{
  "best_metric": 0.9900356268091739,
  "best_model_checkpoint": "Garbage-Classification-SWIN-Transformer/checkpoint-2800",
  "epoch": 9.973285841495994,
  "eval_steps": 500,
  "global_step": 2800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03561887800534283,
      "grad_norm": 3.4222159385681152,
      "learning_rate": 1.7857142857142857e-06,
      "loss": 1.4083,
      "step": 10
    },
    {
      "epoch": 0.07123775601068566,
      "grad_norm": 3.2973814010620117,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 1.3949,
      "step": 20
    },
    {
      "epoch": 0.10685663401602849,
      "grad_norm": 3.3026835918426514,
      "learning_rate": 5.357142857142857e-06,
      "loss": 1.3661,
      "step": 30
    },
    {
      "epoch": 0.14247551202137132,
      "grad_norm": 4.8538289070129395,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.3301,
      "step": 40
    },
    {
      "epoch": 0.17809439002671415,
      "grad_norm": 6.877591609954834,
      "learning_rate": 8.92857142857143e-06,
      "loss": 1.2576,
      "step": 50
    },
    {
      "epoch": 0.21371326803205698,
      "grad_norm": 5.944957256317139,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 1.1654,
      "step": 60
    },
    {
      "epoch": 0.2493321460373998,
      "grad_norm": 6.024969100952148,
      "learning_rate": 1.25e-05,
      "loss": 1.0324,
      "step": 70
    },
    {
      "epoch": 0.28495102404274264,
      "grad_norm": 6.543083667755127,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.8479,
      "step": 80
    },
    {
      "epoch": 0.3205699020480855,
      "grad_norm": 5.732212543487549,
      "learning_rate": 1.6071428571428572e-05,
      "loss": 0.7139,
      "step": 90
    },
    {
      "epoch": 0.3561887800534283,
      "grad_norm": 6.9801459312438965,
      "learning_rate": 1.785714285714286e-05,
      "loss": 0.5947,
      "step": 100
    },
    {
      "epoch": 0.39180765805877116,
      "grad_norm": 7.786228656768799,
      "learning_rate": 1.9642857142857145e-05,
      "loss": 0.5308,
      "step": 110
    },
    {
      "epoch": 0.42742653606411396,
      "grad_norm": 7.892849445343018,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.4402,
      "step": 120
    },
    {
      "epoch": 0.4630454140694568,
      "grad_norm": 6.560166835784912,
      "learning_rate": 2.3214285714285715e-05,
      "loss": 0.4023,
      "step": 130
    },
    {
      "epoch": 0.4986642920747996,
      "grad_norm": 7.141245365142822,
      "learning_rate": 2.5e-05,
      "loss": 0.3745,
      "step": 140
    },
    {
      "epoch": 0.5342831700801425,
      "grad_norm": 4.8248419761657715,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 0.3398,
      "step": 150
    },
    {
      "epoch": 0.5699020480854853,
      "grad_norm": 5.556511878967285,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.2968,
      "step": 160
    },
    {
      "epoch": 0.6055209260908282,
      "grad_norm": 7.37336540222168,
      "learning_rate": 3.0357142857142857e-05,
      "loss": 0.2907,
      "step": 170
    },
    {
      "epoch": 0.641139804096171,
      "grad_norm": 6.2109503746032715,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 0.2644,
      "step": 180
    },
    {
      "epoch": 0.6767586821015138,
      "grad_norm": 5.759757995605469,
      "learning_rate": 3.392857142857143e-05,
      "loss": 0.2918,
      "step": 190
    },
    {
      "epoch": 0.7123775601068566,
      "grad_norm": 3.9079067707061768,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.251,
      "step": 200
    },
    {
      "epoch": 0.7479964381121995,
      "grad_norm": 4.728653430938721,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.255,
      "step": 210
    },
    {
      "epoch": 0.7836153161175423,
      "grad_norm": 5.230493545532227,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.2118,
      "step": 220
    },
    {
      "epoch": 0.8192341941228851,
      "grad_norm": 5.2034101486206055,
      "learning_rate": 4.107142857142857e-05,
      "loss": 0.2045,
      "step": 230
    },
    {
      "epoch": 0.8548530721282279,
      "grad_norm": 5.750576972961426,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.2076,
      "step": 240
    },
    {
      "epoch": 0.8904719501335708,
      "grad_norm": 4.098123550415039,
      "learning_rate": 4.464285714285715e-05,
      "loss": 0.2077,
      "step": 250
    },
    {
      "epoch": 0.9260908281389136,
      "grad_norm": 6.287376880645752,
      "learning_rate": 4.642857142857143e-05,
      "loss": 0.1989,
      "step": 260
    },
    {
      "epoch": 0.9617097061442564,
      "grad_norm": 5.270883083343506,
      "learning_rate": 4.8214285714285716e-05,
      "loss": 0.1782,
      "step": 270
    },
    {
      "epoch": 0.9973285841495992,
      "grad_norm": 9.215749740600586,
      "learning_rate": 5e-05,
      "loss": 0.1969,
      "step": 280
    },
    {
      "epoch": 0.9973285841495992,
      "eval_accuracy": 0.9409374304163883,
      "eval_loss": 0.17398740351200104,
      "eval_runtime": 169.1651,
      "eval_samples_per_second": 106.192,
      "eval_steps_per_second": 1.661,
      "step": 280
    },
    {
      "epoch": 1.0329474621549422,
      "grad_norm": 3.8531081676483154,
      "learning_rate": 4.9801587301587306e-05,
      "loss": 0.1794,
      "step": 290
    },
    {
      "epoch": 1.068566340160285,
      "grad_norm": 5.727213382720947,
      "learning_rate": 4.960317460317461e-05,
      "loss": 0.1792,
      "step": 300
    },
    {
      "epoch": 1.1041852181656278,
      "grad_norm": 5.829253673553467,
      "learning_rate": 4.940476190476191e-05,
      "loss": 0.1445,
      "step": 310
    },
    {
      "epoch": 1.1398040961709706,
      "grad_norm": 5.027329921722412,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 0.1282,
      "step": 320
    },
    {
      "epoch": 1.1754229741763134,
      "grad_norm": 3.377734422683716,
      "learning_rate": 4.900793650793651e-05,
      "loss": 0.1346,
      "step": 330
    },
    {
      "epoch": 1.2110418521816562,
      "grad_norm": 4.863683700561523,
      "learning_rate": 4.880952380952381e-05,
      "loss": 0.1141,
      "step": 340
    },
    {
      "epoch": 1.2466607301869992,
      "grad_norm": 6.36651086807251,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 0.129,
      "step": 350
    },
    {
