss": 0.259,
      "step": 1142
    },
    {
      "epoch": 0.7419066937119675,
      "grad_norm": 0.07211928814649582,
      "learning_rate": 7e-06,
      "loss": 0.1802,
      "step": 1143
    },
    {
      "epoch": 0.7425557809330628,
      "grad_norm": 0.13063032925128937,
      "learning_rate": 7e-06,
      "loss": 0.2156,
      "step": 1144
    },
    {
      "epoch": 0.7432048681541582,
      "grad_norm": 0.0886145532131195,
      "learning_rate": 7e-06,
      "loss": 0.1456,
      "step": 1145
    },
    {
      "epoch": 0.7438539553752536,
      "grad_norm": 0.1044364646077156,
      "learning_rate": 7e-06,
      "loss": 0.1976,
      "step": 1146
    },
    {
      "epoch": 0.7445030425963489,
      "grad_norm": 0.09533261507749557,
      "learning_rate": 7e-06,
      "loss": 0.1599,
      "step": 1147
    },
    {
      "epoch": 0.7451521298174442,
      "grad_norm": 0.08895070105791092,
      "learning_rate": 7e-06,
      "loss": 0.2133,
      "step": 1148
    },
    {
      "epoch": 0.7458012170385395,
      "grad_norm": 0.15110258758068085,
      "learning_rate": 7e-06,
      "loss": 0.2074,
      "step": 1149
    },
    {
      "epoch": 0.7464503042596349,
      "grad_norm": 0.05506841465830803,
      "learning_rate": 7e-06,
      "loss": 0.3534,
      "step": 1150
    },
    {
      "epoch": 0.7470993914807302,
      "grad_norm": 0.08078233152627945,
      "learning_rate": 7e-06,
      "loss": 0.1812,
      "step": 1151
    },
    {
      "epoch": 0.7477484787018256,
      "grad_norm": 0.08422894775867462,
      "learning_rate": 7e-06,
      "loss": 0.1983,
      "step": 1152
    },
    {
      "epoch": 0.7483975659229208,
      "grad_norm": 0.09646874666213989,
      "learning_rate": 7e-06,
      "loss": 0.1859,
      "step": 1153
    },
    {
      "epoch": 0.7490466531440162,
      "grad_norm": 0.107677161693573,
      "learning_rate": 7e-06,
      "loss": 0.1875,
      "step": 1154
    },
    {
      "epoch": 0.7496957403651116,
      "grad_norm": 0.06354208290576935,
      "learning_rate": 7e-06,
      "loss": 0.1793,
      "step": 1155
    },
    {
      "epoch": 0.7503448275862069,
      "grad_norm": 0.15374499559402466,
      "learning_rate": 7e-06,
      "loss": 0.1618,
      "step": 1156
    },
    {
      "epoch": 0.7509939148073023,
      "grad_norm": 0.0692959576845169,
      "learning_rate": 7e-06,
      "loss": 0.5851,
      "step": 1157
    },
    {
      "epoch": 0.7516430020283975,
      "grad_norm": 0.0851849839091301,
      "learning_rate": 7e-06,
      "loss": 0.2621,
      "step": 1158
    },
    {
      "epoch": 0.7522920892494929,
      "grad_norm": 0.08572663366794586,
      "learning_rate": 7e-06,
      "loss": 0.1575,
      "step": 1159
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.07955417782068253,
      "learning_rate": 7e-06,
      "loss": 0.2101,
      "step": 1160
    },
    {
      "epoch": 0.7535902636916836,
      "grad_norm": 0.0637880265712738,
      "learning_rate": 7e-06,
      "loss": 0.1711,
      "step": 1161
    },
    {
      "epoch": 0.7542393509127789,
      "grad_norm": 0.16911469399929047,
      "learning_rate": 7e-06,
      "loss": 0.1962,
      "step": 1162
    },
    {
      "epoch": 0.7548884381338742,
      "grad_norm": 0.10655989497900009,
      "learning_rate": 7e-06,
      "loss": 0.1871,
      "step": 1163
    },
    {
      "epoch": 0.7555375253549695,
      "grad_norm": 0.08599619567394257,
      "learning_rate": 7e-06,
      "loss": 0.217,
      "step": 1164
    },
    {
      "epoch": 0.7561866125760649,
      "grad_norm": 0.06453023850917816,
      "learning_rate": 7e-06,
      "loss": 0.1825,
      "step": 1165
    },
    {
      "epoch": 0.7568356997971603,
      "grad_norm": 0.07851619273424149,
      "learning_rate": 7e-06,
      "loss": 0.1852,
      "step": 1166
    },
    {
      "epoch": 0.7574847870182556,
      "grad_norm": 0.10866542905569077,
      "learning_rate": 7e-06,
      "loss": 0.2084,
      "step": 1167
    },
    {
      "epoch": 0.7581338742393509,
      "grad_norm": 0.07343946397304535,
      "learning_rate": 7e-06,
      "loss": 0.1906,
      "step": 1168
    },
    {
      "epoch": 0.7587829614604462,
      "grad_norm": 0.10844822227954865,
      "learning_rate": 7e-06,
      "loss": 0.2127,
      "step": 1169
    },
    {
      "epoch": 0.7594320486815416,
      "grad_norm": 0.06473919749259949,
      "learning_rate": 7e-06,
      "loss": 0.1883,
      "step": 1170
    },
    {
      "epoch": 0.7600811359026369,
      "grad_norm": 0.08717571198940277,
      "learning_rate": 7e-06,
      "loss": 0.2263,
      "step": 1171
    },
    {
      "epoch": 0.7607302231237323,
      "grad_norm": 0.11093058437108994,
      "learning_rate": 7e-06,
      "loss": 0.1986,
      "step": 1172
    },
    {
      "epoch": 0.7613793103448275,
      "grad_norm": 0.09462130814790726,
      "learning_rate": 7e-06,
      "loss": 0.175,
      "step": 1173
    },
    {
      "epoch": 0.7620283975659229,
      "grad_norm": 0.24324539303779602,
      "learning_rate": 7e-06,
      "loss": 0.2683,
      "step": 1174
    },
    {
      "epoch": 0.7626774847870182,
      "grad_norm": 0.10794803500175476,
      "learning_rate": 7e-06,
      "loss": 0.1953,
      "step": 1175
    },
    {
      "epoch": 0.7633265720081136,
      "grad_norm": 0.09379436820745468,
      "learning_rate": 7e-06,
      "loss": 0.1705,
      "step": 1176
    },
    {
      "epoch": 0.763975659229209,
      "grad_norm": 0.055336128920316696,
      "learning_rate": 7e-06,
      "loss": 0.1429,
      "step": 1177
    },
    {
      "epoch": 0.7646247464503042,
      "grad_norm": 0.15826186537742615,
      "learning_rate": 7e-06,
      "loss": 0.2151,
      "step": 1178
    },
    {
      "epoch": 0.7652738336713996,
      "grad_norm": 0.10075722634792328,
      "learning_rate": 7e-06,
      "loss": 0.1972,
      "step": 1179
    },
    {
      "epoch": 0.7659229208924949,
      "grad_norm": 0.10398498177528381,
      "learning_rate": 7e-06,
      "loss": 0.4238,
      "step": 1180
    },
    {
      "epoch": 0.7665720081135903,
      "grad_norm": 0.07964881509542465,
      "learning_rate": 7e-06,
      "loss": 0.1785,
      "step": 1181
    },
    {
      "epoch": 0.7672210953346856,
      "grad_norm": 0.07844153046607971,
      "learning_rate": 7e-06,
      "loss": 0.1973,
      "step": 1182
    },
    {
      "epoch": 0.7678701825557809,
      "grad_norm": 0.1185440868139267,
      "learning_rate": 7e-06,
      "loss": 0.1702,
      "step": 1183
    },
    {
      "epoch": 0.7685192697768762,
      "grad_norm": 0.1550600826740265,
      "learning_rate": 7e-06,
      "loss": 0.2469,
      "step": 1184
    },
    {
      "epoch": 0.7691683569979716,
      "grad_norm": 0.06434416025876999,
      "learning_rate": 7e-06,
      "loss": 0.1761,
      "step": 1185
    },
    {
      "epoch": 0.769817444219067,
      "grad_norm": 0.06649652123451233,
      "learning_rate": 7e-06,
      "loss": 0.1933,
      "step": 1186
    },
    {
      "epoch": 0.7704665314401623,
      "grad_norm": 0.07568611204624176,
      "learning_rate": 7e-06,
      "loss": 0.1935,
      "step": 1187
    },
    {
      "epoch": 0.7711156186612576,
      "grad_norm": 0.12630611658096313,
      "learning_rate": 7e-06,
      "loss": 0.2209,
      "step": 1188
    },
    {
      "epoch": 0.7717647058823529,
      "grad_norm": 0.10436341911554337,
      "learning_rate": 7e-06,
      "loss": 0.1788,
      "step": 1189
    },
    {
      "epoch": 0.7724137931034483,
      "grad_norm": 0.07054974883794785,
      "learning_rate": 7e-06,
      "loss": 0.2111,
      "step": 1190
    },
    {
      "epoch": 0.7730628803245436,
      "grad_norm": 0.07960085570812225,
      "learning_rate": 7e-06,
      "loss": 0.1519,
      "step": 1191
    },
    {
      "epoch": 0.773711967545639,
      "grad_norm": 0.11868636310100555,
      "learning_rate": 7e-06,
      "loss": 0.1927,
      "step": 1192
    },
    {
      "epoch": 0.7743610547667342,
      "grad_norm": 0.05327087640762329,
      "learning_rate": 7e-06,
      "loss": 0.1813,
