{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23906356801093642,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008544087491455912,
      "grad_norm": 11.00854206085205,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 2.4425,
      "step": 10
    },
    {
      "epoch": 0.0017088174982911825,
      "grad_norm": 4.686764240264893,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 2.1093,
      "step": 20
    },
    {
      "epoch": 0.002563226247436774,
      "grad_norm": 2.6529407501220703,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.7471,
      "step": 30
    },
    {
      "epoch": 0.003417634996582365,
      "grad_norm": 1.363114356994629,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.4501,
      "step": 40
    },
    {
      "epoch": 0.0042720437457279565,
      "grad_norm": 1.054634690284729,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 1.205,
      "step": 50
    },
    {
      "epoch": 0.005126452494873548,
      "grad_norm": 0.7446718215942383,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 1.092,
      "step": 60
    },
    {
      "epoch": 0.005980861244019139,
      "grad_norm": 0.7012097835540771,
      "learning_rate": 7.814044943820226e-06,
      "loss": 1.0106,
      "step": 70
    },
    {
      "epoch": 0.00683526999316473,
      "grad_norm": 0.6184213757514954,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.9755,
      "step": 80
    },
    {
      "epoch": 0.007689678742310321,
      "grad_norm": 0.6211470365524292,
      "learning_rate": 1.005e-05,
      "loss": 1.0031,
      "step": 90
    },
    {
      "epoch": 0.008544087491455913,
      "grad_norm": 1.4690356254577637,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.9412,
      "step": 100
    },
    {
      "epoch": 0.009398496240601503,
      "grad_norm": 0.6179498434066772,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.9378,
      "step": 110
    },
    {
      "epoch": 0.010252904989747095,
      "grad_norm": 0.651823103427887,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.9391,
      "step": 120
    },
    {
      "epoch": 0.011107313738892685,
      "grad_norm": 0.6029787063598633,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.9291,
      "step": 130
    },
    {
      "epoch": 0.011961722488038277,
      "grad_norm": 0.5876877307891846,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.9231,
      "step": 140
    },
    {
      "epoch": 0.01281613123718387,
      "grad_norm": 0.5466436147689819,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.9285,
      "step": 150
    },
    {
      "epoch": 0.01367053998632946,
      "grad_norm": 0.5822666883468628,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.9159,
      "step": 160
    },
    {
      "epoch": 0.014524948735475052,
      "grad_norm": 0.5883556604385376,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.911,
      "step": 170
    },
    {
      "epoch": 0.015379357484620642,
      "grad_norm": 0.6157915592193604,
      "learning_rate": 2e-05,
      "loss": 0.8931,
      "step": 180
    },
    {
      "epoch": 0.016233766233766232,
      "grad_norm": 0.64449143409729,
      "learning_rate": 2e-05,
      "loss": 0.9024,
      "step": 190
    },
    {
      "epoch": 0.017088174982911826,
      "grad_norm": 0.5318751931190491,
      "learning_rate": 2e-05,
      "loss": 0.9074,
      "step": 200
    },
    {
      "epoch": 0.017942583732057416,
      "grad_norm": 0.5434000492095947,
      "learning_rate": 2e-05,
      "loss": 0.8958,
      "step": 210
    },
    {
      "epoch": 0.018796992481203006,
      "grad_norm": 0.5382893681526184,
      "learning_rate": 2e-05,
      "loss": 0.8747,
      "step": 220
    },
    {
      "epoch": 0.0196514012303486,
      "grad_norm": 0.5032609701156616,
      "learning_rate": 2e-05,
      "loss": 0.8862,
      "step": 230
    },
    {
      "epoch": 0.02050580997949419,
      "grad_norm": 0.543346643447876,
      "learning_rate": 2e-05,
      "loss": 0.8872,
      "step": 240
    },
    {
      "epoch": 0.02136021872863978,
      "grad_norm": 0.527274489402771,
      "learning_rate": 2e-05,
      "loss": 0.8818,
      "step": 250
    },
    {
      "epoch": 0.02221462747778537,
      "grad_norm": 0.5765458345413208,
      "learning_rate": 2e-05,
      "loss": 0.8687,
      "step": 260
    },
    {
      "epoch": 0.023069036226930965,
      "grad_norm": 0.5382829904556274,
      "learning_rate": 2e-05,
      "loss": 0.8915,
      "step": 270
    },
    {
      "epoch": 0.023923444976076555,
      "grad_norm": 0.5533940196037292,
      "learning_rate": 2e-05,
      "loss": 0.8891,
      "step": 280
    },
    {
      "epoch": 0.024777853725222145,
      "grad_norm": 0.5417444705963135,
      "learning_rate": 2e-05,
      "loss": 0.8847,
      "step": 290
    },
    {
      "epoch": 0.02563226247436774,
      "grad_norm": 0.5582782626152039,
      "learning_rate": 2e-05,
      "loss": 0.9424,
      "step": 300
    },
    {
      "epoch": 0.02648667122351333,
      "grad_norm": 0.5055362582206726,
      "learning_rate": 2e-05,
      "loss": 0.8781,
      "step": 310
    },
    {
      "epoch": 0.02734107997265892,
      "grad_norm": 0.5508922934532166,
      "learning_rate": 2e-05,
      "loss": 0.8775,
      "step": 320
    },
    {
      "epoch": 0.02819548872180451,
      "grad_norm": 0.5282697677612305,
      "learning_rate": 2e-05,
      "loss": 0.8627,
      "step": 330
    },
    {
      "epoch": 0.029049897470950103,
      "grad_norm": 0.5219830870628357,
      "learning_rate": 2e-05,
      "loss": 0.8577,
      "step": 340
    },