      "epoch": 1.282279608192342,
      "grad_norm": 6.058999061584473,
      "learning_rate": 4.841269841269841e-05,
      "loss": 0.1304,
      "step": 360
    },
    {
      "epoch": 1.3178984861976848,
      "grad_norm": 3.276484251022339,
      "learning_rate": 4.8214285714285716e-05,
      "loss": 0.1107,
      "step": 370
    },
    {
      "epoch": 1.3535173642030276,
      "grad_norm": 4.594018936157227,
      "learning_rate": 4.801587301587302e-05,
      "loss": 0.1185,
      "step": 380
    },
    {
      "epoch": 1.3891362422083704,
      "grad_norm": 2.975635290145874,
      "learning_rate": 4.781746031746032e-05,
      "loss": 0.1287,
      "step": 390
    },
    {
      "epoch": 1.4247551202137132,
      "grad_norm": 3.8723185062408447,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.1207,
      "step": 400
    },
    {
      "epoch": 1.460373998219056,
      "grad_norm": 2.9883522987365723,
      "learning_rate": 4.7420634920634924e-05,
      "loss": 0.1012,
      "step": 410
    },
    {
      "epoch": 1.495992876224399,
      "grad_norm": 4.591331481933594,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.1092,
      "step": 420
    },
    {
      "epoch": 1.5316117542297416,
      "grad_norm": 3.980555295944214,
      "learning_rate": 4.7023809523809525e-05,
      "loss": 0.1025,
      "step": 430
    },
    {
      "epoch": 1.5672306322350846,
      "grad_norm": 4.750612258911133,
      "learning_rate": 4.682539682539683e-05,
      "loss": 0.1047,
      "step": 440
    },
    {
      "epoch": 1.6028495102404274,
      "grad_norm": 3.2454400062561035,
      "learning_rate": 4.662698412698413e-05,
      "loss": 0.0914,
      "step": 450
    },
    {
      "epoch": 1.6384683882457702,
      "grad_norm": 11.585031509399414,
      "learning_rate": 4.642857142857143e-05,
      "loss": 0.0827,
      "step": 460
    },
    {
      "epoch": 1.674087266251113,
      "grad_norm": 2.573432207107544,
      "learning_rate": 4.623015873015873e-05,
      "loss": 0.0866,
      "step": 470
    },
    {
      "epoch": 1.7097061442564558,
      "grad_norm": 3.991711378097534,
      "learning_rate": 4.603174603174603e-05,
      "loss": 0.088,
      "step": 480
    },
    {
      "epoch": 1.7453250222617989,
      "grad_norm": 4.302712440490723,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 0.0985,
      "step": 490
    },
    {
      "epoch": 1.7809439002671414,
      "grad_norm": 3.247912883758545,
      "learning_rate": 4.563492063492064e-05,
      "loss": 0.1015,
      "step": 500
    },
    {
      "epoch": 1.8165627782724845,
      "grad_norm": 3.324694871902466,
      "learning_rate": 4.543650793650794e-05,
      "loss": 0.101,
      "step": 510
    },
    {
      "epoch": 1.8521816562778273,
      "grad_norm": 5.875315189361572,
      "learning_rate": 4.523809523809524e-05,
      "loss": 0.0908,
      "step": 520
    },
    {
      "epoch": 1.88780053428317,
      "grad_norm": 2.6438138484954834,
      "learning_rate": 4.503968253968254e-05,
      "loss": 0.0979,
      "step": 530
    },
    {
      "epoch": 1.9234194122885129,
      "grad_norm": 2.6687426567077637,
      "learning_rate": 4.4841269841269846e-05,
      "loss": 0.0834,
      "step": 540
    },
    {
      "epoch": 1.9590382902938557,
      "grad_norm": 3.7509348392486572,
      "learning_rate": 4.464285714285715e-05,
      "loss": 0.0826,
      "step": 550
    },
    {
      "epoch": 1.9946571682991987,
      "grad_norm": 3.0679826736450195,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.1014,
      "step": 560
    },
    {
      "epoch": 1.9982190560997328,
      "eval_accuracy": 0.9755065686929414,
      "eval_loss": 0.07521907240152359,
      "eval_runtime": 167.9798,
      "eval_samples_per_second": 106.941,
      "eval_steps_per_second": 1.673,
      "step": 561
    },
    {
      "epoch": 2.0302760463045413,
      "grad_norm": 4.248985290527344,
      "learning_rate": 4.4246031746031744e-05,
      "loss": 0.0633,
      "step": 570
    },
    {
      "epoch": 2.0658949243098843,
      "grad_norm": 3.44899320602417,
      "learning_rate": 4.404761904761905e-05,
      "loss": 0.0665,
      "step": 580
    },
    {
      "epoch": 2.101513802315227,
      "grad_norm": 4.588482856750488,
      "learning_rate": 4.384920634920635e-05,
      "loss": 0.0503,
      "step": 590
    },
    {
      "epoch": 2.13713268032057,
      "grad_norm": 3.4909369945526123,
      "learning_rate": 4.3650793650793655e-05,
      "loss": 0.0513,
      "step": 600
    },
    {
      "epoch": 2.172751558325913,
      "grad_norm": 2.8658242225646973,
      "learning_rate": 4.345238095238096e-05,
      "loss": 0.0552,
      "step": 610
    },
    {
      "epoch": 2.2083704363312555,
      "grad_norm": 3.1010851860046387,
      "learning_rate": 4.3253968253968256e-05,
      "loss": 0.0468,
      "step": 620
    },
    {
      "epoch": 2.2439893143365985,
      "grad_norm": 1.9300130605697632,
      "learning_rate": 4.305555555555556e-05,
      "loss": 0.0551,
      "step": 630
    },
    {
      "epoch": 2.279608192341941,
      "grad_norm": 2.8282604217529297,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.0525,
      "step": 640
    },
    {
      "epoch": 2.315227070347284,
      "grad_norm": 4.43895149230957,
      "learning_rate": 4.265873015873016e-05,
      "loss": 0.0492,
      "step": 650
    },
    {
      "epoch": 2.3508459483526267,
      "grad_norm": 4.581601142883301,
      "learning_rate": 4.2460317460317464e-05,
      "loss": 0.0506,
      "step": 660
    },
    {
      "epoch": 2.3864648263579697,
      "grad_norm": 4.677193641662598,
      "learning_rate": 4.226190476190476e-05,
      "loss": 0.0404,
      "step": 670
    },
    {
      "epoch": 2.4220837043633123,
      "grad_norm": 2.8398616313934326,
      "learning_rate": 4.2063492063492065e-05,
      "loss": 0.0438,
      "step": 680
    },
    {
      "epoch": 2.4577025823686554,
      "grad_norm": 5.424591064453125,
      "learning_rate": 4.186507936507937e-05,
      "loss": 0.0544,
      "step": 690
    },
    {
      "epoch": 2.4933214603739984,
      "grad_norm": 4.595205307006836,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.0557,
      "step": 700
    },
    {
      "epoch": 2.528940338379341,
      "grad_norm": 3.7095601558685303,
      "learning_rate": 4.1468253968253976e-05,
      "loss": 0.0505,