      "step": 1193
    },
    {
      "epoch": 0.7750101419878296,
      "grad_norm": 0.08567620068788528,
      "learning_rate": 7e-06,
      "loss": 0.1528,
      "step": 1194
    },
    {
      "epoch": 0.7756592292089249,
      "grad_norm": 0.10745508223772049,
      "learning_rate": 7e-06,
      "loss": 0.4734,
      "step": 1195
    },
    {
      "epoch": 0.7763083164300203,
      "grad_norm": 0.09263552725315094,
      "learning_rate": 7e-06,
      "loss": 0.1969,
      "step": 1196
    },
    {
      "epoch": 0.7769574036511157,
      "grad_norm": 0.09456706047058105,
      "learning_rate": 7e-06,
      "loss": 0.183,
      "step": 1197
    },
    {
      "epoch": 0.7776064908722109,
      "grad_norm": 0.11210276931524277,
      "learning_rate": 7e-06,
      "loss": 0.1899,
      "step": 1198
    },
    {
      "epoch": 0.7782555780933063,
      "grad_norm": 0.10396410524845123,
      "learning_rate": 7e-06,
      "loss": 0.1766,
      "step": 1199
    },
    {
      "epoch": 0.7789046653144016,
      "grad_norm": 0.13985519111156464,
      "learning_rate": 7e-06,
      "loss": 0.2081,
      "step": 1200
    },
    {
      "epoch": 0.7789046653144016,
      "eval_correct_accuracy": 0.6819338422391857,
      "eval_error_accuracy": 0.48266546600630345,
      "eval_f1": 0.565251779593989,
      "eval_loss": 0.351858526468277,
      "eval_runtime": 35.0383,
      "eval_samples_per_second": 97.037,
      "eval_steps_per_second": 6.079,
      "step": 1200
    },
    {
      "epoch": 0.779553752535497,
      "grad_norm": 0.12135709822177887,
      "learning_rate": 7e-06,
      "loss": 0.1754,
      "step": 1201
    },
    {
      "epoch": 0.7802028397565923,
      "grad_norm": 0.46518445014953613,
      "learning_rate": 7e-06,
      "loss": 0.2156,
      "step": 1202
    },
    {
      "epoch": 0.7808519269776876,
      "grad_norm": 0.09589465707540512,
      "learning_rate": 7e-06,
      "loss": 0.2056,
      "step": 1203
    },
    {
      "epoch": 0.7815010141987829,
      "grad_norm": 0.10043434053659439,
      "learning_rate": 7e-06,
      "loss": 0.1938,
      "step": 1204
    },
    {
      "epoch": 0.7821501014198783,
      "grad_norm": 0.07951034605503082,
      "learning_rate": 7e-06,
      "loss": 0.1561,
      "step": 1205
    },
    {
      "epoch": 0.7827991886409736,
      "grad_norm": 0.07614613324403763,
      "learning_rate": 7e-06,
      "loss": 0.1773,
      "step": 1206
    },
    {
      "epoch": 0.783448275862069,
      "grad_norm": 0.06779353320598602,
      "learning_rate": 7e-06,
      "loss": 0.1831,
      "step": 1207
    },
    {
      "epoch": 0.7840973630831642,
      "grad_norm": 0.05594043433666229,
      "learning_rate": 7e-06,
      "loss": 0.1776,
      "step": 1208
    },
    {
      "epoch": 0.7847464503042596,
      "grad_norm": 0.11095762997865677,
      "learning_rate": 7e-06,
      "loss": 0.2783,
      "step": 1209
    },
    {
      "epoch": 0.785395537525355,
      "grad_norm": 0.07348823547363281,
      "learning_rate": 7e-06,
      "loss": 0.18,
      "step": 1210
    },
    {
      "epoch": 0.7860446247464503,
      "grad_norm": 0.08576832711696625,
      "learning_rate": 7e-06,
      "loss": 0.178,
      "step": 1211
    },
    {
      "epoch": 0.7866937119675457,
      "grad_norm": 0.08465446531772614,
      "learning_rate": 7e-06,
      "loss": 0.1858,
      "step": 1212
    },
    {
      "epoch": 0.7873427991886409,
      "grad_norm": 0.10826869308948517,
      "learning_rate": 7e-06,
      "loss": 0.1883,
      "step": 1213
    },
    {
      "epoch": 0.7879918864097363,
      "grad_norm": 0.06547573208808899,
      "learning_rate": 7e-06,
      "loss": 0.2001,
      "step": 1214
    },
    {
      "epoch": 0.7886409736308316,
      "grad_norm": 0.14382979273796082,
      "learning_rate": 7e-06,
      "loss": 0.2248,
      "step": 1215
    },
    {
      "epoch": 0.789290060851927,
      "grad_norm": 0.07351269572973251,
      "learning_rate": 7e-06,
      "loss": 0.1703,
      "step": 1216
    },
    {
      "epoch": 0.7899391480730223,
      "grad_norm": 0.1031331717967987,
      "learning_rate": 7e-06,
      "loss": 0.2046,
      "step": 1217
    },
    {
      "epoch": 0.7905882352941176,
      "grad_norm": 0.06251981109380722,
      "learning_rate": 7e-06,
      "loss": 0.175,
      "step": 1218
    },
    {
      "epoch": 0.791237322515213,
      "grad_norm": 0.10681910812854767,
      "learning_rate": 7e-06,
      "loss": 0.3241,
      "step": 1219
    },
    {
      "epoch": 0.7918864097363083,
      "grad_norm": 0.14452819526195526,
      "learning_rate": 7e-06,
      "loss": 0.1779,
      "step": 1220
    },
    {
      "epoch": 0.7925354969574037,
      "grad_norm": 0.06987231224775314,
      "learning_rate": 7e-06,
      "loss": 0.1605,
      "step": 1221
    },
    {
      "epoch": 0.793184584178499,
      "grad_norm": 0.05453887954354286,
      "learning_rate": 7e-06,
      "loss": 0.1162,
      "step": 1222
    },
    {
      "epoch": 0.7938336713995943,
      "grad_norm": 0.07798866927623749,
      "learning_rate": 7e-06,
      "loss": 0.2101,
      "step": 1223
    },
    {
      "epoch": 0.7944827586206896,
      "grad_norm": 0.05664776638150215,
      "learning_rate": 7e-06,
      "loss": 0.1435,
      "step": 1224
    },
    {
      "epoch": 0.795131845841785,
      "grad_norm": 0.07407306134700775,
      "learning_rate": 7e-06,
      "loss": 0.2139,
      "step": 1225
    },
    {
      "epoch": 0.7957809330628803,
      "grad_norm": 0.08258751779794693,
      "learning_rate": 7e-06,
      "loss": 0.1526,
      "step": 1226
    },
    {
      "epoch": 0.7964300202839757,
      "grad_norm": 0.10032691061496735,
      "learning_rate": 7e-06,
      "loss": 0.1711,
      "step": 1227
    },
    {
      "epoch": 0.7970791075050709,
      "grad_norm": 0.07326345890760422,
      "learning_rate": 7e-06,
      "loss": 0.1709,
      "step": 1228
    },
    {
      "epoch": 0.7977281947261663,
      "grad_norm": 0.06574992090463638,
      "learning_rate": 7e-06,
      "loss": 0.1511,
      "step": 1229
    },
    {
      "epoch": 0.7983772819472617,
      "grad_norm": 0.0908009484410286,
      "learning_rate": 7e-06,
      "loss": 0.1727,
      "step": 1230
    },
    {
      "epoch": 0.799026369168357,
      "grad_norm": 0.1482851654291153,
      "learning_rate": 7e-06,
      "loss": 0.2756,
      "step": 1231
    },
    {
      "epoch": 0.7996754563894524,
      "grad_norm": 0.08401577174663544,
      "learning_rate": 7e-06,
      "loss": 0.1747,
      "step": 1232
    },
    {
      "epoch": 0.8003245436105477,
      "grad_norm": 0.12067075818777084,
      "learning_rate": 7e-06,
      "loss": 0.198,
      "step": 1233
    },
    {
      "epoch": 0.800973630831643,
      "grad_norm": 0.06479931622743607,
      "learning_rate": 7e-06,
      "loss": 0.1491,
      "step": 1234
    },
    {
      "epoch": 0.8016227180527383,
      "grad_norm": 0.08988012373447418,
      "learning_rate": 7e-06,
      "loss": 0.1832,
      "step": 1235
    },
    {
      "epoch": 0.8022718052738337,
      "grad_norm": 0.06192626804113388,
      "learning_rate": 7e-06,
      "loss": 0.1903,
      "step": 1236
    },
    {
      "epoch": 0.802920892494929,
      "grad_norm": 0.08058572560548782,
      "learning_rate": 7e-06,
      "loss": 0.1523,
      "step": 1237
    },
    {
      "epoch": 0.8035699797160244,
      "grad_norm": 0.06746809184551239,
      "learning_rate": 7e-06,
      "loss": 0.1638,
      "step": 1238
    },
    {
      "epoch": 0.8042190669371196,
      "grad_norm": 0.07876807451248169,
      "learning_rate": 7e-06,
      "loss": 0.3642,
      "step": 1239
    },
    {
      "epoch": 0.804868154158215,
      "grad_norm": 0.06253752112388611,
      "learning_rate": 7e-06,
      "loss": 0.1597,
      "step": 1240
    },
    {
      "epoch": 0.8055172413793104,
      "grad_norm": 0.10956554859876633,
      "learning_rate": 7e-06,
      "loss": 0.1969,
      "step": 1241
    },
    {
      "epoch": 0.8061663286004057,
      "grad_norm": 0.1515057384967804,