    {
      "epoch": 0.029904306220095694,
      "grad_norm": 0.5210185050964355,
      "learning_rate": 2e-05,
      "loss": 0.9101,
      "step": 350
    },
    {
      "epoch": 0.030758714969241284,
      "grad_norm": 0.5474709272384644,
      "learning_rate": 2e-05,
      "loss": 0.8914,
      "step": 360
    },
    {
      "epoch": 0.03161312371838688,
      "grad_norm": 0.5275512337684631,
      "learning_rate": 2e-05,
      "loss": 0.879,
      "step": 370
    },
    {
      "epoch": 0.032467532467532464,
      "grad_norm": 0.5367026925086975,
      "learning_rate": 2e-05,
      "loss": 0.8771,
      "step": 380
    },
    {
      "epoch": 0.03332194121667806,
      "grad_norm": 0.5371636152267456,
      "learning_rate": 2e-05,
      "loss": 0.88,
      "step": 390
    },
    {
      "epoch": 0.03417634996582365,
      "grad_norm": 0.5706266760826111,
      "learning_rate": 2e-05,
      "loss": 0.8772,
      "step": 400
    },
    {
      "epoch": 0.03503075871496924,
      "grad_norm": 0.5139058232307434,
      "learning_rate": 2e-05,
      "loss": 0.8763,
      "step": 410
    },
    {
      "epoch": 0.03588516746411483,
      "grad_norm": 0.5124853849411011,
      "learning_rate": 2e-05,
      "loss": 0.8585,
      "step": 420
    },
    {
      "epoch": 0.036739576213260426,
      "grad_norm": 0.4997583329677582,
      "learning_rate": 2e-05,
      "loss": 0.8638,
      "step": 430
    },
    {
      "epoch": 0.03759398496240601,
      "grad_norm": 0.5006685853004456,
      "learning_rate": 2e-05,
      "loss": 0.8651,
      "step": 440
    },
    {
      "epoch": 0.03844839371155161,
      "grad_norm": 0.5022147297859192,
      "learning_rate": 2e-05,
      "loss": 0.856,
      "step": 450
    },
    {
      "epoch": 0.0393028024606972,
      "grad_norm": 0.5060321688652039,
      "learning_rate": 2e-05,
      "loss": 0.8772,
      "step": 460
    },
    {
      "epoch": 0.04015721120984279,
      "grad_norm": 0.5752074718475342,
      "learning_rate": 2e-05,
      "loss": 0.8583,
      "step": 470
    },
    {
      "epoch": 0.04101161995898838,
      "grad_norm": 0.5028130412101746,
      "learning_rate": 2e-05,
      "loss": 0.8486,
      "step": 480
    },
    {
      "epoch": 0.041866028708133975,
      "grad_norm": 0.46682220697402954,
      "learning_rate": 2e-05,
      "loss": 0.8486,
      "step": 490
    },
    {
      "epoch": 0.04272043745727956,
      "grad_norm": 0.4957294464111328,
      "learning_rate": 2e-05,
      "loss": 0.8593,
      "step": 500
    },
    {
      "epoch": 0.043574846206425155,
      "grad_norm": 0.5031411051750183,
      "learning_rate": 2e-05,
      "loss": 0.8823,
      "step": 510
    },
    {
      "epoch": 0.04442925495557074,
      "grad_norm": 0.572361171245575,
      "learning_rate": 2e-05,
      "loss": 0.8664,
      "step": 520
    },
    {
      "epoch": 0.045283663704716336,
      "grad_norm": 0.4737163484096527,
      "learning_rate": 2e-05,
      "loss": 0.8273,
      "step": 530
    },
    {
      "epoch": 0.04613807245386193,
      "grad_norm": 0.5212064981460571,
      "learning_rate": 2e-05,
      "loss": 0.8265,
      "step": 540
    },
    {
      "epoch": 0.046992481203007516,
      "grad_norm": 0.4948560297489166,
      "learning_rate": 2e-05,
      "loss": 0.8636,
      "step": 550
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 0.5002424716949463,
      "learning_rate": 2e-05,
      "loss": 0.8632,
      "step": 560
    },
    {
      "epoch": 0.048701298701298704,
      "grad_norm": 0.6509451270103455,
      "learning_rate": 2e-05,
      "loss": 0.8552,
      "step": 570
    },
    {
      "epoch": 0.04955570745044429,
      "grad_norm": 0.4619647264480591,
      "learning_rate": 2e-05,
      "loss": 0.852,
      "step": 580
    },
    {
      "epoch": 0.050410116199589884,
      "grad_norm": 0.5018244385719299,
      "learning_rate": 2e-05,
      "loss": 0.8336,
      "step": 590
    },
    {
      "epoch": 0.05126452494873548,
      "grad_norm": 0.47025132179260254,
      "learning_rate": 2e-05,
      "loss": 0.839,
      "step": 600
    },
    {
      "epoch": 0.052118933697881065,
      "grad_norm": 0.5157033801078796,
      "learning_rate": 2e-05,
      "loss": 0.8513,
      "step": 610
    },
    {
      "epoch": 0.05297334244702666,
      "grad_norm": 0.506414532661438,
      "learning_rate": 2e-05,
      "loss": 0.8433,
      "step": 620
    },
    {
      "epoch": 0.05382775119617225,
      "grad_norm": 0.48786959052085876,
      "learning_rate": 2e-05,
      "loss": 0.8747,
      "step": 630
    },
    {
      "epoch": 0.05468215994531784,
      "grad_norm": 0.4625915586948395,
      "learning_rate": 2e-05,
      "loss": 0.8321,
      "step": 640
    },
    {
      "epoch": 0.05553656869446343,
      "grad_norm": 0.49463289976119995,
      "learning_rate": 2e-05,
      "loss": 0.8449,
      "step": 650
    },
    {
      "epoch": 0.05639097744360902,
      "grad_norm": 0.47395265102386475,
      "learning_rate": 2e-05,
      "loss": 0.867,
      "step": 660
    },
    {
      "epoch": 0.05724538619275461,
      "grad_norm": 0.49984267354011536,
      "learning_rate": 2e-05,
      "loss": 0.8622,
      "step": 670
    },
    {
      "epoch": 0.05809979494190021,
      "grad_norm": 0.47769609093666077,
      "learning_rate": 2e-05,
      "loss": 0.8332,
      "step": 680
    },
    {
      "epoch": 0.058954203691045794,
      "grad_norm": 0.4874252676963806,
      "learning_rate": 2e-05,
      "loss": 0.8662,
      "step": 690
    },
    {
      "epoch": 0.05980861244019139,
      "grad_norm": 0.4563353955745697,