      "step": 710
    },
    {
      "epoch": 2.564559216384684,
      "grad_norm": 2.084617853164673,
      "learning_rate": 4.126984126984127e-05,
      "loss": 0.037,
      "step": 720
    },
    {
      "epoch": 2.6001780943900266,
      "grad_norm": 3.442814350128174,
      "learning_rate": 4.107142857142857e-05,
      "loss": 0.0399,
      "step": 730
    },
    {
      "epoch": 2.6357969723953696,
      "grad_norm": 3.6135501861572266,
      "learning_rate": 4.0873015873015874e-05,
      "loss": 0.0498,
      "step": 740
    },
    {
      "epoch": 2.671415850400712,
      "grad_norm": 3.422394275665283,
      "learning_rate": 4.067460317460318e-05,
      "loss": 0.0526,
      "step": 750
    },
    {
      "epoch": 2.707034728406055,
      "grad_norm": 4.467539310455322,
      "learning_rate": 4.047619047619048e-05,
      "loss": 0.0392,
      "step": 760
    },
    {
      "epoch": 2.742653606411398,
      "grad_norm": 2.9515881538391113,
      "learning_rate": 4.027777777777778e-05,
      "loss": 0.0468,
      "step": 770
    },
    {
      "epoch": 2.778272484416741,
      "grad_norm": 4.296915054321289,
      "learning_rate": 4.007936507936508e-05,
      "loss": 0.0534,
      "step": 780
    },
    {
      "epoch": 2.813891362422084,
      "grad_norm": 2.723884344100952,
      "learning_rate": 3.9880952380952386e-05,
      "loss": 0.048,
      "step": 790
    },
    {
      "epoch": 2.8495102404274264,
      "grad_norm": 1.9511892795562744,
      "learning_rate": 3.968253968253968e-05,
      "loss": 0.0429,
      "step": 800
    },
    {
      "epoch": 2.8851291184327694,
      "grad_norm": 2.8428244590759277,
      "learning_rate": 3.9484126984126986e-05,
      "loss": 0.0386,
      "step": 810
    },
    {
      "epoch": 2.920747996438112,
      "grad_norm": 5.256746768951416,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.0421,
      "step": 820
    },
    {
      "epoch": 2.956366874443455,
      "grad_norm": 2.277379035949707,
      "learning_rate": 3.908730158730159e-05,
      "loss": 0.0521,
      "step": 830
    },
    {
      "epoch": 2.991985752448798,
      "grad_norm": 2.638746500015259,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0333,
      "step": 840
    },
    {
      "epoch": 2.9991095280498663,
      "eval_accuracy": 0.9824092629703852,
      "eval_loss": 0.05514274910092354,
      "eval_runtime": 167.4573,
      "eval_samples_per_second": 107.275,
      "eval_steps_per_second": 1.678,
      "step": 842
    },
    {
      "epoch": 3.0276046304541406,
      "grad_norm": 2.1443052291870117,
      "learning_rate": 3.8690476190476195e-05,
      "loss": 0.0221,
      "step": 850
    },
    {
      "epoch": 3.0632235084594837,
      "grad_norm": 2.5836849212646484,
      "learning_rate": 3.84920634920635e-05,
      "loss": 0.0258,
      "step": 860
    },
    {
      "epoch": 3.0988423864648262,
      "grad_norm": 4.255194187164307,
      "learning_rate": 3.8293650793650795e-05,
      "loss": 0.0269,
      "step": 870
    },
    {
      "epoch": 3.1344612644701693,
      "grad_norm": 1.1687568426132202,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.0229,
      "step": 880
    },
    {
      "epoch": 3.170080142475512,
      "grad_norm": 3.9044461250305176,
      "learning_rate": 3.7896825396825396e-05,
      "loss": 0.0241,
      "step": 890
    },
    {
      "epoch": 3.205699020480855,
      "grad_norm": 3.447392225265503,
      "learning_rate": 3.76984126984127e-05,
      "loss": 0.0258,
      "step": 900
    },
    {
      "epoch": 3.241317898486198,
      "grad_norm": 1.6584926843643188,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0221,
      "step": 910
    },
    {
      "epoch": 3.2769367764915405,
      "grad_norm": 6.36900520324707,
      "learning_rate": 3.730158730158731e-05,
      "loss": 0.0272,
      "step": 920
    },
    {
      "epoch": 3.3125556544968835,
      "grad_norm": 1.01226007938385,
      "learning_rate": 3.7103174603174604e-05,
      "loss": 0.0242,
      "step": 930
    },
    {
      "epoch": 3.348174532502226,
      "grad_norm": 0.7302751541137695,
      "learning_rate": 3.690476190476191e-05,
      "loss": 0.0276,
      "step": 940
    },
    {
      "epoch": 3.383793410507569,
      "grad_norm": 5.937874794006348,
      "learning_rate": 3.6706349206349205e-05,
      "loss": 0.03,
      "step": 950
    },
    {
      "epoch": 3.4194122885129117,
      "grad_norm": 3.688383102416992,
      "learning_rate": 3.650793650793651e-05,
      "loss": 0.0239,
      "step": 960
    },
    {
      "epoch": 3.4550311665182547,
      "grad_norm": 8.206720352172852,
      "learning_rate": 3.630952380952381e-05,
      "loss": 0.038,
      "step": 970
    },
    {
      "epoch": 3.4906500445235977,
      "grad_norm": 1.0089924335479736,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.0275,
      "step": 980
    },
    {
      "epoch": 3.5262689225289403,
      "grad_norm": 4.124368190765381,
      "learning_rate": 3.591269841269841e-05,
      "loss": 0.0383,
      "step": 990
    },
    {
      "epoch": 3.5618878005342833,
      "grad_norm": 4.853917598724365,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.0183,
      "step": 1000
    },
    {
      "epoch": 3.597506678539626,
      "grad_norm": 0.8174078464508057,
      "learning_rate": 3.551587301587302e-05,
      "loss": 0.0176,
      "step": 1010
    },
    {
      "epoch": 3.633125556544969,
      "grad_norm": 2.9447782039642334,
      "learning_rate": 3.5317460317460324e-05,
      "loss": 0.0294,
      "step": 1020
    },
    {
      "epoch": 3.6687444345503115,
      "grad_norm": 2.926154375076294,
      "learning_rate": 3.511904761904762e-05,
      "loss": 0.0257,
      "step": 1030
    },
    {
      "epoch": 3.7043633125556545,
      "grad_norm": 2.566096305847168,
      "learning_rate": 3.492063492063492e-05,
      "loss": 0.0172,
      "step": 1040
    },
    {
      "epoch": 3.7399821905609976,
      "grad_norm": 3.302891492843628,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.0314,
      "step": 1050
    },
    {
      "epoch": 3.77560106856634,
      "grad_norm": 1.366655945777893,
      "learning_rate": 3.4523809523809526e-05,
      "loss": 0.0243,
      "step": 1060
    },
    {
      "epoch": 3.8112199465716827,
      "grad_norm": 1.3453521728515625,
      "learning_rate": 3.432539682539683e-05,
      "loss": 0.0166,