      "learning_rate": 7e-06,
      "loss": 0.177,
      "step": 1242
    },
    {
      "epoch": 0.8068154158215011,
      "grad_norm": 0.06274090707302094,
      "learning_rate": 7e-06,
      "loss": 0.3328,
      "step": 1243
    },
    {
      "epoch": 0.8074645030425963,
      "grad_norm": 0.06224995106458664,
      "learning_rate": 7e-06,
      "loss": 0.1375,
      "step": 1244
    },
    {
      "epoch": 0.8081135902636917,
      "grad_norm": 0.06519916653633118,
      "learning_rate": 7e-06,
      "loss": 0.2099,
      "step": 1245
    },
    {
      "epoch": 0.808762677484787,
      "grad_norm": 0.07164008170366287,
      "learning_rate": 7e-06,
      "loss": 0.1362,
      "step": 1246
    },
    {
      "epoch": 0.8094117647058824,
      "grad_norm": 0.09753094613552094,
      "learning_rate": 7e-06,
      "loss": 0.2023,
      "step": 1247
    },
    {
      "epoch": 0.8100608519269777,
      "grad_norm": 0.12464012205600739,
      "learning_rate": 7e-06,
      "loss": 0.1703,
      "step": 1248
    },
    {
      "epoch": 0.810709939148073,
      "grad_norm": 0.07537607848644257,
      "learning_rate": 7e-06,
      "loss": 0.1727,
      "step": 1249
    },
    {
      "epoch": 0.8113590263691683,
      "grad_norm": 0.14848613739013672,
      "learning_rate": 7e-06,
      "loss": 0.2102,
      "step": 1250
    },
    {
      "epoch": 0.8120081135902637,
      "grad_norm": 0.11275041848421097,
      "learning_rate": 7e-06,
      "loss": 0.1541,
      "step": 1251
    },
    {
      "epoch": 0.8126572008113591,
      "grad_norm": 0.16357794404029846,
      "learning_rate": 7e-06,
      "loss": 0.1917,
      "step": 1252
    },
    {
      "epoch": 0.8133062880324544,
      "grad_norm": 0.13957515358924866,
      "learning_rate": 7e-06,
      "loss": 0.191,
      "step": 1253
    },
    {
      "epoch": 0.8139553752535497,
      "grad_norm": 0.10380546003580093,
      "learning_rate": 7e-06,
      "loss": 0.1486,
      "step": 1254
    },
    {
      "epoch": 0.814604462474645,
      "grad_norm": 0.10582253336906433,
      "learning_rate": 7e-06,
      "loss": 0.2479,
      "step": 1255
    },
    {
      "epoch": 0.8152535496957404,
      "grad_norm": 0.14148911833763123,
      "learning_rate": 7e-06,
      "loss": 0.2969,
      "step": 1256
    },
    {
      "epoch": 0.8159026369168357,
      "grad_norm": 0.16120371222496033,
      "learning_rate": 7e-06,
      "loss": 0.222,
      "step": 1257
    },
    {
      "epoch": 0.8165517241379311,
      "grad_norm": 0.13647429645061493,
      "learning_rate": 7e-06,
      "loss": 0.1981,
      "step": 1258
    },
    {
      "epoch": 0.8172008113590263,
      "grad_norm": 0.16789746284484863,
      "learning_rate": 7e-06,
      "loss": 0.2447,
      "step": 1259
    },
    {
      "epoch": 0.8178498985801217,
      "grad_norm": 0.11321352422237396,
      "learning_rate": 7e-06,
      "loss": 0.1514,
      "step": 1260
    },
    {
      "epoch": 0.818498985801217,
      "grad_norm": 0.11045759916305542,
      "learning_rate": 7e-06,
      "loss": 0.1626,
      "step": 1261
    },
    {
      "epoch": 0.8191480730223124,
      "grad_norm": 0.07845539599657059,
      "learning_rate": 7e-06,
      "loss": 0.1822,
      "step": 1262
    },
    {
      "epoch": 0.8197971602434078,
      "grad_norm": 0.12436660379171371,
      "learning_rate": 7e-06,
      "loss": 0.1952,
      "step": 1263
    },
    {
      "epoch": 0.820446247464503,
      "grad_norm": 0.0833103358745575,
      "learning_rate": 7e-06,
      "loss": 0.1633,
      "step": 1264
    },
    {
      "epoch": 0.8210953346855984,
      "grad_norm": 0.12951387465000153,
      "learning_rate": 7e-06,
      "loss": 0.1941,
      "step": 1265
    },
    {
      "epoch": 0.8217444219066937,
      "grad_norm": 0.11982247978448868,
      "learning_rate": 7e-06,
      "loss": 0.1936,
      "step": 1266
    },
    {
      "epoch": 0.8223935091277891,
      "grad_norm": 0.08206292986869812,
      "learning_rate": 7e-06,
      "loss": 0.1872,
      "step": 1267
    },
    {
      "epoch": 0.8230425963488844,
      "grad_norm": 0.116920605301857,
      "learning_rate": 7e-06,
      "loss": 0.2235,
      "step": 1268
    },
    {
      "epoch": 0.8236916835699797,
      "grad_norm": 0.11303439736366272,
      "learning_rate": 7e-06,
      "loss": 0.2337,
      "step": 1269
    },
    {
      "epoch": 0.824340770791075,
      "grad_norm": 0.09126239269971848,
      "learning_rate": 7e-06,
      "loss": 0.2052,
      "step": 1270
    },
    {
      "epoch": 0.8249898580121704,
      "grad_norm": 0.06691264361143112,
      "learning_rate": 7e-06,
      "loss": 0.1624,
      "step": 1271
    },
    {
      "epoch": 0.8256389452332658,
      "grad_norm": 0.11018788069486618,
      "learning_rate": 7e-06,
      "loss": 0.2007,
      "step": 1272
    },
    {
      "epoch": 0.8262880324543611,
      "grad_norm": 0.12781552970409393,
      "learning_rate": 7e-06,
      "loss": 0.2196,
      "step": 1273
    },
    {
      "epoch": 0.8269371196754564,
      "grad_norm": 0.0973103865981102,
      "learning_rate": 7e-06,
      "loss": 0.2187,
      "step": 1274
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.07473714649677277,
      "learning_rate": 7e-06,
      "loss": 0.2827,
      "step": 1275
    },
    {
      "epoch": 0.8282352941176471,
      "grad_norm": 0.082256980240345,
      "learning_rate": 7e-06,
      "loss": 0.113,
      "step": 1276
    },
    {
      "epoch": 0.8288843813387424,
      "grad_norm": 0.11014839261770248,
      "learning_rate": 7e-06,
      "loss": 0.1999,
      "step": 1277
    },
    {
      "epoch": 0.8295334685598378,
      "grad_norm": 0.06798030436038971,
      "learning_rate": 7e-06,
      "loss": 0.1838,
      "step": 1278
    },
    {
      "epoch": 0.830182555780933,
      "grad_norm": 0.08683328330516815,
      "learning_rate": 7e-06,
      "loss": 0.1942,
      "step": 1279
    },
    {
      "epoch": 0.8308316430020284,
      "grad_norm": 0.09757524728775024,
      "learning_rate": 7e-06,
      "loss": 0.4104,
      "step": 1280
    },
    {
      "epoch": 0.8314807302231237,
      "grad_norm": 0.12037760019302368,
      "learning_rate": 7e-06,
      "loss": 0.1793,
      "step": 1281
    },
    {
      "epoch": 0.8321298174442191,
      "grad_norm": 0.1527567356824875,
      "learning_rate": 7e-06,
      "loss": 0.3563,
      "step": 1282
    },
    {
      "epoch": 0.8327789046653145,
      "grad_norm": 0.08320245891809464,
      "learning_rate": 7e-06,
      "loss": 0.1293,
      "step": 1283
    },
    {
      "epoch": 0.8334279918864097,
      "grad_norm": 0.09939316660165787,
      "learning_rate": 7e-06,
      "loss": 0.2172,
      "step": 1284
    },
    {
      "epoch": 0.8340770791075051,
      "grad_norm": 0.1325017362833023,
      "learning_rate": 7e-06,
      "loss": 0.1747,
      "step": 1285
    },
    {
      "epoch": 0.8347261663286004,
      "grad_norm": 0.14410065114498138,
      "learning_rate": 7e-06,
      "loss": 0.3393,
      "step": 1286
    },
    {
      "epoch": 0.8353752535496958,
      "grad_norm": 0.10517040640115738,
      "learning_rate": 7e-06,
      "loss": 0.3431,
      "step": 1287
    },
    {
      "epoch": 0.8360243407707911,
      "grad_norm": 0.12986606359481812,
      "learning_rate": 7e-06,
      "loss": 0.1554,
      "step": 1288
    },
    {
      "epoch": 0.8366734279918864,
      "grad_norm": 0.06273689866065979,
      "learning_rate": 7e-06,
      "loss": 0.1631,
      "step": 1289
    },
    {
      "epoch": 0.8373225152129817,
      "grad_norm": 0.11514387279748917,
      "learning_rate": 7e-06,
      "loss": 0.1748,
      "step": 1290
    },
    {
      "epoch": 0.8379716024340771,
      "grad_norm": 0.20667687058448792,
      "learning_rate": 7e-06,
      "loss": 0.2401,
      "step": 1291
    },
    {
      "epoch": 0.8386206896551724,
      "grad_norm": 0.11547894775867462,
      "learning_rate": 7e-06,
      "loss": 0.1711,
      "step": 1292
    },
    {
      "epoch": 0.8392697768762678,
      "grad_norm": 0.06603022664785385,
      "learning_rate": 7e-06,