      "learning_rate": 2e-05,
      "loss": 0.848,
      "step": 700
    },
    {
      "epoch": 0.06066302118933698,
      "grad_norm": 0.461029589176178,
      "learning_rate": 2e-05,
      "loss": 0.8245,
      "step": 710
    },
    {
      "epoch": 0.06151742993848257,
      "grad_norm": 0.4584606885910034,
      "learning_rate": 2e-05,
      "loss": 0.8558,
      "step": 720
    },
    {
      "epoch": 0.06237183868762816,
      "grad_norm": 0.5101044774055481,
      "learning_rate": 2e-05,
      "loss": 0.8361,
      "step": 730
    },
    {
      "epoch": 0.06322624743677376,
      "grad_norm": 0.4820401668548584,
      "learning_rate": 2e-05,
      "loss": 0.8452,
      "step": 740
    },
    {
      "epoch": 0.06408065618591935,
      "grad_norm": 0.49986669421195984,
      "learning_rate": 2e-05,
      "loss": 0.8406,
      "step": 750
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 0.4644050598144531,
      "learning_rate": 2e-05,
      "loss": 0.7966,
      "step": 760
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 0.4689406752586365,
      "learning_rate": 2e-05,
      "loss": 0.8434,
      "step": 770
    },
    {
      "epoch": 0.06664388243335612,
      "grad_norm": 0.4809776544570923,
      "learning_rate": 2e-05,
      "loss": 0.8433,
      "step": 780
    },
    {
      "epoch": 0.06749829118250171,
      "grad_norm": 0.4512708783149719,
      "learning_rate": 2e-05,
      "loss": 0.8581,
      "step": 790
    },
    {
      "epoch": 0.0683526999316473,
      "grad_norm": 0.45067834854125977,
      "learning_rate": 2e-05,
      "loss": 0.8289,
      "step": 800
    },
    {
      "epoch": 0.0692071086807929,
      "grad_norm": 0.45861950516700745,
      "learning_rate": 2e-05,
      "loss": 0.8213,
      "step": 810
    },
    {
      "epoch": 0.07006151742993848,
      "grad_norm": 0.8090688586235046,
      "learning_rate": 2e-05,
      "loss": 0.8438,
      "step": 820
    },
    {
      "epoch": 0.07091592617908407,
      "grad_norm": 0.47155073285102844,
      "learning_rate": 2e-05,
      "loss": 0.816,
      "step": 830
    },
    {
      "epoch": 0.07177033492822966,
      "grad_norm": 0.494607150554657,
      "learning_rate": 2e-05,
      "loss": 0.8342,
      "step": 840
    },
    {
      "epoch": 0.07262474367737526,
      "grad_norm": 0.4732503592967987,
      "learning_rate": 2e-05,
      "loss": 0.8551,
      "step": 850
    },
    {
      "epoch": 0.07347915242652085,
      "grad_norm": 0.45871812105178833,
      "learning_rate": 2e-05,
      "loss": 0.8466,
      "step": 860
    },
    {
      "epoch": 0.07433356117566643,
      "grad_norm": 0.4696637690067291,
      "learning_rate": 2e-05,
      "loss": 0.8548,
      "step": 870
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 0.49322789907455444,
      "learning_rate": 2e-05,
      "loss": 0.8635,
      "step": 880
    },
    {
      "epoch": 0.07604237867395762,
      "grad_norm": 0.4646133780479431,
      "learning_rate": 2e-05,
      "loss": 0.8431,
      "step": 890
    },
    {
      "epoch": 0.07689678742310321,
      "grad_norm": 0.4524765908718109,
      "learning_rate": 2e-05,
      "loss": 0.8164,
      "step": 900
    },
    {
      "epoch": 0.07775119617224881,
      "grad_norm": 0.4888342022895813,
      "learning_rate": 2e-05,
      "loss": 0.8548,
      "step": 910
    },
    {
      "epoch": 0.0786056049213944,
      "grad_norm": 0.43915030360221863,
      "learning_rate": 2e-05,
      "loss": 0.812,
      "step": 920
    },
    {
      "epoch": 0.07946001367053998,
      "grad_norm": 0.4614696800708771,
      "learning_rate": 2e-05,
      "loss": 0.8156,
      "step": 930
    },
    {
      "epoch": 0.08031442241968557,
      "grad_norm": 0.46576476097106934,
      "learning_rate": 2e-05,
      "loss": 0.8391,
      "step": 940
    },
    {
      "epoch": 0.08116883116883117,
      "grad_norm": 0.44493210315704346,
      "learning_rate": 2e-05,
      "loss": 0.826,
      "step": 950
    },
    {
      "epoch": 0.08202323991797676,
      "grad_norm": 0.4456934928894043,
      "learning_rate": 2e-05,
      "loss": 0.8421,
      "step": 960
    },
    {
      "epoch": 0.08287764866712236,
      "grad_norm": 0.5433761477470398,
      "learning_rate": 2e-05,
      "loss": 0.87,
      "step": 970
    },
    {
      "epoch": 0.08373205741626795,
      "grad_norm": 0.4579722285270691,
      "learning_rate": 2e-05,
      "loss": 0.8216,
      "step": 980
    },
    {
      "epoch": 0.08458646616541353,
      "grad_norm": 0.452722430229187,
      "learning_rate": 2e-05,
      "loss": 0.8337,
      "step": 990
    },
    {
      "epoch": 0.08544087491455912,
      "grad_norm": 0.431753545999527,
      "learning_rate": 2e-05,
      "loss": 0.8508,
      "step": 1000
    },
    {
      "epoch": 0.08629528366370472,
      "grad_norm": 0.5925270915031433,
      "learning_rate": 2e-05,
      "loss": 0.8105,
      "step": 1010
    },
    {
      "epoch": 0.08714969241285031,
      "grad_norm": 0.44082966446876526,
      "learning_rate": 2e-05,
      "loss": 0.8191,
      "step": 1020
    },
    {
      "epoch": 0.0880041011619959,
      "grad_norm": 0.47487062215805054,
      "learning_rate": 2e-05,
      "loss": 0.8214,
      "step": 1030
    },
    {
      "epoch": 0.08885850991114148,
      "grad_norm": 0.49121612310409546,
      "learning_rate": 2e-05,
      "loss": 0.8482,
      "step": 1040
    },
    {
      "epoch": 0.08971291866028708,
      "grad_norm": 0.45580044388771057,
      "learning_rate": 2e-05,
      "loss": 0.8376,
      "step": 1050
    },
    {
      "epoch": 0.09056732740943267,