      "step": 1070
    },
    {
      "epoch": 3.8468388245770258,
      "grad_norm": 3.0241684913635254,
      "learning_rate": 3.412698412698413e-05,
      "loss": 0.0341,
      "step": 1080
    },
    {
      "epoch": 3.8824577025823688,
      "grad_norm": 4.319317817687988,
      "learning_rate": 3.392857142857143e-05,
      "loss": 0.0199,
      "step": 1090
    },
    {
      "epoch": 3.9180765805877114,
      "grad_norm": 0.412803053855896,
      "learning_rate": 3.3730158730158734e-05,
      "loss": 0.0282,
      "step": 1100
    },
    {
      "epoch": 3.9536954585930544,
      "grad_norm": 2.4635729789733887,
      "learning_rate": 3.353174603174603e-05,
      "loss": 0.0201,
      "step": 1110
    },
    {
      "epoch": 3.9893143365983974,
      "grad_norm": 3.8697004318237305,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0332,
      "step": 1120
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9844689378757515,
      "eval_loss": 0.05261413753032684,
      "eval_runtime": 166.8993,
      "eval_samples_per_second": 107.634,
      "eval_steps_per_second": 1.684,
      "step": 1123
    },
    {
      "epoch": 4.02493321460374,
      "grad_norm": 0.7120935916900635,
      "learning_rate": 3.313492063492064e-05,
      "loss": 0.0137,
      "step": 1130
    },
    {
      "epoch": 4.060552092609083,
      "grad_norm": 4.946304798126221,
      "learning_rate": 3.2936507936507936e-05,
      "loss": 0.0199,
      "step": 1140
    },
    {
      "epoch": 4.096170970614426,
      "grad_norm": 3.8117804527282715,
      "learning_rate": 3.273809523809524e-05,
      "loss": 0.0177,
      "step": 1150
    },
    {
      "epoch": 4.131789848619769,
      "grad_norm": 1.8831413984298706,
      "learning_rate": 3.253968253968254e-05,
      "loss": 0.0197,
      "step": 1160
    },
    {
      "epoch": 4.167408726625111,
      "grad_norm": 0.7759003639221191,
      "learning_rate": 3.234126984126985e-05,
      "loss": 0.0151,
      "step": 1170
    },
    {
      "epoch": 4.203027604630454,
      "grad_norm": 4.501601696014404,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 0.0148,
      "step": 1180
    },
    {
      "epoch": 4.238646482635797,
      "grad_norm": 2.070884943008423,
      "learning_rate": 3.194444444444444e-05,
      "loss": 0.0176,
      "step": 1190
    },
    {
      "epoch": 4.27426536064114,
      "grad_norm": 2.1252646446228027,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.0141,
      "step": 1200
    },
    {
      "epoch": 4.309884238646482,
      "grad_norm": 2.5485196113586426,
      "learning_rate": 3.154761904761905e-05,
      "loss": 0.017,
      "step": 1210
    },
    {
      "epoch": 4.345503116651826,
      "grad_norm": 2.234440803527832,
      "learning_rate": 3.134920634920635e-05,
      "loss": 0.0149,
      "step": 1220
    },
    {
      "epoch": 4.3811219946571685,
      "grad_norm": 0.32285788655281067,
      "learning_rate": 3.1150793650793656e-05,
      "loss": 0.0119,
      "step": 1230
    },
    {
      "epoch": 4.416740872662511,
      "grad_norm": 1.612191081047058,
      "learning_rate": 3.095238095238095e-05,
      "loss": 0.0173,
      "step": 1240
    },
    {
      "epoch": 4.452359750667854,
      "grad_norm": 5.2718987464904785,
      "learning_rate": 3.075396825396826e-05,
      "loss": 0.0201,
      "step": 1250
    },
    {
      "epoch": 4.487978628673197,
      "grad_norm": 0.8849789500236511,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.0144,
      "step": 1260
    },
    {
      "epoch": 4.52359750667854,
      "grad_norm": 2.3857195377349854,
      "learning_rate": 3.0357142857142857e-05,
      "loss": 0.0202,
      "step": 1270
    },
    {
      "epoch": 4.559216384683882,
      "grad_norm": 0.264274924993515,
      "learning_rate": 3.0158730158730158e-05,
      "loss": 0.0185,
      "step": 1280
    },
    {
      "epoch": 4.594835262689225,
      "grad_norm": 2.823655605316162,
      "learning_rate": 2.996031746031746e-05,
      "loss": 0.0158,
      "step": 1290
    },
    {
      "epoch": 4.630454140694568,
      "grad_norm": 1.4026707410812378,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 0.018,
      "step": 1300
    },
    {
      "epoch": 4.666073018699911,
      "grad_norm": 3.624246120452881,
      "learning_rate": 2.9563492063492066e-05,
      "loss": 0.0113,
      "step": 1310
    },
    {
      "epoch": 4.7016918967052534,
      "grad_norm": 7.601430892944336,
      "learning_rate": 2.9365079365079366e-05,
      "loss": 0.016,
      "step": 1320
    },
    {
      "epoch": 4.737310774710597,
      "grad_norm": 3.959538221359253,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.023,
      "step": 1330
    },
    {
      "epoch": 4.7729296527159395,
      "grad_norm": 5.305376052856445,
      "learning_rate": 2.8968253968253974e-05,
      "loss": 0.0126,
      "step": 1340
    },
    {
      "epoch": 4.808548530721282,
      "grad_norm": 3.621107816696167,
      "learning_rate": 2.876984126984127e-05,
      "loss": 0.0174,
      "step": 1350
    },
    {
      "epoch": 4.844167408726625,
      "grad_norm": 1.0203227996826172,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.0152,
      "step": 1360
    },
    {
      "epoch": 4.879786286731968,
      "grad_norm": 1.6705145835876465,
      "learning_rate": 2.8373015873015875e-05,
      "loss": 0.0117,
      "step": 1370
    },
    {
      "epoch": 4.915405164737311,
      "grad_norm": 0.6089171767234802,
      "learning_rate": 2.8174603174603175e-05,
      "loss": 0.0184,
      "step": 1380
    },
    {
      "epoch": 4.951024042742653,
      "grad_norm": 1.959324836730957,
      "learning_rate": 2.797619047619048e-05,
      "loss": 0.0135,
      "step": 1390
    },
    {
      "epoch": 4.986642920747997,
      "grad_norm": 1.1502999067306519,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0218,
      "step": 1400
    },
    {
      "epoch": 4.997328584149599,
      "eval_accuracy": 0.986584279670452,
      "eval_loss": 0.05108034238219261,
      "eval_runtime": 172.0304,
      "eval_samples_per_second": 104.423,
      "eval_steps_per_second": 1.633,
      "step": 1403
    },
    {
      "epoch": 5.022261798753339,
      "grad_norm": 1.9193094968795776,
      "learning_rate": 2.7579365079365083e-05,
      "loss": 0.0109,
      "step": 1410
    },
    {
      "epoch": 5.057880676758682,