      "loss": 0.1827,
      "step": 1293
    },
    {
      "epoch": 0.839918864097363,
      "grad_norm": 0.06122205778956413,
      "learning_rate": 7e-06,
      "loss": 0.1581,
      "step": 1294
    },
    {
      "epoch": 0.8405679513184584,
      "grad_norm": 0.11857891082763672,
      "learning_rate": 7e-06,
      "loss": 0.1946,
      "step": 1295
    },
    {
      "epoch": 0.8412170385395538,
      "grad_norm": 0.10037039965391159,
      "learning_rate": 7e-06,
      "loss": 0.1965,
      "step": 1296
    },
    {
      "epoch": 0.8418661257606491,
      "grad_norm": 0.09463918209075928,
      "learning_rate": 7e-06,
      "loss": 0.2001,
      "step": 1297
    },
    {
      "epoch": 0.8425152129817445,
      "grad_norm": 0.04920235648751259,
      "learning_rate": 7e-06,
      "loss": 0.1268,
      "step": 1298
    },
    {
      "epoch": 0.8431643002028397,
      "grad_norm": 0.05238345265388489,
      "learning_rate": 7e-06,
      "loss": 0.1679,
      "step": 1299
    },
    {
      "epoch": 0.8438133874239351,
      "grad_norm": 0.19458365440368652,
      "learning_rate": 7e-06,
      "loss": 0.1977,
      "step": 1300
    },
    {
      "epoch": 0.8438133874239351,
      "eval_correct_accuracy": 0.7650551314673452,
      "eval_error_accuracy": 0.3845114813147231,
      "eval_f1": 0.5117971914233169,
      "eval_loss": 0.35462164878845215,
      "eval_runtime": 35.2996,
      "eval_samples_per_second": 96.318,
      "eval_steps_per_second": 6.034,
      "step": 1300
    },
    {
      "epoch": 0.8444624746450304,
      "grad_norm": 0.08665528893470764,
      "learning_rate": 7e-06,
      "loss": 0.1906,
      "step": 1301
    },
    {
      "epoch": 0.8451115618661258,
      "grad_norm": 0.11286671459674835,
      "learning_rate": 7e-06,
      "loss": 0.1639,
      "step": 1302
    },
    {
      "epoch": 0.8457606490872212,
      "grad_norm": 0.08465243875980377,
      "learning_rate": 7e-06,
      "loss": 0.1887,
      "step": 1303
    },
    {
      "epoch": 0.8464097363083164,
      "grad_norm": 0.09702262282371521,
      "learning_rate": 7e-06,
      "loss": 0.2052,
      "step": 1304
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.1367177516222,
      "learning_rate": 7e-06,
      "loss": 0.2028,
      "step": 1305
    },
    {
      "epoch": 0.8477079107505071,
      "grad_norm": 0.08765251934528351,
      "learning_rate": 7e-06,
      "loss": 0.1602,
      "step": 1306
    },
    {
      "epoch": 0.8483569979716025,
      "grad_norm": 0.06276577711105347,
      "learning_rate": 7e-06,
      "loss": 0.1477,
      "step": 1307
    },
    {
      "epoch": 0.8490060851926978,
      "grad_norm": 0.07988291233778,
      "learning_rate": 7e-06,
      "loss": 0.1717,
      "step": 1308
    },
    {
      "epoch": 0.8496551724137931,
      "grad_norm": 0.1543007642030716,
      "learning_rate": 7e-06,
      "loss": 0.2045,
      "step": 1309
    },
    {
      "epoch": 0.8503042596348884,
      "grad_norm": 0.12605327367782593,
      "learning_rate": 7e-06,
      "loss": 0.1929,
      "step": 1310
    },
    {
      "epoch": 0.8509533468559838,
      "grad_norm": 0.08716985583305359,
      "learning_rate": 7e-06,
      "loss": 0.2031,
      "step": 1311
    },
    {
      "epoch": 0.8516024340770791,
      "grad_norm": 0.055786989629268646,
      "learning_rate": 7e-06,
      "loss": 0.1438,
      "step": 1312
    },
    {
      "epoch": 0.8522515212981745,
      "grad_norm": 0.1157737597823143,
      "learning_rate": 7e-06,
      "loss": 0.22,
      "step": 1313
    },
    {
      "epoch": 0.8529006085192697,
      "grad_norm": 0.25744500756263733,
      "learning_rate": 7e-06,
      "loss": 0.1675,
      "step": 1314
    },
    {
      "epoch": 0.8535496957403651,
      "grad_norm": 0.12455101311206818,
      "learning_rate": 7e-06,
      "loss": 0.2103,
      "step": 1315
    },
    {
      "epoch": 0.8541987829614605,
      "grad_norm": 0.09033727645874023,
      "learning_rate": 7e-06,
      "loss": 0.266,
      "step": 1316
    },
    {
      "epoch": 0.8548478701825558,
      "grad_norm": 0.08827075362205505,
      "learning_rate": 7e-06,
      "loss": 0.3367,
      "step": 1317
    },
    {
      "epoch": 0.8554969574036512,
      "grad_norm": 0.20030443370342255,
      "learning_rate": 7e-06,
      "loss": 0.2783,
      "step": 1318
    },
    {
      "epoch": 0.8561460446247464,
      "grad_norm": 0.15678615868091583,
      "learning_rate": 7e-06,
      "loss": 0.1784,
      "step": 1319
    },
    {
      "epoch": 0.8567951318458418,
      "grad_norm": 0.22422730922698975,
      "learning_rate": 7e-06,
      "loss": 0.2111,
      "step": 1320
    },
    {
      "epoch": 0.8574442190669371,
      "grad_norm": 0.07186123728752136,
      "learning_rate": 7e-06,
      "loss": 0.2201,
      "step": 1321
    },
    {
      "epoch": 0.8580933062880325,
      "grad_norm": 0.09901744872331619,
      "learning_rate": 7e-06,
      "loss": 0.1943,
      "step": 1322
    },
    {
      "epoch": 0.8587423935091278,
      "grad_norm": 0.11821915954351425,
      "learning_rate": 7e-06,
      "loss": 0.2426,
      "step": 1323
    },
    {
      "epoch": 0.8593914807302231,
      "grad_norm": 0.09146321564912796,
      "learning_rate": 7e-06,
      "loss": 0.1904,
      "step": 1324
    },
    {
      "epoch": 0.8600405679513184,
      "grad_norm": 0.07141463458538055,
      "learning_rate": 7e-06,
      "loss": 0.1546,
      "step": 1325
    },
    {
      "epoch": 0.8606896551724138,
      "grad_norm": 0.09153498709201813,
      "learning_rate": 7e-06,
      "loss": 0.2371,
      "step": 1326
    },
    {
      "epoch": 0.8613387423935092,
      "grad_norm": 0.16618481278419495,
      "learning_rate": 7e-06,
      "loss": 0.1738,
      "step": 1327
    },
    {
      "epoch": 0.8619878296146045,
      "grad_norm": 0.05655239149928093,
      "learning_rate": 7e-06,
      "loss": 0.1513,
      "step": 1328
    },
    {
      "epoch": 0.8626369168356998,
      "grad_norm": 0.1140107661485672,
      "learning_rate": 7e-06,
      "loss": 0.2137,
      "step": 1329
    },
    {
      "epoch": 0.8632860040567951,
      "grad_norm": 0.10972538590431213,
      "learning_rate": 7e-06,
      "loss": 0.1613,
      "step": 1330
    },
    {
      "epoch": 0.8639350912778905,
      "grad_norm": 0.07323839515447617,
      "learning_rate": 7e-06,
      "loss": 0.1865,
      "step": 1331
    },
    {
      "epoch": 0.8645841784989858,
      "grad_norm": 0.0785713791847229,
      "learning_rate": 7e-06,
      "loss": 0.186,
      "step": 1332
    },
    {
      "epoch": 0.8652332657200812,
      "grad_norm": 0.058130498975515366,
      "learning_rate": 7e-06,
      "loss": 0.1443,
      "step": 1333
    },
    {
      "epoch": 0.8658823529411764,
      "grad_norm": 0.07591551542282104,
      "learning_rate": 7e-06,
      "loss": 0.158,
      "step": 1334
    },
    {
      "epoch": 0.8665314401622718,
      "grad_norm": 0.11421910673379898,
      "learning_rate": 7e-06,
      "loss": 0.1449,
      "step": 1335
    },
    {
      "epoch": 0.8671805273833672,
      "grad_norm": 0.074659064412117,
      "learning_rate": 7e-06,
      "loss": 0.1578,
      "step": 1336
    },
    {
      "epoch": 0.8678296146044625,
      "grad_norm": 0.10084477812051773,
      "learning_rate": 7e-06,
      "loss": 0.213,
      "step": 1337
    },
    {
      "epoch": 0.8684787018255579,
      "grad_norm": 0.08061375468969345,
      "learning_rate": 7e-06,
      "loss": 0.1736,
      "step": 1338
    },
    {
      "epoch": 0.8691277890466531,
      "grad_norm": 0.08272751420736313,
      "learning_rate": 7e-06,
      "loss": 0.1739,
      "step": 1339
    },
    {
      "epoch": 0.8697768762677485,
      "grad_norm": 0.1740090399980545,
      "learning_rate": 7e-06,
      "loss": 0.1431,
      "step": 1340
    },
    {
      "epoch": 0.8704259634888438,
      "grad_norm": 0.08548545837402344,
      "learning_rate": 7e-06,
      "loss": 0.2043,
      "step": 1341
    },
    {
      "epoch": 0.8710750507099392,
      "grad_norm": 0.13228361308574677,