      "grad_norm": 0.4568115174770355,
      "learning_rate": 2e-05,
      "loss": 0.8573,
      "step": 1060
    },
    {
      "epoch": 0.09142173615857827,
      "grad_norm": 0.4428640604019165,
      "learning_rate": 2e-05,
      "loss": 0.8159,
      "step": 1070
    },
    {
      "epoch": 0.09227614490772386,
      "grad_norm": 0.4813441038131714,
      "learning_rate": 2e-05,
      "loss": 0.8493,
      "step": 1080
    },
    {
      "epoch": 0.09313055365686945,
      "grad_norm": 0.4206986129283905,
      "learning_rate": 2e-05,
      "loss": 0.8088,
      "step": 1090
    },
    {
      "epoch": 0.09398496240601503,
      "grad_norm": 0.49628499150276184,
      "learning_rate": 2e-05,
      "loss": 0.815,
      "step": 1100
    },
    {
      "epoch": 0.09483937115516063,
      "grad_norm": 0.4241103529930115,
      "learning_rate": 2e-05,
      "loss": 0.8077,
      "step": 1110
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 0.4558090567588806,
      "learning_rate": 2e-05,
      "loss": 0.8052,
      "step": 1120
    },
    {
      "epoch": 0.09654818865345181,
      "grad_norm": 0.4508516192436218,
      "learning_rate": 2e-05,
      "loss": 0.82,
      "step": 1130
    },
    {
      "epoch": 0.09740259740259741,
      "grad_norm": 0.4674357771873474,
      "learning_rate": 2e-05,
      "loss": 0.814,
      "step": 1140
    },
    {
      "epoch": 0.09825700615174299,
      "grad_norm": 0.46306923031806946,
      "learning_rate": 2e-05,
      "loss": 0.8521,
      "step": 1150
    },
    {
      "epoch": 0.09911141490088858,
      "grad_norm": 0.43954190611839294,
      "learning_rate": 2e-05,
      "loss": 0.813,
      "step": 1160
    },
    {
      "epoch": 0.09996582365003417,
      "grad_norm": 0.4370790421962738,
      "learning_rate": 2e-05,
      "loss": 0.8143,
      "step": 1170
    },
    {
      "epoch": 0.10082023239917977,
      "grad_norm": 0.4371121823787689,
      "learning_rate": 2e-05,
      "loss": 0.836,
      "step": 1180
    },
    {
      "epoch": 0.10167464114832536,
      "grad_norm": 0.45741012692451477,
      "learning_rate": 2e-05,
      "loss": 0.83,
      "step": 1190
    },
    {
      "epoch": 0.10252904989747096,
      "grad_norm": 0.4397066831588745,
      "learning_rate": 2e-05,
      "loss": 0.8045,
      "step": 1200
    },
    {
      "epoch": 0.10338345864661654,
      "grad_norm": 0.45700281858444214,
      "learning_rate": 2e-05,
      "loss": 0.812,
      "step": 1210
    },
    {
      "epoch": 0.10423786739576213,
      "grad_norm": 0.4776708781719208,
      "learning_rate": 2e-05,
      "loss": 0.8301,
      "step": 1220
    },
    {
      "epoch": 0.10509227614490772,
      "grad_norm": 0.4925238788127899,
      "learning_rate": 2e-05,
      "loss": 0.806,
      "step": 1230
    },
    {
      "epoch": 0.10594668489405332,
      "grad_norm": 0.4427919089794159,
      "learning_rate": 2e-05,
      "loss": 0.8161,
      "step": 1240
    },
    {
      "epoch": 0.10680109364319891,
      "grad_norm": 0.45902568101882935,
      "learning_rate": 2e-05,
      "loss": 0.8254,
      "step": 1250
    },
    {
      "epoch": 0.1076555023923445,
      "grad_norm": 0.4676574468612671,
      "learning_rate": 2e-05,
      "loss": 0.8269,
      "step": 1260
    },
    {
      "epoch": 0.10850991114149008,
      "grad_norm": 0.443413645029068,
      "learning_rate": 2e-05,
      "loss": 0.8188,
      "step": 1270
    },
    {
      "epoch": 0.10936431989063568,
      "grad_norm": 0.43236881494522095,
      "learning_rate": 2e-05,
      "loss": 0.8103,
      "step": 1280
    },
    {
      "epoch": 0.11021872863978127,
      "grad_norm": 0.4279523193836212,
      "learning_rate": 2e-05,
      "loss": 0.7924,
      "step": 1290
    },
    {
      "epoch": 0.11107313738892687,
      "grad_norm": 0.4617557227611542,
      "learning_rate": 2e-05,
      "loss": 0.825,
      "step": 1300
    },
    {
      "epoch": 0.11192754613807246,
      "grad_norm": 0.4349711537361145,
      "learning_rate": 2e-05,
      "loss": 0.8275,
      "step": 1310
    },
    {
      "epoch": 0.11278195488721804,
      "grad_norm": 0.46123847365379333,
      "learning_rate": 2e-05,
      "loss": 0.808,
      "step": 1320
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.46817174553871155,
      "learning_rate": 2e-05,
      "loss": 0.8134,
      "step": 1330
    },
    {
      "epoch": 0.11449077238550923,
      "grad_norm": 0.43027958273887634,
      "learning_rate": 2e-05,
      "loss": 0.8239,
      "step": 1340
    },
    {
      "epoch": 0.11534518113465482,
      "grad_norm": 0.4255163371562958,
      "learning_rate": 2e-05,
      "loss": 0.8354,
      "step": 1350
    },
    {
      "epoch": 0.11619958988380041,
      "grad_norm": 0.42436283826828003,
      "learning_rate": 2e-05,
      "loss": 0.8334,
      "step": 1360
    },
    {
      "epoch": 0.11705399863294601,
      "grad_norm": 0.41989049315452576,
      "learning_rate": 2e-05,
      "loss": 0.8014,
      "step": 1370
    },
    {
      "epoch": 0.11790840738209159,
      "grad_norm": 0.4478135406970978,
      "learning_rate": 2e-05,
      "loss": 0.8041,
      "step": 1380
    },
    {
      "epoch": 0.11876281613123718,
      "grad_norm": 0.45139527320861816,
      "learning_rate": 2e-05,
      "loss": 0.7863,
      "step": 1390
    },
    {
      "epoch": 0.11961722488038277,
      "grad_norm": 0.5576887726783752,
      "learning_rate": 2e-05,
      "loss": 0.8462,
      "step": 1400
    },
    {
      "epoch": 0.12047163362952837,
      "grad_norm": 0.5432232618331909,
      "learning_rate": 2e-05,
      "loss": 0.8301,