      "grad_norm": 0.6912887096405029,
      "learning_rate": 2.7380952380952383e-05,
      "loss": 0.0092,
      "step": 1420
    },
    {
      "epoch": 5.0934995547640245,
      "grad_norm": 0.3243821859359741,
      "learning_rate": 2.718253968253968e-05,
      "loss": 0.0107,
      "step": 1430
    },
    {
      "epoch": 5.129118432769368,
      "grad_norm": 1.4951286315917969,
      "learning_rate": 2.6984126984126984e-05,
      "loss": 0.0057,
      "step": 1440
    },
    {
      "epoch": 5.1647373107747105,
      "grad_norm": 1.5525418519973755,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 0.0084,
      "step": 1450
    },
    {
      "epoch": 5.200356188780053,
      "grad_norm": 1.0544503927230835,
      "learning_rate": 2.6587301587301588e-05,
      "loss": 0.0143,
      "step": 1460
    },
    {
      "epoch": 5.235975066785397,
      "grad_norm": 5.903578758239746,
      "learning_rate": 2.6388888888888892e-05,
      "loss": 0.0135,
      "step": 1470
    },
    {
      "epoch": 5.271593944790739,
      "grad_norm": 0.9685418009757996,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 0.0122,
      "step": 1480
    },
    {
      "epoch": 5.307212822796082,
      "grad_norm": 1.8341890573501587,
      "learning_rate": 2.5992063492063496e-05,
      "loss": 0.0174,
      "step": 1490
    },
    {
      "epoch": 5.342831700801424,
      "grad_norm": 1.3028405904769897,
      "learning_rate": 2.5793650793650796e-05,
      "loss": 0.0074,
      "step": 1500
    },
    {
      "epoch": 5.378450578806768,
      "grad_norm": 0.8573488593101501,
      "learning_rate": 2.5595238095238093e-05,
      "loss": 0.0123,
      "step": 1510
    },
    {
      "epoch": 5.41406945681211,
      "grad_norm": 0.8495379686355591,
      "learning_rate": 2.5396825396825397e-05,
      "loss": 0.0092,
      "step": 1520
    },
    {
      "epoch": 5.449688334817453,
      "grad_norm": 4.806192874908447,
      "learning_rate": 2.5198412698412697e-05,
      "loss": 0.0117,
      "step": 1530
    },
    {
      "epoch": 5.485307212822796,
      "grad_norm": 1.6827951669692993,
      "learning_rate": 2.5e-05,
      "loss": 0.0109,
      "step": 1540
    },
    {
      "epoch": 5.520926090828139,
      "grad_norm": 1.2856072187423706,
      "learning_rate": 2.4801587301587305e-05,
      "loss": 0.0066,
      "step": 1550
    },
    {
      "epoch": 5.556544968833482,
      "grad_norm": 1.8056079149246216,
      "learning_rate": 2.4603174603174602e-05,
      "loss": 0.0103,
      "step": 1560
    },
    {
      "epoch": 5.592163846838824,
      "grad_norm": 1.3088467121124268,
      "learning_rate": 2.4404761904761906e-05,
      "loss": 0.0071,
      "step": 1570
    },
    {
      "epoch": 5.627782724844168,
      "grad_norm": 0.6147578954696655,
      "learning_rate": 2.4206349206349206e-05,
      "loss": 0.0135,
      "step": 1580
    },
    {
      "epoch": 5.66340160284951,
      "grad_norm": 3.193516969680786,
      "learning_rate": 2.400793650793651e-05,
      "loss": 0.0128,
      "step": 1590
    },
    {
      "epoch": 5.699020480854853,
      "grad_norm": 1.0563770532608032,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.0116,
      "step": 1600
    },
    {
      "epoch": 5.734639358860196,
      "grad_norm": 4.569545269012451,
      "learning_rate": 2.361111111111111e-05,
      "loss": 0.0134,
      "step": 1610
    },
    {
      "epoch": 5.770258236865539,
      "grad_norm": 1.7688589096069336,
      "learning_rate": 2.3412698412698414e-05,
      "loss": 0.0104,
      "step": 1620
    },
    {
      "epoch": 5.805877114870881,
      "grad_norm": 0.6101610064506531,
      "learning_rate": 2.3214285714285715e-05,
      "loss": 0.0124,
      "step": 1630
    },
    {
      "epoch": 5.841495992876224,
      "grad_norm": 6.201462745666504,
      "learning_rate": 2.3015873015873015e-05,
      "loss": 0.0154,
      "step": 1640
    },
    {
      "epoch": 5.8771148708815675,
      "grad_norm": 0.349431574344635,
      "learning_rate": 2.281746031746032e-05,
      "loss": 0.0073,
      "step": 1650
    },
    {
      "epoch": 5.91273374888691,
      "grad_norm": 2.9831745624542236,
      "learning_rate": 2.261904761904762e-05,
      "loss": 0.0116,
      "step": 1660
    },
    {
      "epoch": 5.948352626892253,
      "grad_norm": 2.7858543395996094,
      "learning_rate": 2.2420634920634923e-05,
      "loss": 0.0099,
      "step": 1670
    },
    {
      "epoch": 5.983971504897596,
      "grad_norm": 1.6756843328475952,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0086,
      "step": 1680
    },
    {
      "epoch": 5.998219056099733,
      "eval_accuracy": 0.9873079492317969,
      "eval_loss": 0.051540642976760864,
      "eval_runtime": 168.5925,
      "eval_samples_per_second": 106.553,
      "eval_steps_per_second": 1.667,
      "step": 1684
    },
    {
      "epoch": 6.019590382902939,
      "grad_norm": 3.378427028656006,
      "learning_rate": 2.2023809523809524e-05,
      "loss": 0.0089,
      "step": 1690
    },
    {
      "epoch": 6.055209260908281,
      "grad_norm": 2.4920456409454346,
      "learning_rate": 2.1825396825396827e-05,
      "loss": 0.0096,
      "step": 1700
    },
    {
      "epoch": 6.090828138913624,
      "grad_norm": 2.810772657394409,
      "learning_rate": 2.1626984126984128e-05,
      "loss": 0.0102,
      "step": 1710
    },
    {
      "epoch": 6.126447016918967,
      "grad_norm": 0.348102331161499,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.0146,
      "step": 1720
    },
    {
      "epoch": 6.16206589492431,
      "grad_norm": 1.5229803323745728,
      "learning_rate": 2.1230158730158732e-05,
      "loss": 0.0128,
      "step": 1730
    },
    {
      "epoch": 6.1976847729296525,
      "grad_norm": 1.736290693283081,
      "learning_rate": 2.1031746031746032e-05,
      "loss": 0.011,
      "step": 1740
    },
    {
      "epoch": 6.233303650934996,
      "grad_norm": 0.5413634777069092,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.006,
      "step": 1750
    },
    {
      "epoch": 6.2689225289403385,
      "grad_norm": 1.1734927892684937,
      "learning_rate": 2.0634920634920636e-05,
      "loss": 0.0087,
      "step": 1760
    },
    {
      "epoch": 6.304541406945681,
      "grad_norm": 0.21049003303050995,
      "learning_rate": 2.0436507936507937e-05,
      "loss": 0.0074,