      "learning_rate": 7e-06,
      "loss": 0.1573,
      "step": 1342
    },
    {
      "epoch": 0.8717241379310345,
      "grad_norm": 0.12396644055843353,
      "learning_rate": 7e-06,
      "loss": 0.2008,
      "step": 1343
    },
    {
      "epoch": 0.8723732251521298,
      "grad_norm": 0.11849795281887054,
      "learning_rate": 7e-06,
      "loss": 0.2324,
      "step": 1344
    },
    {
      "epoch": 0.8730223123732251,
      "grad_norm": 0.09914084523916245,
      "learning_rate": 7e-06,
      "loss": 0.1817,
      "step": 1345
    },
    {
      "epoch": 0.8736713995943205,
      "grad_norm": 0.07012328505516052,
      "learning_rate": 7e-06,
      "loss": 0.1998,
      "step": 1346
    },
    {
      "epoch": 0.8743204868154159,
      "grad_norm": 0.07937942445278168,
      "learning_rate": 7e-06,
      "loss": 0.1529,
      "step": 1347
    },
    {
      "epoch": 0.8749695740365112,
      "grad_norm": 0.16418886184692383,
      "learning_rate": 7e-06,
      "loss": 0.1872,
      "step": 1348
    },
    {
      "epoch": 0.8756186612576065,
      "grad_norm": 0.10875436663627625,
      "learning_rate": 7e-06,
      "loss": 0.1653,
      "step": 1349
    },
    {
      "epoch": 0.8762677484787018,
      "grad_norm": 0.12615583837032318,
      "learning_rate": 7e-06,
      "loss": 0.1809,
      "step": 1350
    },
    {
      "epoch": 0.8769168356997972,
      "grad_norm": 0.12788601219654083,
      "learning_rate": 7e-06,
      "loss": 0.1751,
      "step": 1351
    },
    {
      "epoch": 0.8775659229208925,
      "grad_norm": 0.06504851579666138,
      "learning_rate": 7e-06,
      "loss": 0.1711,
      "step": 1352
    },
    {
      "epoch": 0.8782150101419879,
      "grad_norm": 0.18422412872314453,
      "learning_rate": 7e-06,
      "loss": 0.2147,
      "step": 1353
    },
    {
      "epoch": 0.8788640973630831,
      "grad_norm": 0.08443067967891693,
      "learning_rate": 7e-06,
      "loss": 0.1741,
      "step": 1354
    },
    {
      "epoch": 0.8795131845841785,
      "grad_norm": 0.06205539032816887,
      "learning_rate": 7e-06,
      "loss": 0.1871,
      "step": 1355
    },
    {
      "epoch": 0.8801622718052738,
      "grad_norm": 0.061886683106422424,
      "learning_rate": 7e-06,
      "loss": 0.2132,
      "step": 1356
    },
    {
      "epoch": 0.8808113590263692,
      "grad_norm": 0.062220413237810135,
      "learning_rate": 7e-06,
      "loss": 0.195,
      "step": 1357
    },
    {
      "epoch": 0.8814604462474646,
      "grad_norm": 0.13313128054141998,
      "learning_rate": 7e-06,
      "loss": 0.3493,
      "step": 1358
    },
    {
      "epoch": 0.8821095334685598,
      "grad_norm": 0.13952822983264923,
      "learning_rate": 7e-06,
      "loss": 0.1523,
      "step": 1359
    },
    {
      "epoch": 0.8827586206896552,
      "grad_norm": 0.12005273252725601,
      "learning_rate": 7e-06,
      "loss": 0.1879,
      "step": 1360
    },
    {
      "epoch": 0.8834077079107505,
      "grad_norm": 0.08022362738847733,
      "learning_rate": 7e-06,
      "loss": 0.1721,
      "step": 1361
    },
    {
      "epoch": 0.8840567951318459,
      "grad_norm": 0.08233587443828583,
      "learning_rate": 7e-06,
      "loss": 0.1806,
      "step": 1362
    },
    {
      "epoch": 0.8847058823529412,
      "grad_norm": 0.05539390817284584,
      "learning_rate": 7e-06,
      "loss": 0.1263,
      "step": 1363
    },
    {
      "epoch": 0.8853549695740365,
      "grad_norm": 0.148041233420372,
      "learning_rate": 7e-06,
      "loss": 0.1886,
      "step": 1364
    },
    {
      "epoch": 0.8860040567951318,
      "grad_norm": 0.20179122686386108,
      "learning_rate": 7e-06,
      "loss": 0.1787,
      "step": 1365
    },
    {
      "epoch": 0.8866531440162272,
      "grad_norm": 0.32341504096984863,
      "learning_rate": 7e-06,
      "loss": 0.1985,
      "step": 1366
    },
    {
      "epoch": 0.8873022312373225,
      "grad_norm": 0.07685403525829315,
      "learning_rate": 7e-06,
      "loss": 0.1564,
      "step": 1367
    },
    {
      "epoch": 0.8879513184584179,
      "grad_norm": 0.10985764116048813,
      "learning_rate": 7e-06,
      "loss": 0.1986,
      "step": 1368
    },
    {
      "epoch": 0.8886004056795132,
      "grad_norm": 0.10021812468767166,
      "learning_rate": 7e-06,
      "loss": 0.2048,
      "step": 1369
    },
    {
      "epoch": 0.8892494929006085,
      "grad_norm": 0.11998467892408371,
      "learning_rate": 7e-06,
      "loss": 0.198,
      "step": 1370
    },
    {
      "epoch": 0.8898985801217039,
      "grad_norm": 0.07196857035160065,
      "learning_rate": 7e-06,
      "loss": 0.1385,
      "step": 1371
    },
    {
      "epoch": 0.8905476673427992,
      "grad_norm": 0.08413168787956238,
      "learning_rate": 7e-06,
      "loss": 0.2077,
      "step": 1372
    },
    {
      "epoch": 0.8911967545638946,
      "grad_norm": 0.06033769249916077,
      "learning_rate": 7e-06,
      "loss": 0.1879,
      "step": 1373
    },
    {
      "epoch": 0.8918458417849898,
      "grad_norm": 0.16023875772953033,
      "learning_rate": 7e-06,
      "loss": 0.336,
      "step": 1374
    },
    {
      "epoch": 0.8924949290060852,
      "grad_norm": 0.08191760629415512,
      "learning_rate": 7e-06,
      "loss": 0.1848,
      "step": 1375
    },
    {
      "epoch": 0.8931440162271805,
      "grad_norm": 0.09898726642131805,
      "learning_rate": 7e-06,
      "loss": 0.2114,
      "step": 1376
    },
    {
      "epoch": 0.8937931034482759,
      "grad_norm": 0.14590629935264587,
      "learning_rate": 7e-06,
      "loss": 0.203,
      "step": 1377
    },
    {
      "epoch": 0.8944421906693713,
      "grad_norm": 0.10940130800008774,
      "learning_rate": 7e-06,
      "loss": 0.1879,
      "step": 1378
    },
    {
      "epoch": 0.8950912778904665,
      "grad_norm": 0.13803733885288239,
      "learning_rate": 7e-06,
      "loss": 0.1641,
      "step": 1379
    },
    {
      "epoch": 0.8957403651115619,
      "grad_norm": 0.13507364690303802,
      "learning_rate": 7e-06,
      "loss": 0.1885,
      "step": 1380
    },
    {
      "epoch": 0.8963894523326572,
      "grad_norm": 0.089432492852211,
      "learning_rate": 7e-06,
      "loss": 0.1605,
      "step": 1381
    },
    {
      "epoch": 0.8970385395537526,
      "grad_norm": 0.10064804553985596,
      "learning_rate": 7e-06,
      "loss": 0.1638,
      "step": 1382
    },
    {
      "epoch": 0.8976876267748479,
      "grad_norm": 0.07115018367767334,
      "learning_rate": 7e-06,
      "loss": 0.1332,
      "step": 1383
    },
    {
      "epoch": 0.8983367139959432,
      "grad_norm": 0.10578377544879913,
      "learning_rate": 7e-06,
      "loss": 0.1618,
      "step": 1384
    },
    {
      "epoch": 0.8989858012170385,
      "grad_norm": 0.10272284597158432,
      "learning_rate": 7e-06,
      "loss": 0.1851,
      "step": 1385
    },
    {
      "epoch": 0.8996348884381339,
      "grad_norm": 0.0724041685461998,
      "learning_rate": 7e-06,
      "loss": 0.1871,
      "step": 1386
    },
    {
      "epoch": 0.9002839756592292,
      "grad_norm": 0.23150499165058136,
      "learning_rate": 7e-06,
      "loss": 0.2935,
      "step": 1387
    },
    {
      "epoch": 0.9009330628803246,
      "grad_norm": 0.10664230585098267,
      "learning_rate": 7e-06,
      "loss": 0.2802,
      "step": 1388
    },
    {
      "epoch": 0.9015821501014198,
      "grad_norm": 0.3517186641693115,
      "learning_rate": 7e-06,
      "loss": 0.2133,
      "step": 1389
    },
    {
      "epoch": 0.9022312373225152,
      "grad_norm": 0.10411582142114639,
      "learning_rate": 7e-06,
      "loss": 0.1957,
      "step": 1390
    },
    {
      "epoch": 0.9028803245436106,
      "grad_norm": 0.10243440419435501,
      "learning_rate": 7e-06,
      "loss": 0.2356,
      "step": 1391
    },
    {
      "epoch": 0.9035294117647059,
      "grad_norm": 0.11145135015249252,
      "learning_rate": 7e-06,
      "loss": 0.2004,
      "step": 1392
    },
    {
      "epoch": 0.9041784989858013,
      "grad_norm": 0.08904942125082016,