      "step": 1410
    },
    {
      "epoch": 0.12132604237867396,
      "grad_norm": 0.4304180145263672,
      "learning_rate": 2e-05,
      "loss": 0.8182,
      "step": 1420
    },
    {
      "epoch": 0.12218045112781954,
      "grad_norm": 0.4250909388065338,
      "learning_rate": 2e-05,
      "loss": 0.7976,
      "step": 1430
    },
    {
      "epoch": 0.12303485987696514,
      "grad_norm": 0.4376416802406311,
      "learning_rate": 2e-05,
      "loss": 0.8251,
      "step": 1440
    },
    {
      "epoch": 0.12388926862611073,
      "grad_norm": 0.5384215712547302,
      "learning_rate": 2e-05,
      "loss": 0.8283,
      "step": 1450
    },
    {
      "epoch": 0.12474367737525632,
      "grad_norm": 0.44483479857444763,
      "learning_rate": 2e-05,
      "loss": 0.82,
      "step": 1460
    },
    {
      "epoch": 0.1255980861244019,
      "grad_norm": 0.4774000942707062,
      "learning_rate": 2e-05,
      "loss": 0.8185,
      "step": 1470
    },
    {
      "epoch": 0.1264524948735475,
      "grad_norm": 0.45032012462615967,
      "learning_rate": 2e-05,
      "loss": 0.8084,
      "step": 1480
    },
    {
      "epoch": 0.1273069036226931,
      "grad_norm": 0.43089014291763306,
      "learning_rate": 2e-05,
      "loss": 0.8098,
      "step": 1490
    },
    {
      "epoch": 0.1281613123718387,
      "grad_norm": 0.44045063853263855,
      "learning_rate": 2e-05,
      "loss": 0.802,
      "step": 1500
    },
    {
      "epoch": 0.12901572112098428,
      "grad_norm": 0.441500723361969,
      "learning_rate": 2e-05,
      "loss": 0.8227,
      "step": 1510
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.43266189098358154,
      "learning_rate": 2e-05,
      "loss": 0.814,
      "step": 1520
    },
    {
      "epoch": 0.13072453861927547,
      "grad_norm": 0.4659614562988281,
      "learning_rate": 2e-05,
      "loss": 0.8303,
      "step": 1530
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.42092642188072205,
      "learning_rate": 2e-05,
      "loss": 0.8176,
      "step": 1540
    },
    {
      "epoch": 0.13243335611756665,
      "grad_norm": 0.44579121470451355,
      "learning_rate": 2e-05,
      "loss": 0.7871,
      "step": 1550
    },
    {
      "epoch": 0.13328776486671223,
      "grad_norm": 0.6033672094345093,
      "learning_rate": 2e-05,
      "loss": 0.8148,
      "step": 1560
    },
    {
      "epoch": 0.1341421736158578,
      "grad_norm": 0.44670525193214417,
      "learning_rate": 2e-05,
      "loss": 0.7947,
      "step": 1570
    },
    {
      "epoch": 0.13499658236500342,
      "grad_norm": 0.45696425437927246,
      "learning_rate": 2e-05,
      "loss": 0.8021,
      "step": 1580
    },
    {
      "epoch": 0.135850991114149,
      "grad_norm": 0.4262278079986572,
      "learning_rate": 2e-05,
      "loss": 0.7942,
      "step": 1590
    },
    {
      "epoch": 0.1367053998632946,
      "grad_norm": 0.4282379746437073,
      "learning_rate": 2e-05,
      "loss": 0.8398,
      "step": 1600
    },
    {
      "epoch": 0.1375598086124402,
      "grad_norm": 0.4352816343307495,
      "learning_rate": 2e-05,
      "loss": 0.7778,
      "step": 1610
    },
    {
      "epoch": 0.1384142173615858,
      "grad_norm": 0.44685494899749756,
      "learning_rate": 2e-05,
      "loss": 0.788,
      "step": 1620
    },
    {
      "epoch": 0.13926862611073137,
      "grad_norm": 0.43920254707336426,
      "learning_rate": 2e-05,
      "loss": 0.8238,
      "step": 1630
    },
    {
      "epoch": 0.14012303485987695,
      "grad_norm": 0.4376579821109772,
      "learning_rate": 2e-05,
      "loss": 0.8061,
      "step": 1640
    },
    {
      "epoch": 0.14097744360902256,
      "grad_norm": 0.43427619338035583,
      "learning_rate": 2e-05,
      "loss": 0.7982,
      "step": 1650
    },
    {
      "epoch": 0.14183185235816814,
      "grad_norm": 0.478322833776474,
      "learning_rate": 2e-05,
      "loss": 0.8192,
      "step": 1660
    },
    {
      "epoch": 0.14268626110731375,
      "grad_norm": 0.43004366755485535,
      "learning_rate": 2e-05,
      "loss": 0.8136,
      "step": 1670
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 0.45207637548446655,
      "learning_rate": 2e-05,
      "loss": 0.8166,
      "step": 1680
    },
    {
      "epoch": 0.1443950786056049,
      "grad_norm": 0.4198301434516907,
      "learning_rate": 2e-05,
      "loss": 0.8011,
      "step": 1690
    },
    {
      "epoch": 0.14524948735475052,
      "grad_norm": 0.4201711118221283,
      "learning_rate": 2e-05,
      "loss": 0.7908,
      "step": 1700
    },
    {
      "epoch": 0.1461038961038961,
      "grad_norm": 0.4392196536064148,
      "learning_rate": 2e-05,
      "loss": 0.7841,
      "step": 1710
    },
    {
      "epoch": 0.1469583048530417,
      "grad_norm": 0.43777990341186523,
      "learning_rate": 2e-05,
      "loss": 0.7922,
      "step": 1720
    },
    {
      "epoch": 0.14781271360218728,
      "grad_norm": 0.41786715388298035,
      "learning_rate": 2e-05,
      "loss": 0.8177,
      "step": 1730
    },
    {
      "epoch": 0.14866712235133286,
      "grad_norm": 0.45031750202178955,
      "learning_rate": 2e-05,
      "loss": 0.7949,
      "step": 1740
    },
    {
      "epoch": 0.14952153110047847,
      "grad_norm": 0.4286364018917084,
      "learning_rate": 2e-05,
      "loss": 0.7885,
      "step": 1750
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.4539773166179657,
      "learning_rate": 2e-05,
      "loss": 0.8298,
      "step": 1760
    },
    {
      "epoch": 0.15123034859876966,
      "grad_norm": 0.41946274042129517,