      "step": 1770
    },
    {
      "epoch": 6.340160284951024,
      "grad_norm": 1.5480449199676514,
      "learning_rate": 2.023809523809524e-05,
      "loss": 0.0072,
      "step": 1780
    },
    {
      "epoch": 6.375779162956367,
      "grad_norm": 1.130774736404419,
      "learning_rate": 2.003968253968254e-05,
      "loss": 0.0082,
      "step": 1790
    },
    {
      "epoch": 6.41139804096171,
      "grad_norm": 0.9111453890800476,
      "learning_rate": 1.984126984126984e-05,
      "loss": 0.0081,
      "step": 1800
    },
    {
      "epoch": 6.447016918967052,
      "grad_norm": 0.12502439320087433,
      "learning_rate": 1.9642857142857145e-05,
      "loss": 0.0095,
      "step": 1810
    },
    {
      "epoch": 6.482635796972396,
      "grad_norm": 0.832012414932251,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.0042,
      "step": 1820
    },
    {
      "epoch": 6.518254674977738,
      "grad_norm": 3.6857128143310547,
      "learning_rate": 1.924603174603175e-05,
      "loss": 0.0081,
      "step": 1830
    },
    {
      "epoch": 6.553873552983081,
      "grad_norm": 2.5364391803741455,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.0089,
      "step": 1840
    },
    {
      "epoch": 6.5894924309884235,
      "grad_norm": 23.89657211303711,
      "learning_rate": 1.884920634920635e-05,
      "loss": 0.0118,
      "step": 1850
    },
    {
      "epoch": 6.625111308993767,
      "grad_norm": 2.562563180923462,
      "learning_rate": 1.8650793650793654e-05,
      "loss": 0.0096,
      "step": 1860
    },
    {
      "epoch": 6.66073018699911,
      "grad_norm": 3.3216705322265625,
      "learning_rate": 1.8452380952380954e-05,
      "loss": 0.0113,
      "step": 1870
    },
    {
      "epoch": 6.696349065004452,
      "grad_norm": 0.8016022443771362,
      "learning_rate": 1.8253968253968254e-05,
      "loss": 0.0054,
      "step": 1880
    },
    {
      "epoch": 6.731967943009796,
      "grad_norm": 3.4590423107147217,
      "learning_rate": 1.8055555555555555e-05,
      "loss": 0.0071,
      "step": 1890
    },
    {
      "epoch": 6.767586821015138,
      "grad_norm": 0.12237533181905746,
      "learning_rate": 1.785714285714286e-05,
      "loss": 0.0073,
      "step": 1900
    },
    {
      "epoch": 6.803205699020481,
      "grad_norm": 1.500787615776062,
      "learning_rate": 1.7658730158730162e-05,
      "loss": 0.0055,
      "step": 1910
    },
    {
      "epoch": 6.838824577025823,
      "grad_norm": 3.2452268600463867,
      "learning_rate": 1.746031746031746e-05,
      "loss": 0.0112,
      "step": 1920
    },
    {
      "epoch": 6.874443455031167,
      "grad_norm": 0.4780968129634857,
      "learning_rate": 1.7261904761904763e-05,
      "loss": 0.0074,
      "step": 1930
    },
    {
      "epoch": 6.910062333036509,
      "grad_norm": 0.4808253347873688,
      "learning_rate": 1.7063492063492063e-05,
      "loss": 0.0096,
      "step": 1940
    },
    {
      "epoch": 6.945681211041852,
      "grad_norm": 1.5511194467544556,
      "learning_rate": 1.6865079365079367e-05,
      "loss": 0.0047,
      "step": 1950
    },
    {
      "epoch": 6.9813000890471955,
      "grad_norm": 0.8193422555923462,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0057,
      "step": 1960
    },
    {
      "epoch": 6.999109528049867,
      "eval_accuracy": 0.9875306167891338,
      "eval_loss": 0.04618992656469345,
      "eval_runtime": 166.9392,
      "eval_samples_per_second": 107.608,
      "eval_steps_per_second": 1.683,
      "step": 1965
    },
    {
      "epoch": 7.016918967052538,
      "grad_norm": 0.1917089819908142,
      "learning_rate": 1.6468253968253968e-05,
      "loss": 0.0042,
      "step": 1970
    },
    {
      "epoch": 7.052537845057881,
      "grad_norm": 0.48844099044799805,
      "learning_rate": 1.626984126984127e-05,
      "loss": 0.0053,
      "step": 1980
    },
    {
      "epoch": 7.088156723063223,
      "grad_norm": 1.94171941280365,
      "learning_rate": 1.6071428571428572e-05,
      "loss": 0.0064,
      "step": 1990
    },
    {
      "epoch": 7.123775601068567,
      "grad_norm": 10.181970596313477,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.0072,
      "step": 2000
    },
    {
      "epoch": 7.159394479073909,
      "grad_norm": 0.4458209276199341,
      "learning_rate": 1.5674603174603176e-05,
      "loss": 0.0086,
      "step": 2010
    },
    {
      "epoch": 7.195013357079252,
      "grad_norm": 1.125260829925537,
      "learning_rate": 1.5476190476190476e-05,
      "loss": 0.0064,
      "step": 2020
    },
    {
      "epoch": 7.230632235084594,
      "grad_norm": 2.555405616760254,
      "learning_rate": 1.527777777777778e-05,
      "loss": 0.0047,
      "step": 2030
    },
    {
      "epoch": 7.266251113089938,
      "grad_norm": 0.7010562419891357,
      "learning_rate": 1.5079365079365079e-05,
      "loss": 0.0027,
      "step": 2040
    },
    {
      "epoch": 7.3018699910952805,
      "grad_norm": 0.19031189382076263,
      "learning_rate": 1.4880952380952381e-05,
      "loss": 0.004,
      "step": 2050
    },
    {
      "epoch": 7.337488869100623,
      "grad_norm": 0.25679388642311096,
      "learning_rate": 1.4682539682539683e-05,
      "loss": 0.0024,
      "step": 2060
    },
    {
      "epoch": 7.3731077471059665,
      "grad_norm": 0.22514384984970093,
      "learning_rate": 1.4484126984126987e-05,
      "loss": 0.0022,
      "step": 2070
    },
    {
      "epoch": 7.408726625111309,
      "grad_norm": 1.700714111328125,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.0069,
      "step": 2080
    },
    {
      "epoch": 7.444345503116652,
      "grad_norm": 3.598724842071533,
      "learning_rate": 1.4087301587301587e-05,
      "loss": 0.0043,
      "step": 2090
    },
    {
      "epoch": 7.479964381121994,
      "grad_norm": 0.9559303522109985,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0069,
      "step": 2100
    },
    {
      "epoch": 7.515583259127338,
      "grad_norm": 2.183023452758789,
      "learning_rate": 1.3690476190476192e-05,
      "loss": 0.0043,
      "step": 2110
    },
    {
      "epoch": 7.55120213713268,
      "grad_norm": 0.6762595772743225,
      "learning_rate": 1.3492063492063492e-05,
      "loss": 0.0054,
      "step": 2120
    },
    {
      "epoch": 7.586821015138023,
      "grad_norm": 0.12739060819149017,