      "learning_rate": 7e-06,
      "loss": 0.1824,
      "step": 1393
    },
    {
      "epoch": 0.9048275862068965,
      "grad_norm": 0.1174086332321167,
      "learning_rate": 7e-06,
      "loss": 0.1866,
      "step": 1394
    },
    {
      "epoch": 0.9054766734279919,
      "grad_norm": 0.08107534795999527,
      "learning_rate": 7e-06,
      "loss": 0.3567,
      "step": 1395
    },
    {
      "epoch": 0.9061257606490872,
      "grad_norm": 0.10085786879062653,
      "learning_rate": 7e-06,
      "loss": 0.2202,
      "step": 1396
    },
    {
      "epoch": 0.9067748478701826,
      "grad_norm": 0.08243635296821594,
      "learning_rate": 7e-06,
      "loss": 0.168,
      "step": 1397
    },
    {
      "epoch": 0.9074239350912779,
      "grad_norm": 0.14398981630802155,
      "learning_rate": 7e-06,
      "loss": 0.2433,
      "step": 1398
    },
    {
      "epoch": 0.9080730223123732,
      "grad_norm": 0.08094363659620285,
      "learning_rate": 7e-06,
      "loss": 0.2115,
      "step": 1399
    },
    {
      "epoch": 0.9087221095334685,
      "grad_norm": 0.11846261471509933,
      "learning_rate": 7e-06,
      "loss": 0.1704,
      "step": 1400
    },
    {
      "epoch": 0.9087221095334685,
      "eval_correct_accuracy": 0.6878710771840543,
      "eval_error_accuracy": 0.46915803692030617,
      "eval_f1": 0.557842910419312,
      "eval_loss": 0.36854952573776245,
      "eval_runtime": 35.3443,
      "eval_samples_per_second": 96.197,
      "eval_steps_per_second": 6.026,
      "step": 1400
    },
    {
      "epoch": 0.9093711967545639,
      "grad_norm": 0.13833342492580414,
      "learning_rate": 7e-06,
      "loss": 0.2038,
      "step": 1401
    },
    {
      "epoch": 0.9100202839756593,
      "grad_norm": 0.05516054108738899,
      "learning_rate": 7e-06,
      "loss": 0.1731,
      "step": 1402
    },
    {
      "epoch": 0.9106693711967546,
      "grad_norm": 0.09859669208526611,
      "learning_rate": 7e-06,
      "loss": 0.2033,
      "step": 1403
    },
    {
      "epoch": 0.9113184584178499,
      "grad_norm": 0.1567087471485138,
      "learning_rate": 7e-06,
      "loss": 0.2118,
      "step": 1404
    },
    {
      "epoch": 0.9119675456389452,
      "grad_norm": 0.07222668826580048,
      "learning_rate": 7e-06,
      "loss": 0.164,
      "step": 1405
    },
    {
      "epoch": 0.9126166328600406,
      "grad_norm": 0.08978309482336044,
      "learning_rate": 7e-06,
      "loss": 0.1798,
      "step": 1406
    },
    {
      "epoch": 0.9132657200811359,
      "grad_norm": 0.0905078649520874,
      "learning_rate": 7e-06,
      "loss": 0.1973,
      "step": 1407
    },
    {
      "epoch": 0.9139148073022313,
      "grad_norm": 0.0936221033334732,
      "learning_rate": 7e-06,
      "loss": 0.296,
      "step": 1408
    },
    {
      "epoch": 0.9145638945233265,
      "grad_norm": 0.07016237080097198,
      "learning_rate": 7e-06,
      "loss": 0.1697,
      "step": 1409
    },
    {
      "epoch": 0.9152129817444219,
      "grad_norm": 0.10002986341714859,
      "learning_rate": 7e-06,
      "loss": 0.188,
      "step": 1410
    },
    {
      "epoch": 0.9158620689655173,
      "grad_norm": 0.058715254068374634,
      "learning_rate": 7e-06,
      "loss": 0.1843,
      "step": 1411
    },
    {
      "epoch": 0.9165111561866126,
      "grad_norm": 0.0827600285410881,
      "learning_rate": 7e-06,
      "loss": 0.162,
      "step": 1412
    },
    {
      "epoch": 0.917160243407708,
      "grad_norm": 0.050004858523607254,
      "learning_rate": 7e-06,
      "loss": 0.1503,
      "step": 1413
    },
    {
      "epoch": 0.9178093306288032,
      "grad_norm": 0.08891229331493378,
      "learning_rate": 7e-06,
      "loss": 0.1616,
      "step": 1414
    },
    {
      "epoch": 0.9184584178498986,
      "grad_norm": 0.06464681774377823,
      "learning_rate": 7e-06,
      "loss": 0.1873,
      "step": 1415
    },
    {
      "epoch": 0.9191075050709939,
      "grad_norm": 0.17748574912548065,
      "learning_rate": 7e-06,
      "loss": 0.2144,
      "step": 1416
    },
    {
      "epoch": 0.9197565922920893,
      "grad_norm": 0.10100189596414566,
      "learning_rate": 7e-06,
      "loss": 0.206,
      "step": 1417
    },
    {
      "epoch": 0.9204056795131846,
      "grad_norm": 0.056519098579883575,
      "learning_rate": 7e-06,
      "loss": 0.1667,
      "step": 1418
    },
    {
      "epoch": 0.9210547667342799,
      "grad_norm": 0.17171835899353027,
      "learning_rate": 7e-06,
      "loss": 0.2188,
      "step": 1419
    },
    {
      "epoch": 0.9217038539553752,
      "grad_norm": 0.06262408941984177,
      "learning_rate": 7e-06,
      "loss": 0.1614,
      "step": 1420
    },
    {
      "epoch": 0.9223529411764706,
      "grad_norm": 0.09128474444150925,
      "learning_rate": 7e-06,
      "loss": 0.1808,
      "step": 1421
    },
    {
      "epoch": 0.923002028397566,
      "grad_norm": 0.06217663735151291,
      "learning_rate": 7e-06,
      "loss": 0.1806,
      "step": 1422
    },
    {
      "epoch": 0.9236511156186613,
      "grad_norm": 0.06859725713729858,
      "learning_rate": 7e-06,
      "loss": 0.1563,
      "step": 1423
    },
    {
      "epoch": 0.9243002028397566,
      "grad_norm": 0.11466571688652039,
      "learning_rate": 7e-06,
      "loss": 0.2194,
      "step": 1424
    },
    {
      "epoch": 0.9249492900608519,
      "grad_norm": 0.0993122085928917,
      "learning_rate": 7e-06,
      "loss": 0.2437,
      "step": 1425
    },
    {
      "epoch": 0.9255983772819473,
      "grad_norm": 0.09681776165962219,
      "learning_rate": 7e-06,
      "loss": 0.2012,
      "step": 1426
    },
    {
      "epoch": 0.9262474645030426,
      "grad_norm": 0.07332218438386917,
      "learning_rate": 7e-06,
      "loss": 0.1472,
      "step": 1427
    },
    {
      "epoch": 0.926896551724138,
      "grad_norm": 0.07086972147226334,
      "learning_rate": 7e-06,
      "loss": 0.1737,
      "step": 1428
    },
    {
      "epoch": 0.9275456389452332,
      "grad_norm": 0.08291802555322647,
      "learning_rate": 7e-06,
      "loss": 0.1748,
      "step": 1429
    },
    {
      "epoch": 0.9281947261663286,
      "grad_norm": 0.06350383907556534,
      "learning_rate": 7e-06,
      "loss": 0.169,
      "step": 1430
    },
    {
      "epoch": 0.9288438133874239,
      "grad_norm": 0.05643841624259949,
      "learning_rate": 7e-06,
      "loss": 0.1699,
      "step": 1431
    },
    {
      "epoch": 0.9294929006085193,
      "grad_norm": 0.10205026715993881,
      "learning_rate": 7e-06,
      "loss": 0.1764,
      "step": 1432
    },
    {
      "epoch": 0.9301419878296147,
      "grad_norm": 0.07998646795749664,
      "learning_rate": 7e-06,
      "loss": 0.1972,
      "step": 1433
    },
    {
      "epoch": 0.9307910750507099,
      "grad_norm": 0.16770702600479126,
      "learning_rate": 7e-06,
      "loss": 0.1848,
      "step": 1434
    },
    {
      "epoch": 0.9314401622718053,
      "grad_norm": 0.06452329456806183,
      "learning_rate": 7e-06,
      "loss": 0.1987,
      "step": 1435
    },
    {
      "epoch": 0.9320892494929006,
      "grad_norm": 0.04470575600862503,
      "learning_rate": 7e-06,
      "loss": 0.1862,
      "step": 1436
    },
    {
      "epoch": 0.932738336713996,
      "grad_norm": 0.09256593137979507,
      "learning_rate": 7e-06,
      "loss": 0.1978,
      "step": 1437
    },
    {
      "epoch": 0.9333874239350913,
      "grad_norm": 0.08456490933895111,
      "learning_rate": 7e-06,
      "loss": 0.1868,
      "step": 1438
    },
    {
      "epoch": 0.9340365111561866,
      "grad_norm": 0.1031418964266777,
      "learning_rate": 7e-06,
      "loss": 0.165,
      "step": 1439
    },
    {
      "epoch": 0.9346855983772819,
      "grad_norm": 0.06185892969369888,
      "learning_rate": 7e-06,
      "loss": 0.2091,
      "step": 1440
    },
    {
      "epoch": 0.9353346855983773,
      "grad_norm": 0.13752059638500214,
      "learning_rate": 7e-06,
      "loss": 0.2372,
      "step": 1441
    },
    {