      "learning_rate": 2e-05,
      "loss": 0.8042,
      "step": 1770
    },
    {
      "epoch": 0.15208475734791524,
      "grad_norm": 0.44184574484825134,
      "learning_rate": 2e-05,
      "loss": 0.8141,
      "step": 1780
    },
    {
      "epoch": 0.15293916609706085,
      "grad_norm": 0.453799843788147,
      "learning_rate": 2e-05,
      "loss": 0.8356,
      "step": 1790
    },
    {
      "epoch": 0.15379357484620643,
      "grad_norm": 0.46639925241470337,
      "learning_rate": 2e-05,
      "loss": 0.7995,
      "step": 1800
    },
    {
      "epoch": 0.154647983595352,
      "grad_norm": 0.42801088094711304,
      "learning_rate": 2e-05,
      "loss": 0.7778,
      "step": 1810
    },
    {
      "epoch": 0.15550239234449761,
      "grad_norm": 0.4495405852794647,
      "learning_rate": 2e-05,
      "loss": 0.799,
      "step": 1820
    },
    {
      "epoch": 0.1563568010936432,
      "grad_norm": 0.4354593753814697,
      "learning_rate": 2e-05,
      "loss": 0.8257,
      "step": 1830
    },
    {
      "epoch": 0.1572112098427888,
      "grad_norm": 0.4067724347114563,
      "learning_rate": 2e-05,
      "loss": 0.7885,
      "step": 1840
    },
    {
      "epoch": 0.15806561859193438,
      "grad_norm": 0.4517872631549835,
      "learning_rate": 2e-05,
      "loss": 0.779,
      "step": 1850
    },
    {
      "epoch": 0.15892002734107996,
      "grad_norm": 0.4226350784301758,
      "learning_rate": 2e-05,
      "loss": 0.7816,
      "step": 1860
    },
    {
      "epoch": 0.15977443609022557,
      "grad_norm": 0.43251317739486694,
      "learning_rate": 2e-05,
      "loss": 0.7999,
      "step": 1870
    },
    {
      "epoch": 0.16062884483937115,
      "grad_norm": 0.4463696777820587,
      "learning_rate": 2e-05,
      "loss": 0.816,
      "step": 1880
    },
    {
      "epoch": 0.16148325358851676,
      "grad_norm": 0.41246628761291504,
      "learning_rate": 2e-05,
      "loss": 0.7909,
      "step": 1890
    },
    {
      "epoch": 0.16233766233766234,
      "grad_norm": 0.4619990885257721,
      "learning_rate": 2e-05,
      "loss": 0.794,
      "step": 1900
    },
    {
      "epoch": 0.16319207108680792,
      "grad_norm": 0.6987309455871582,
      "learning_rate": 2e-05,
      "loss": 0.8339,
      "step": 1910
    },
    {
      "epoch": 0.16404647983595352,
      "grad_norm": 0.4621772766113281,
      "learning_rate": 2e-05,
      "loss": 0.8005,
      "step": 1920
    },
    {
      "epoch": 0.1649008885850991,
      "grad_norm": 0.4086742401123047,
      "learning_rate": 2e-05,
      "loss": 0.7964,
      "step": 1930
    },
    {
      "epoch": 0.1657552973342447,
      "grad_norm": 0.4323413670063019,
      "learning_rate": 2e-05,
      "loss": 0.7759,
      "step": 1940
    },
    {
      "epoch": 0.1666097060833903,
      "grad_norm": 0.4169401526451111,
      "learning_rate": 2e-05,
      "loss": 0.7965,
      "step": 1950
    },
    {
      "epoch": 0.1674641148325359,
      "grad_norm": 0.44284898042678833,
      "learning_rate": 2e-05,
      "loss": 0.8008,
      "step": 1960
    },
    {
      "epoch": 0.16831852358168148,
      "grad_norm": 0.44360917806625366,
      "learning_rate": 2e-05,
      "loss": 0.8244,
      "step": 1970
    },
    {
      "epoch": 0.16917293233082706,
      "grad_norm": 0.43291980028152466,
      "learning_rate": 2e-05,
      "loss": 0.7864,
      "step": 1980
    },
    {
      "epoch": 0.17002734107997267,
      "grad_norm": 0.43684226274490356,
      "learning_rate": 2e-05,
      "loss": 0.8172,
      "step": 1990
    },
    {
      "epoch": 0.17088174982911825,
      "grad_norm": 0.4126867651939392,
      "learning_rate": 2e-05,
      "loss": 0.7949,
      "step": 2000
    },
    {
      "epoch": 0.17173615857826385,
      "grad_norm": 0.4156489968299866,
      "learning_rate": 2e-05,
      "loss": 0.818,
      "step": 2010
    },
    {
      "epoch": 0.17259056732740943,
      "grad_norm": 0.4190804362297058,
      "learning_rate": 2e-05,
      "loss": 0.7805,
      "step": 2020
    },
    {
      "epoch": 0.173444976076555,
      "grad_norm": 0.4342236816883087,
      "learning_rate": 2e-05,
      "loss": 0.7805,
      "step": 2030
    },
    {
      "epoch": 0.17429938482570062,
      "grad_norm": 0.4375854730606079,
      "learning_rate": 2e-05,
      "loss": 0.8016,
      "step": 2040
    },
    {
      "epoch": 0.1751537935748462,
      "grad_norm": 0.43170157074928284,
      "learning_rate": 2e-05,
      "loss": 0.7991,
      "step": 2050
    },
    {
      "epoch": 0.1760082023239918,
      "grad_norm": 0.4225408136844635,
      "learning_rate": 2e-05,
      "loss": 0.8297,
      "step": 2060
    },
    {
      "epoch": 0.1768626110731374,
      "grad_norm": 0.4088500142097473,
      "learning_rate": 2e-05,
      "loss": 0.8231,
      "step": 2070
    },
    {
      "epoch": 0.17771701982228297,
      "grad_norm": 0.39183762669563293,
      "learning_rate": 2e-05,
      "loss": 0.7654,
      "step": 2080
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.4299352169036865,
      "learning_rate": 2e-05,
      "loss": 0.7944,
      "step": 2090
    },
    {
      "epoch": 0.17942583732057416,
      "grad_norm": 0.41311776638031006,
      "learning_rate": 2e-05,
      "loss": 0.8065,
      "step": 2100
    },
    {
      "epoch": 0.18028024606971976,
      "grad_norm": 0.4197043180465698,
      "learning_rate": 2e-05,
      "loss": 0.7967,
      "step": 2110
    },
    {
      "epoch": 0.18113465481886534,
      "grad_norm": 0.4080440104007721,
      "learning_rate": 2e-05,
      "loss": 0.7941,
      "step": 2120