      "learning_rate": 1.3293650793650794e-05,
      "loss": 0.0059,
      "step": 2130
    },
    {
      "epoch": 7.622439893143366,
      "grad_norm": 0.8051192164421082,
      "learning_rate": 1.3095238095238096e-05,
      "loss": 0.0014,
      "step": 2140
    },
    {
      "epoch": 7.658058771148709,
      "grad_norm": 1.1333496570587158,
      "learning_rate": 1.2896825396825398e-05,
      "loss": 0.0072,
      "step": 2150
    },
    {
      "epoch": 7.6936776491540515,
      "grad_norm": 0.06419402360916138,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 0.0044,
      "step": 2160
    },
    {
      "epoch": 7.729296527159395,
      "grad_norm": 1.2567334175109863,
      "learning_rate": 1.25e-05,
      "loss": 0.0028,
      "step": 2170
    },
    {
      "epoch": 7.7649154051647375,
      "grad_norm": 4.354968070983887,
      "learning_rate": 1.2301587301587301e-05,
      "loss": 0.0062,
      "step": 2180
    },
    {
      "epoch": 7.80053428317008,
      "grad_norm": 0.17071713507175446,
      "learning_rate": 1.2103174603174603e-05,
      "loss": 0.0045,
      "step": 2190
    },
    {
      "epoch": 7.836153161175423,
      "grad_norm": 0.057894542813301086,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 0.0068,
      "step": 2200
    },
    {
      "epoch": 7.871772039180766,
      "grad_norm": 4.474624156951904,
      "learning_rate": 1.1706349206349207e-05,
      "loss": 0.0043,
      "step": 2210
    },
    {
      "epoch": 7.907390917186109,
      "grad_norm": 0.9991622567176819,
      "learning_rate": 1.1507936507936508e-05,
      "loss": 0.0074,
      "step": 2220
    },
    {
      "epoch": 7.943009795191451,
      "grad_norm": 0.0822732001543045,
      "learning_rate": 1.130952380952381e-05,
      "loss": 0.0041,
      "step": 2230
    },
    {
      "epoch": 7.978628673196794,
      "grad_norm": 1.9230424165725708,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0043,
      "step": 2240
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9890892896904921,
      "eval_loss": 0.045326121151447296,
      "eval_runtime": 168.1961,
      "eval_samples_per_second": 106.804,
      "eval_steps_per_second": 1.671,
      "step": 2246
    },
    {
      "epoch": 8.014247551202137,
      "grad_norm": 2.2943098545074463,
      "learning_rate": 1.0912698412698414e-05,
      "loss": 0.0047,
      "step": 2250
    },
    {
      "epoch": 8.04986642920748,
      "grad_norm": 0.5264036059379578,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 0.0038,
      "step": 2260
    },
    {
      "epoch": 8.085485307212823,
      "grad_norm": 1.6306657791137695,
      "learning_rate": 1.0515873015873016e-05,
      "loss": 0.0023,
      "step": 2270
    },
    {
      "epoch": 8.121104185218165,
      "grad_norm": 0.7527822852134705,
      "learning_rate": 1.0317460317460318e-05,
      "loss": 0.0034,
      "step": 2280
    },
    {
      "epoch": 8.156723063223508,
      "grad_norm": 1.7613914012908936,
      "learning_rate": 1.011904761904762e-05,
      "loss": 0.0103,
      "step": 2290
    },
    {
      "epoch": 8.192341941228852,
      "grad_norm": 0.3057126998901367,
      "learning_rate": 9.92063492063492e-06,
      "loss": 0.002,
      "step": 2300
    },
    {
      "epoch": 8.227960819234195,
      "grad_norm": 0.1171383410692215,
      "learning_rate": 9.722222222222223e-06,
      "loss": 0.0038,
      "step": 2310
    },
    {
      "epoch": 8.263579697239537,
      "grad_norm": 0.17709870636463165,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.0104,
      "step": 2320
    },
    {
      "epoch": 8.29919857524488,
      "grad_norm": 2.5424516201019287,
      "learning_rate": 9.325396825396827e-06,
      "loss": 0.0028,
      "step": 2330
    },
    {
      "epoch": 8.334817453250222,
      "grad_norm": 1.413736343383789,
      "learning_rate": 9.126984126984127e-06,
      "loss": 0.0019,
      "step": 2340
    },
    {
      "epoch": 8.370436331255565,
      "grad_norm": 0.8712714910507202,
      "learning_rate": 8.92857142857143e-06,
      "loss": 0.0044,
      "step": 2350
    },
    {
      "epoch": 8.406055209260908,
      "grad_norm": 5.921164035797119,
      "learning_rate": 8.73015873015873e-06,
      "loss": 0.0027,
      "step": 2360
    },
    {
      "epoch": 8.441674087266252,
      "grad_norm": 0.6600878238677979,
      "learning_rate": 8.531746031746032e-06,
      "loss": 0.0094,
      "step": 2370
    },
    {
      "epoch": 8.477292965271594,
      "grad_norm": 0.046510376036167145,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0073,
      "step": 2380
    },
    {
      "epoch": 8.512911843276937,
      "grad_norm": 0.2806013822555542,
      "learning_rate": 8.134920634920636e-06,
      "loss": 0.0074,
      "step": 2390
    },
    {
      "epoch": 8.54853072128228,
      "grad_norm": 0.09230457246303558,
      "learning_rate": 7.936507936507936e-06,
      "loss": 0.0053,
      "step": 2400
    },
    {
      "epoch": 8.584149599287622,
      "grad_norm": 1.893324851989746,
      "learning_rate": 7.738095238095238e-06,
      "loss": 0.006,
      "step": 2410
    },
    {
      "epoch": 8.619768477292965,
      "grad_norm": 1.035352349281311,
      "learning_rate": 7.5396825396825394e-06,
      "loss": 0.0056,
      "step": 2420
    },
    {
      "epoch": 8.655387355298307,
      "grad_norm": 2.519357204437256,
      "learning_rate": 7.3412698412698415e-06,
      "loss": 0.0019,
      "step": 2430
    },
    {
      "epoch": 8.691006233303652,
      "grad_norm": 0.36915910243988037,
      "learning_rate": 7.142857142857143e-06,
      "loss": 0.0053,
      "step": 2440
    },
    {
      "epoch": 8.726625111308994,
      "grad_norm": 2.2446630001068115,
      "learning_rate": 6.944444444444445e-06,
      "loss": 0.0023,
      "step": 2450
    },
    {
      "epoch": 8.762243989314337,
      "grad_norm": 0.3775590658187866,
      "learning_rate": 6.746031746031746e-06,
      "loss": 0.0039,
      "step": 2460
    },
    {
      "epoch": 8.79786286731968,
      "grad_norm": 3.002919912338257,
      "learning_rate": 6.547619047619048e-06,
      "loss": 0.0047,
      "step": 2470
    },
    {
      "epoch": 8.833481745325022,
      "grad_norm": 2.3306655883789062,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.0066,
      "step": 2480
    },
    {
      "epoch": 8.869100623330365,