      "epoch": 0.9359837728194726,
      "grad_norm": 0.11665524542331696,
      "learning_rate": 7e-06,
      "loss": 0.2147,
      "step": 1442
    },
    {
      "epoch": 0.936632860040568,
      "grad_norm": 0.06347955763339996,
      "learning_rate": 7e-06,
      "loss": 0.191,
      "step": 1443
    },
    {
      "epoch": 0.9372819472616633,
      "grad_norm": 0.06839793920516968,
      "learning_rate": 7e-06,
      "loss": 0.1896,
      "step": 1444
    },
    {
      "epoch": 0.9379310344827586,
      "grad_norm": 0.06493601948022842,
      "learning_rate": 7e-06,
      "loss": 0.1549,
      "step": 1445
    },
    {
      "epoch": 0.938580121703854,
      "grad_norm": 0.11673151701688766,
      "learning_rate": 7e-06,
      "loss": 0.2047,
      "step": 1446
    },
    {
      "epoch": 0.9392292089249493,
      "grad_norm": 0.15195529162883759,
      "learning_rate": 7e-06,
      "loss": 0.3,
      "step": 1447
    },
    {
      "epoch": 0.9398782961460447,
      "grad_norm": 0.06980127841234207,
      "learning_rate": 7e-06,
      "loss": 0.1811,
      "step": 1448
    },
    {
      "epoch": 0.9405273833671399,
      "grad_norm": 0.06640547513961792,
      "learning_rate": 7e-06,
      "loss": 0.1819,
      "step": 1449
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.09252885729074478,
      "learning_rate": 7e-06,
      "loss": 0.1868,
      "step": 1450
    },
    {
      "epoch": 0.9418255578093306,
      "grad_norm": 0.09874745458364487,
      "learning_rate": 7e-06,
      "loss": 0.2081,
      "step": 1451
    },
    {
      "epoch": 0.942474645030426,
      "grad_norm": 0.08511047065258026,
      "learning_rate": 7e-06,
      "loss": 0.1815,
      "step": 1452
    },
    {
      "epoch": 0.9431237322515214,
      "grad_norm": 0.04287916049361229,
      "learning_rate": 7e-06,
      "loss": 0.2143,
      "step": 1453
    },
    {
      "epoch": 0.9437728194726166,
      "grad_norm": 0.08777709305286407,
      "learning_rate": 7e-06,
      "loss": 0.2027,
      "step": 1454
    },
    {
      "epoch": 0.944421906693712,
      "grad_norm": 0.058918096125125885,
      "learning_rate": 7e-06,
      "loss": 0.1723,
      "step": 1455
    },
    {
      "epoch": 0.9450709939148073,
      "grad_norm": 0.09275218099355698,
      "learning_rate": 7e-06,
      "loss": 0.1974,
      "step": 1456
    },
    {
      "epoch": 0.9457200811359027,
      "grad_norm": 0.060622427612543106,
      "learning_rate": 7e-06,
      "loss": 0.1653,
      "step": 1457
    },
    {
      "epoch": 0.946369168356998,
      "grad_norm": 0.07625995576381683,
      "learning_rate": 7e-06,
      "loss": 0.2146,
      "step": 1458
    },
    {
      "epoch": 0.9470182555780933,
      "grad_norm": 0.11632992327213287,
      "learning_rate": 7e-06,
      "loss": 0.1476,
      "step": 1459
    },
    {
      "epoch": 0.9476673427991886,
      "grad_norm": 0.16648252308368683,
      "learning_rate": 7e-06,
      "loss": 0.1929,
      "step": 1460
    },
    {
      "epoch": 0.948316430020284,
      "grad_norm": 0.08729204535484314,
      "learning_rate": 7e-06,
      "loss": 0.2295,
      "step": 1461
    },
    {
      "epoch": 0.9489655172413793,
      "grad_norm": 0.2512153387069702,
      "learning_rate": 7e-06,
      "loss": 0.2734,
      "step": 1462
    },
    {
      "epoch": 0.9496146044624747,
      "grad_norm": 0.09698393940925598,
      "learning_rate": 7e-06,
      "loss": 0.1462,
      "step": 1463
    },
    {
      "epoch": 0.9502636916835699,
      "grad_norm": 0.06855327636003494,
      "learning_rate": 7e-06,
      "loss": 0.2043,
      "step": 1464
    },
    {
      "epoch": 0.9509127789046653,
      "grad_norm": 0.15599815547466278,
      "learning_rate": 7e-06,
      "loss": 0.1972,
      "step": 1465
    },
    {
      "epoch": 0.9515618661257607,
      "grad_norm": 0.11493218690156937,
      "learning_rate": 7e-06,
      "loss": 0.215,
      "step": 1466
    },
    {
      "epoch": 0.952210953346856,
      "grad_norm": 0.14803063869476318,
      "learning_rate": 7e-06,
      "loss": 0.1878,
      "step": 1467
    },
    {
      "epoch": 0.9528600405679514,
      "grad_norm": 0.1316743940114975,
      "learning_rate": 7e-06,
      "loss": 0.2044,
      "step": 1468
    },
    {
      "epoch": 0.9535091277890466,
      "grad_norm": 0.12233086675405502,
      "learning_rate": 7e-06,
      "loss": 0.1704,
      "step": 1469
    },
    {
      "epoch": 0.954158215010142,
      "grad_norm": 0.09860173612833023,
      "learning_rate": 7e-06,
      "loss": 0.1644,
      "step": 1470
    },
    {
      "epoch": 0.9548073022312373,
      "grad_norm": 0.11040355265140533,
      "learning_rate": 7e-06,
      "loss": 0.2585,
      "step": 1471
    },
    {
      "epoch": 0.9554563894523327,
      "grad_norm": 0.06805054098367691,
      "learning_rate": 7e-06,
      "loss": 0.1847,
      "step": 1472
    },
    {
      "epoch": 0.956105476673428,
      "grad_norm": 0.1502326875925064,
      "learning_rate": 7e-06,
      "loss": 0.2399,
      "step": 1473
    },
    {
      "epoch": 0.9567545638945233,
      "grad_norm": 0.16522245109081268,
      "learning_rate": 7e-06,
      "loss": 0.2088,
      "step": 1474
    },
    {
      "epoch": 0.9574036511156186,
      "grad_norm": 0.22201400995254517,
      "learning_rate": 7e-06,
      "loss": 0.21,
      "step": 1475
    },
    {
      "epoch": 0.958052738336714,
      "grad_norm": 0.09754539281129837,
      "learning_rate": 7e-06,
      "loss": 0.1524,
      "step": 1476
    },
    {
      "epoch": 0.9587018255578094,
      "grad_norm": 0.08718102425336838,
      "learning_rate": 7e-06,
      "loss": 0.1801,
      "step": 1477
    },
    {
      "epoch": 0.9593509127789047,
      "grad_norm": 0.17842167615890503,
      "learning_rate": 7e-06,
      "loss": 0.4417,
      "step": 1478
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09177764505147934,
      "learning_rate": 7e-06,
      "loss": 0.1604,
      "step": 1479
    },
    {
      "epoch": 0.9606490872210953,
      "grad_norm": 0.09919729083776474,
      "learning_rate": 7e-06,
      "loss": 0.1932,
      "step": 1480
    },
    {
      "epoch": 0.9612981744421907,
      "grad_norm": 0.13959084451198578,
      "learning_rate": 7e-06,
      "loss": 0.1705,
      "step": 1481
    },
    {
      "epoch": 0.961947261663286,
      "grad_norm": 0.07125594466924667,
      "learning_rate": 7e-06,
      "loss": 0.1732,
      "step": 1482
    },
    {
      "epoch": 0.9625963488843814,
      "grad_norm": 0.09140107035636902,
      "learning_rate": 7e-06,
      "loss": 0.2216,
      "step": 1483
    },
    {
      "epoch": 0.9632454361054766,
      "grad_norm": 0.07044266164302826,
      "learning_rate": 7e-06,
      "loss": 0.2028,
      "step": 1484
    },
    {
      "epoch": 0.963894523326572,
      "grad_norm": 0.1132982149720192,
      "learning_rate": 7e-06,
      "loss": 0.363,
      "step": 1485
    },
    {
      "epoch": 0.9645436105476674,
      "grad_norm": 0.09800714999437332,
      "learning_rate": 7e-06,
      "loss": 0.1884,
      "step": 1486
    },
    {
      "epoch": 0.9651926977687627,
      "grad_norm": 0.11982666701078415,
      "learning_rate": 7e-06,
      "loss": 0.2251,
      "step": 1487
    },
    {
      "epoch": 0.9658417849898581,
      "grad_norm": 0.09538500010967255,
      "learning_rate": 7e-06,
      "loss": 0.1925,
      "step": 1488
    },
    {
      "epoch": 0.9664908722109533,
      "grad_norm": 0.058517273515462875,
      "learning_rate": 7e-06,
      "loss": 0.1737,
      "step": 1489
    },
    {
      "epoch": 0.9671399594320487,
      "grad_norm": 0.06642070412635803,
      "learning_rate": 7e-06,
      "loss": 0.2092,
      "step": 1490
    },
    {
      "epoch": 0.967789046653144,
      "grad_norm": 0.07364137470722198,
      "learning_rate": 7e-06,
      "loss": 0.2138,
      "step": 1491
    },
    {
      "epoch": 0.9684381338742394,
      "grad_norm": 0.11384686082601547,
      "learning_rate": 7e-06,
      "loss": 0.1624,
      "step": 1492
    },
    {
      "epoch": 0.9690872210953347,