    },
    {
      "epoch": 0.18198906356801095,
      "grad_norm": 0.4393218159675598,
      "learning_rate": 2e-05,
      "loss": 0.7926,
      "step": 2130
    },
    {
      "epoch": 0.18284347231715653,
      "grad_norm": 0.4172094464302063,
      "learning_rate": 2e-05,
      "loss": 0.7831,
      "step": 2140
    },
    {
      "epoch": 0.1836978810663021,
      "grad_norm": 0.4084227979183197,
      "learning_rate": 2e-05,
      "loss": 0.7879,
      "step": 2150
    },
    {
      "epoch": 0.18455228981544772,
      "grad_norm": 0.4330205023288727,
      "learning_rate": 2e-05,
      "loss": 0.7875,
      "step": 2160
    },
    {
      "epoch": 0.1854066985645933,
      "grad_norm": 0.3870986998081207,
      "learning_rate": 2e-05,
      "loss": 0.7813,
      "step": 2170
    },
    {
      "epoch": 0.1862611073137389,
      "grad_norm": 0.4238833785057068,
      "learning_rate": 2e-05,
      "loss": 0.7915,
      "step": 2180
    },
    {
      "epoch": 0.18711551606288448,
      "grad_norm": 0.4221448004245758,
      "learning_rate": 2e-05,
      "loss": 0.8056,
      "step": 2190
    },
    {
      "epoch": 0.18796992481203006,
      "grad_norm": 0.4315853416919708,
      "learning_rate": 2e-05,
      "loss": 0.7838,
      "step": 2200
    },
    {
      "epoch": 0.18882433356117567,
      "grad_norm": 0.4521797001361847,
      "learning_rate": 2e-05,
      "loss": 0.798,
      "step": 2210
    },
    {
      "epoch": 0.18967874231032125,
      "grad_norm": 0.42917776107788086,
      "learning_rate": 2e-05,
      "loss": 0.8113,
      "step": 2220
    },
    {
      "epoch": 0.19053315105946686,
      "grad_norm": 0.4716418385505676,
      "learning_rate": 2e-05,
      "loss": 0.8062,
      "step": 2230
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 0.4381401836872101,
      "learning_rate": 2e-05,
      "loss": 0.7671,
      "step": 2240
    },
    {
      "epoch": 0.19224196855775802,
      "grad_norm": 0.42370718717575073,
      "learning_rate": 2e-05,
      "loss": 0.7853,
      "step": 2250
    },
    {
      "epoch": 0.19309637730690363,
      "grad_norm": 0.4564455449581146,
      "learning_rate": 2e-05,
      "loss": 0.7809,
      "step": 2260
    },
    {
      "epoch": 0.1939507860560492,
      "grad_norm": 0.4647822976112366,
      "learning_rate": 2e-05,
      "loss": 0.8156,
      "step": 2270
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 0.43348145484924316,
      "learning_rate": 2e-05,
      "loss": 0.7993,
      "step": 2280
    },
    {
      "epoch": 0.1956596035543404,
      "grad_norm": 0.40158313512802124,
      "learning_rate": 2e-05,
      "loss": 0.7929,
      "step": 2290
    },
    {
      "epoch": 0.19651401230348597,
      "grad_norm": 0.43731987476348877,
      "learning_rate": 2e-05,
      "loss": 0.8001,
      "step": 2300
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 0.42699843645095825,
      "learning_rate": 2e-05,
      "loss": 0.7947,
      "step": 2310
    },
    {
      "epoch": 0.19822282980177716,
      "grad_norm": 0.4112282693386078,
      "learning_rate": 2e-05,
      "loss": 0.7848,
      "step": 2320
    },
    {
      "epoch": 0.19907723855092277,
      "grad_norm": 0.4258609116077423,
      "learning_rate": 2e-05,
      "loss": 0.7714,
      "step": 2330
    },
    {
      "epoch": 0.19993164730006835,
      "grad_norm": 0.41939055919647217,
      "learning_rate": 2e-05,
      "loss": 0.7786,
      "step": 2340
    },
    {
      "epoch": 0.20078605604921396,
      "grad_norm": 0.42235198616981506,
      "learning_rate": 2e-05,
      "loss": 0.8058,
      "step": 2350
    },
    {
      "epoch": 0.20164046479835954,
      "grad_norm": 0.4100799262523651,
      "learning_rate": 2e-05,
      "loss": 0.7895,
      "step": 2360
    },
    {
      "epoch": 0.20249487354750512,
      "grad_norm": 0.4226270020008087,
      "learning_rate": 2e-05,
      "loss": 0.8104,
      "step": 2370
    },
    {
      "epoch": 0.20334928229665072,
      "grad_norm": 0.41681861877441406,
      "learning_rate": 2e-05,
      "loss": 0.7823,
      "step": 2380
    },
    {
      "epoch": 0.2042036910457963,
      "grad_norm": 0.41445469856262207,
      "learning_rate": 2e-05,
      "loss": 0.7792,
      "step": 2390
    },
    {
      "epoch": 0.2050580997949419,
      "grad_norm": 0.4336954951286316,
      "learning_rate": 2e-05,
      "loss": 0.7979,
      "step": 2400
    },
    {
      "epoch": 0.2059125085440875,
      "grad_norm": 0.4223636984825134,
      "learning_rate": 2e-05,
      "loss": 0.8185,
      "step": 2410
    },
    {
      "epoch": 0.20676691729323307,
      "grad_norm": 0.4034973084926605,
      "learning_rate": 2e-05,
      "loss": 0.7982,
      "step": 2420
    },
    {
      "epoch": 0.20762132604237868,
      "grad_norm": 0.42055076360702515,
      "learning_rate": 2e-05,
      "loss": 0.7701,
      "step": 2430
    },
    {
      "epoch": 0.20847573479152426,
      "grad_norm": 0.4145602285861969,
      "learning_rate": 2e-05,
      "loss": 0.7973,
      "step": 2440
    },
    {
      "epoch": 0.20933014354066987,
      "grad_norm": 0.4494640827178955,
      "learning_rate": 2e-05,
      "loss": 0.7956,
      "step": 2450
    },
    {
      "epoch": 0.21018455228981545,
      "grad_norm": 0.4173319339752197,
      "learning_rate": 2e-05,
      "loss": 0.832,
      "step": 2460
    },
    {
      "epoch": 0.21103896103896103,
      "grad_norm": 0.4216117560863495,
      "learning_rate": 2e-05,
      "loss": 0.7925,
      "step": 2470
    },
    {
      "epoch": 0.21189336978810663,
      "grad_norm": 0.9099227786064148,