      "grad_norm": 0.08028317987918854,
      "learning_rate": 6.1507936507936505e-06,
      "loss": 0.0035,
      "step": 2490
    },
    {
      "epoch": 8.904719501335707,
      "grad_norm": 1.2194794416427612,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 0.0045,
      "step": 2500
    },
    {
      "epoch": 8.940338379341052,
      "grad_norm": 1.457444429397583,
      "learning_rate": 5.753968253968254e-06,
      "loss": 0.0042,
      "step": 2510
    },
    {
      "epoch": 8.975957257346394,
      "grad_norm": 1.0034886598587036,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0012,
      "step": 2520
    },
    {
      "epoch": 8.9973285841496,
      "eval_accuracy": 0.988810955243821,
      "eval_loss": 0.04604629799723625,
      "eval_runtime": 167.0665,
      "eval_samples_per_second": 107.526,
      "eval_steps_per_second": 1.682,
      "step": 2526
    },
    {
      "epoch": 9.011576135351737,
      "grad_norm": 0.16471421718597412,
      "learning_rate": 5.357142857142857e-06,
      "loss": 0.0059,
      "step": 2530
    },
    {
      "epoch": 9.04719501335708,
      "grad_norm": 0.5944855213165283,
      "learning_rate": 5.158730158730159e-06,
      "loss": 0.0068,
      "step": 2540
    },
    {
      "epoch": 9.082813891362422,
      "grad_norm": 1.3986272811889648,
      "learning_rate": 4.96031746031746e-06,
      "loss": 0.0023,
      "step": 2550
    },
    {
      "epoch": 9.118432769367764,
      "grad_norm": 0.8911547660827637,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.0023,
      "step": 2560
    },
    {
      "epoch": 9.154051647373107,
      "grad_norm": 2.983407735824585,
      "learning_rate": 4.563492063492064e-06,
      "loss": 0.0039,
      "step": 2570
    },
    {
      "epoch": 9.189670525378451,
      "grad_norm": 0.6036033630371094,
      "learning_rate": 4.365079365079365e-06,
      "loss": 0.0065,
      "step": 2580
    },
    {
      "epoch": 9.225289403383794,
      "grad_norm": 9.958078384399414,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.0073,
      "step": 2590
    },
    {
      "epoch": 9.260908281389137,
      "grad_norm": 0.27652016282081604,
      "learning_rate": 3.968253968253968e-06,
      "loss": 0.003,
      "step": 2600
    },
    {
      "epoch": 9.29652715939448,
      "grad_norm": 0.2213822901248932,
      "learning_rate": 3.7698412698412697e-06,
      "loss": 0.0015,
      "step": 2610
    },
    {
      "epoch": 9.332146037399822,
      "grad_norm": 0.18189971148967743,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 0.0019,
      "step": 2620
    },
    {
      "epoch": 9.367764915405164,
      "grad_norm": 0.05522046610713005,
      "learning_rate": 3.373015873015873e-06,
      "loss": 0.001,
      "step": 2630
    },
    {
      "epoch": 9.403383793410507,
      "grad_norm": 2.0256989002227783,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.0069,
      "step": 2640
    },
    {
      "epoch": 9.439002671415851,
      "grad_norm": 3.011732339859009,
      "learning_rate": 2.9761904761904763e-06,
      "loss": 0.0042,
      "step": 2650
    },
    {
      "epoch": 9.474621549421194,
      "grad_norm": 0.815857470035553,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.0021,
      "step": 2660
    },
    {
      "epoch": 9.510240427426536,
      "grad_norm": 1.9958930015563965,
      "learning_rate": 2.5793650793650795e-06,
      "loss": 0.0008,
      "step": 2670
    },
    {
      "epoch": 9.545859305431879,
      "grad_norm": 0.05693604424595833,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 0.0028,
      "step": 2680
    },
    {
      "epoch": 9.581478183437222,
      "grad_norm": 4.779353618621826,
      "learning_rate": 2.1825396825396824e-06,
      "loss": 0.0071,
      "step": 2690
    },
    {
      "epoch": 9.617097061442564,
      "grad_norm": 0.09340893477201462,
      "learning_rate": 1.984126984126984e-06,
      "loss": 0.0029,
      "step": 2700
    },
    {
      "epoch": 9.652715939447907,
      "grad_norm": 1.627168893814087,
      "learning_rate": 1.7857142857142857e-06,
      "loss": 0.0038,
      "step": 2710
    },
    {
      "epoch": 9.68833481745325,
      "grad_norm": 0.4794100224971771,
      "learning_rate": 1.5873015873015873e-06,
      "loss": 0.0033,
      "step": 2720
    },
    {
      "epoch": 9.723953695458594,
      "grad_norm": 0.7291146516799927,
      "learning_rate": 1.388888888888889e-06,
      "loss": 0.0024,
      "step": 2730
    },
    {
      "epoch": 9.759572573463936,
      "grad_norm": 0.5635161399841309,
      "learning_rate": 1.1904761904761904e-06,
      "loss": 0.0009,
      "step": 2740
    },
    {
      "epoch": 9.795191451469279,
      "grad_norm": 0.027575811371207237,
      "learning_rate": 9.92063492063492e-07,
      "loss": 0.0015,
      "step": 2750
    },
    {
      "epoch": 9.830810329474621,
      "grad_norm": 0.4068202078342438,
      "learning_rate": 7.936507936507937e-07,
      "loss": 0.0019,
      "step": 2760
    },
    {
      "epoch": 9.866429207479964,
      "grad_norm": 0.08091460168361664,
      "learning_rate": 5.952380952380952e-07,
      "loss": 0.0021,
      "step": 2770
    },
    {
      "epoch": 9.902048085485307,
      "grad_norm": 0.043514594435691833,
      "learning_rate": 3.9682539682539683e-07,
      "loss": 0.005,
      "step": 2780
    },
    {
      "epoch": 9.93766696349065,
      "grad_norm": 0.17870892584323883,
      "learning_rate": 1.9841269841269841e-07,
      "loss": 0.0024,
      "step": 2790
    },
    {
      "epoch": 9.973285841495994,
      "grad_norm": 0.13601838052272797,
      "learning_rate": 0.0,
      "loss": 0.0017,
      "step": 2800
    },
    {
      "epoch": 9.973285841495994,
      "eval_accuracy": 0.9900356268091739,
      "eval_loss": 0.04398982226848602,
      "eval_runtime": 167.3655,
      "eval_samples_per_second": 107.334,
      "eval_steps_per_second": 1.679,
      "step": 2800
    },
    {
      "epoch": 9.973285841495994,
      "step": 2800,
      "total_flos": 1.7813294264095949e+19,
      "train_loss": 0.08161249804892577,
      "train_runtime": 11582.5203,
      "train_samples_per_second": 62.035,
      "train_steps_per_second": 0.242
    }
  ],
  "logging_steps": 10,
  "max_steps": 2800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7813294264095949e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}