      "grad_norm": 0.08539901673793793,
      "learning_rate": 7e-06,
      "loss": 0.2001,
      "step": 1493
    },
    {
      "epoch": 0.96973630831643,
      "grad_norm": 0.11918032169342041,
      "learning_rate": 7e-06,
      "loss": 0.1952,
      "step": 1494
    },
    {
      "epoch": 0.9703853955375253,
      "grad_norm": 0.06409487128257751,
      "learning_rate": 7e-06,
      "loss": 0.1457,
      "step": 1495
    },
    {
      "epoch": 0.9710344827586207,
      "grad_norm": 0.09563875198364258,
      "learning_rate": 7e-06,
      "loss": 0.116,
      "step": 1496
    },
    {
      "epoch": 0.971683569979716,
      "grad_norm": 0.07286424934864044,
      "learning_rate": 7e-06,
      "loss": 0.1698,
      "step": 1497
    },
    {
      "epoch": 0.9723326572008114,
      "grad_norm": 0.11045240610837936,
      "learning_rate": 7e-06,
      "loss": 0.1951,
      "step": 1498
    },
    {
      "epoch": 0.9729817444219067,
      "grad_norm": 0.0962943583726883,
      "learning_rate": 7e-06,
      "loss": 0.1916,
      "step": 1499
    },
    {
      "epoch": 0.973630831643002,
      "grad_norm": 0.09126906096935272,
      "learning_rate": 7e-06,
      "loss": 0.2002,
      "step": 1500
    },
    {
      "epoch": 0.973630831643002,
      "eval_correct_accuracy": 0.7217981340118744,
      "eval_error_accuracy": 0.43268797838811346,
      "eval_f1": 0.5410431049025997,
      "eval_loss": 0.3677108883857727,
      "eval_runtime": 35.1367,
      "eval_samples_per_second": 96.765,
      "eval_steps_per_second": 6.062,
      "step": 1500
    },
    {
      "epoch": 0.9742799188640974,
      "grad_norm": 0.06386500597000122,
      "learning_rate": 7e-06,
      "loss": 0.1592,
      "step": 1501
    },
    {
      "epoch": 0.9749290060851927,
      "grad_norm": 0.12646670639514923,
      "learning_rate": 7e-06,
      "loss": 0.2366,
      "step": 1502
    },
    {
      "epoch": 0.9755780933062881,
      "grad_norm": 0.05434926226735115,
      "learning_rate": 7e-06,
      "loss": 0.154,
      "step": 1503
    },
    {
      "epoch": 0.9762271805273833,
      "grad_norm": 0.07827460765838623,
      "learning_rate": 7e-06,
      "loss": 0.2454,
      "step": 1504
    },
    {
      "epoch": 0.9768762677484787,
      "grad_norm": 0.14506754279136658,
      "learning_rate": 7e-06,
      "loss": 0.239,
      "step": 1505
    },
    {
      "epoch": 0.977525354969574,
      "grad_norm": 0.1042436808347702,
      "learning_rate": 7e-06,
      "loss": 0.1527,
      "step": 1506
    },
    {
      "epoch": 0.9781744421906694,
      "grad_norm": 0.09074635058641434,
      "learning_rate": 7e-06,
      "loss": 0.1633,
      "step": 1507
    },
    {
      "epoch": 0.9788235294117648,
      "grad_norm": 0.0825517401099205,
      "learning_rate": 7e-06,
      "loss": 0.1609,
      "step": 1508
    },
    {
      "epoch": 0.97947261663286,
      "grad_norm": 0.1224844828248024,
      "learning_rate": 7e-06,
      "loss": 0.2044,
      "step": 1509
    },
    {
      "epoch": 0.9801217038539554,
      "grad_norm": 0.08661146461963654,
      "learning_rate": 7e-06,
      "loss": 0.2082,
      "step": 1510
    },
    {
      "epoch": 0.9807707910750507,
      "grad_norm": 0.14415007829666138,
      "learning_rate": 7e-06,
      "loss": 0.1745,
      "step": 1511
    },
    {
      "epoch": 0.9814198782961461,
      "grad_norm": 0.10742678493261337,
      "learning_rate": 7e-06,
      "loss": 0.2139,
      "step": 1512
    },
    {
      "epoch": 0.9820689655172414,
      "grad_norm": 0.12840139865875244,
      "learning_rate": 7e-06,
      "loss": 0.2181,
      "step": 1513
    },
    {
      "epoch": 0.9827180527383367,
      "grad_norm": 0.07588692754507065,
      "learning_rate": 7e-06,
      "loss": 0.4567,
      "step": 1514
    },
    {
      "epoch": 0.983367139959432,
      "grad_norm": 0.10324545204639435,
      "learning_rate": 7e-06,
      "loss": 0.1808,
      "step": 1515
    },
    {
      "epoch": 0.9840162271805274,
      "grad_norm": 0.06963858008384705,
      "learning_rate": 7e-06,
      "loss": 0.3038,
      "step": 1516
    },
    {
      "epoch": 0.9846653144016227,
      "grad_norm": 0.09993474185466766,
      "learning_rate": 7e-06,
      "loss": 0.1713,
      "step": 1517
    },
    {
      "epoch": 0.9853144016227181,
      "grad_norm": 0.07568129897117615,
      "learning_rate": 7e-06,
      "loss": 0.1868,
      "step": 1518
    },
    {
      "epoch": 0.9859634888438134,
      "grad_norm": 0.06582873314619064,
      "learning_rate": 7e-06,
      "loss": 0.1507,
      "step": 1519
    },
    {
      "epoch": 0.9866125760649087,
      "grad_norm": 0.05880097299814224,
      "learning_rate": 7e-06,
      "loss": 0.1645,
      "step": 1520
    },
    {
      "epoch": 0.9872616632860041,
      "grad_norm": 0.09218595921993256,
      "learning_rate": 7e-06,
      "loss": 0.1965,
      "step": 1521
    },
    {
      "epoch": 0.9879107505070994,
      "grad_norm": 0.07783514261245728,
      "learning_rate": 7e-06,
      "loss": 0.1986,
      "step": 1522
    },
    {
      "epoch": 0.9885598377281948,
      "grad_norm": 0.04523421451449394,
      "learning_rate": 7e-06,
      "loss": 0.1501,
      "step": 1523
    },
    {
      "epoch": 0.98920892494929,
      "grad_norm": 0.058497361838817596,
      "learning_rate": 7e-06,
      "loss": 0.1697,
      "step": 1524
    },
    {
      "epoch": 0.9898580121703854,
      "grad_norm": 0.0879085585474968,
      "learning_rate": 7e-06,
      "loss": 0.3724,
      "step": 1525
    },
    {
      "epoch": 0.9905070993914807,
      "grad_norm": 0.15824659168720245,
      "learning_rate": 7e-06,
      "loss": 0.2184,
      "step": 1526
    },
    {
      "epoch": 0.9911561866125761,
      "grad_norm": 0.08007409423589706,
      "learning_rate": 7e-06,
      "loss": 0.1641,
      "step": 1527
    },
    {
      "epoch": 0.9918052738336715,
      "grad_norm": 0.13636934757232666,
      "learning_rate": 7e-06,
      "loss": 0.1964,
      "step": 1528
    },
    {
      "epoch": 0.9924543610547667,
      "grad_norm": 0.11167921870946884,
      "learning_rate": 7e-06,
      "loss": 0.2312,
      "step": 1529
    },
    {
      "epoch": 0.993103448275862,
      "grad_norm": 0.08559376746416092,
      "learning_rate": 7e-06,
      "loss": 0.2175,
      "step": 1530
    },
    {
      "epoch": 0.9937525354969574,
      "grad_norm": 0.09317987412214279,
      "learning_rate": 7e-06,
      "loss": 0.1678,
      "step": 1531
    },
    {
      "epoch": 0.9944016227180528,
      "grad_norm": 0.07704206556081772,
      "learning_rate": 7e-06,
      "loss": 0.2023,
      "step": 1532
    },
    {
      "epoch": 0.9950507099391481,
      "grad_norm": 0.06724517792463303,
      "learning_rate": 7e-06,
      "loss": 0.1762,
      "step": 1533
    },
    {
      "epoch": 0.9956997971602434,
      "grad_norm": 0.11360162496566772,
      "learning_rate": 7e-06,
      "loss": 0.1866,
      "step": 1534
    },
    {
      "epoch": 0.9963488843813387,
      "grad_norm": 0.08944576233625412,
      "learning_rate": 7e-06,
      "loss": 0.1237,
      "step": 1535
    },
    {
      "epoch": 0.9969979716024341,
      "grad_norm": 0.06546694785356522,
      "learning_rate": 7e-06,
      "loss": 0.1742,
      "step": 1536
    },
    {
      "epoch": 0.9976470588235294,
      "grad_norm": 0.08051436394453049,
      "learning_rate": 7e-06,
      "loss": 0.1597,
      "step": 1537
    },
    {
      "epoch": 0.9982961460446248,
      "grad_norm": 0.13805879652500153,
      "learning_rate": 7e-06,
      "loss": 0.2124,
      "step": 1538
    },
    {
      "epoch": 0.99894523326572,
      "grad_norm": 0.060585152357816696,
      "learning_rate": 7e-06,
      "loss": 0.1538,
      "step": 1539
    },
    {
      "epoch": 0.9995943204868154,
      "grad_norm": 0.08599524199962616,
      "learning_rate": 7e-06,
      "loss": 0.1979,
      "step": 1540
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 1540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.744696043623678e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}