      "learning_rate": 2e-05,
      "loss": 0.811,
      "step": 2480
    },
    {
      "epoch": 0.2127477785372522,
      "grad_norm": 0.41247525811195374,
      "learning_rate": 2e-05,
      "loss": 0.7879,
      "step": 2490
    },
    {
      "epoch": 0.21360218728639782,
      "grad_norm": 0.40090277791023254,
      "learning_rate": 2e-05,
      "loss": 0.7759,
      "step": 2500
    },
    {
      "epoch": 0.2144565960355434,
      "grad_norm": 0.43528005480766296,
      "learning_rate": 2e-05,
      "loss": 0.742,
      "step": 2510
    },
    {
      "epoch": 0.215311004784689,
      "grad_norm": 0.40456560254096985,
      "learning_rate": 2e-05,
      "loss": 0.7851,
      "step": 2520
    },
    {
      "epoch": 0.2161654135338346,
      "grad_norm": 0.41995969414711,
      "learning_rate": 2e-05,
      "loss": 0.7725,
      "step": 2530
    },
    {
      "epoch": 0.21701982228298017,
      "grad_norm": 0.43686243891716003,
      "learning_rate": 2e-05,
      "loss": 0.7767,
      "step": 2540
    },
    {
      "epoch": 0.21787423103212578,
      "grad_norm": 0.4023416340351105,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.8399,
      "step": 2550
    },
    {
      "epoch": 0.21872863978127136,
      "grad_norm": 0.4311876893043518,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7955,
      "step": 2560
    },
    {
      "epoch": 0.21958304853041696,
      "grad_norm": 0.4159518778324127,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.7572,
      "step": 2570
    },
    {
      "epoch": 0.22043745727956254,
      "grad_norm": 0.4297788739204407,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7869,
      "step": 2580
    },
    {
      "epoch": 0.22129186602870812,
      "grad_norm": 0.4200313091278076,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.7765,
      "step": 2590
    },
    {
      "epoch": 0.22214627477785373,
      "grad_norm": 0.39208364486694336,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7778,
      "step": 2600
    },
    {
      "epoch": 0.2230006835269993,
      "grad_norm": 0.4059743583202362,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7991,
      "step": 2610
    },
    {
      "epoch": 0.22385509227614492,
      "grad_norm": 0.41379305720329285,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.7823,
      "step": 2620
    },
    {
      "epoch": 0.2247095010252905,
      "grad_norm": 0.4382677972316742,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.792,
      "step": 2630
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 0.43146514892578125,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.7753,
      "step": 2640
    },
    {
      "epoch": 0.22641831852358169,
      "grad_norm": 0.440703421831131,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7718,
      "step": 2650
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.40435701608657837,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.7975,
      "step": 2660
    },
    {
      "epoch": 0.22812713602187287,
      "grad_norm": 0.42384541034698486,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.8044,
      "step": 2670
    },
    {
      "epoch": 0.22898154477101845,
      "grad_norm": 0.4161738157272339,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.8068,
      "step": 2680
    },
    {
      "epoch": 0.22983595352016406,
      "grad_norm": 0.3990834653377533,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.7981,
      "step": 2690
    },
    {
      "epoch": 0.23069036226930964,
      "grad_norm": 0.3977971076965332,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.769,
      "step": 2700
    },
    {
      "epoch": 0.23154477101845522,
      "grad_norm": 0.4111315906047821,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.7569,
      "step": 2710
    },
    {
      "epoch": 0.23239917976760083,
      "grad_norm": 0.3821330666542053,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.786,
      "step": 2720
    },
    {
      "epoch": 0.2332535885167464,
      "grad_norm": 0.39468124508857727,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.7588,
      "step": 2730
    },
    {
      "epoch": 0.23410799726589201,
      "grad_norm": 0.39685073494911194,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.7568,
      "step": 2740
    },
    {
      "epoch": 0.2349624060150376,
      "grad_norm": 0.3943333327770233,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.761,
      "step": 2750
    },
    {
      "epoch": 0.23581681476418317,
      "grad_norm": 0.4170905649662018,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.777,
      "step": 2760
    },
    {
      "epoch": 0.23667122351332878,
      "grad_norm": 0.5196862816810608,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.7576,
      "step": 2770
    },
    {
      "epoch": 0.23752563226247436,
      "grad_norm": 0.3846542537212372,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.7622,
      "step": 2780
    },
    {
      "epoch": 0.23838004101161997,
      "grad_norm": 0.3985555171966553,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.7833,
      "step": 2790
    },
    {
      "epoch": 0.23906356801093642,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.07050594557516059,
      "train_runtime": 2287.0129,
      "train_samples_per_second": 14.681,
      "train_steps_per_second": 1.223
    }
  ],
  "logging_steps": 10,
  "max_steps": 2798,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 159,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1366756130249245e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}