{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.992903607332939,
  "eval_steps": 500,
  "global_step": 1688,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02365464222353637,
      "grad_norm": 2.022057166002628,
      "learning_rate": 5e-06,
      "loss": 0.888,
      "step": 10
    },
    {
      "epoch": 0.04730928444707274,
      "grad_norm": 4.2838438835520005,
      "learning_rate": 5e-06,
      "loss": 0.7936,
      "step": 20
    },
    {
      "epoch": 0.0709639266706091,
      "grad_norm": 5.767519526095153,
      "learning_rate": 5e-06,
      "loss": 0.7721,
      "step": 30
    },
    {
      "epoch": 0.09461856889414548,
      "grad_norm": 2.248924439813238,
      "learning_rate": 5e-06,
      "loss": 0.7537,
      "step": 40
    },
    {
      "epoch": 0.11827321111768184,
      "grad_norm": 1.2653464134086752,
      "learning_rate": 5e-06,
      "loss": 0.7355,
      "step": 50
    },
    {
      "epoch": 0.1419278533412182,
      "grad_norm": 0.9171723485495338,
      "learning_rate": 5e-06,
      "loss": 0.7205,
      "step": 60
    },
    {
      "epoch": 0.16558249556475457,
      "grad_norm": 0.5551007647195453,
      "learning_rate": 5e-06,
      "loss": 0.7141,
      "step": 70
    },
    {
      "epoch": 0.18923713778829096,
      "grad_norm": 0.6529142931017199,
      "learning_rate": 5e-06,
      "loss": 0.703,
      "step": 80
    },
    {
      "epoch": 0.21289178001182732,
      "grad_norm": 0.827144174510547,
      "learning_rate": 5e-06,
      "loss": 0.687,
      "step": 90
    },
    {
      "epoch": 0.23654642223536368,
      "grad_norm": 0.6269470648770907,
      "learning_rate": 5e-06,
      "loss": 0.6856,
      "step": 100
    },
    {
      "epoch": 0.26020106445890007,
      "grad_norm": 0.5434193508379527,
      "learning_rate": 5e-06,
      "loss": 0.6906,
      "step": 110
    },
    {
      "epoch": 0.2838557066824364,
      "grad_norm": 0.536059739065128,
      "learning_rate": 5e-06,
      "loss": 0.6776,
      "step": 120
    },
    {
      "epoch": 0.3075103489059728,
      "grad_norm": 0.5739273992748293,
      "learning_rate": 5e-06,
      "loss": 0.6737,
      "step": 130
    },
    {
      "epoch": 0.33116499112950915,
      "grad_norm": 0.6849912224993461,
      "learning_rate": 5e-06,
      "loss": 0.682,
      "step": 140
    },
    {
      "epoch": 0.35481963335304556,
      "grad_norm": 0.847605379720015,
      "learning_rate": 5e-06,
      "loss": 0.6647,
      "step": 150
    },
    {
      "epoch": 0.3784742755765819,
      "grad_norm": 0.4574232609702974,
      "learning_rate": 5e-06,
      "loss": 0.6693,
      "step": 160
    },
    {
      "epoch": 0.4021289178001183,
      "grad_norm": 0.5749856137025093,
      "learning_rate": 5e-06,
      "loss": 0.6668,
      "step": 170
    },
    {
      "epoch": 0.42578356002365464,
      "grad_norm": 0.5270300994955561,
      "learning_rate": 5e-06,
      "loss": 0.6739,
      "step": 180
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.4564112773847777,
      "learning_rate": 5e-06,
      "loss": 0.67,
      "step": 190
    },
    {
      "epoch": 0.47309284447072736,
      "grad_norm": 0.6424018806184643,
      "learning_rate": 5e-06,
      "loss": 0.6689,
      "step": 200
    },
    {
      "epoch": 0.4967474866942638,
      "grad_norm": 0.9633823614289843,
      "learning_rate": 5e-06,
      "loss": 0.6693,
      "step": 210
    },
    {
      "epoch": 0.5204021289178001,
      "grad_norm": 0.5911923837305756,
      "learning_rate": 5e-06,
      "loss": 0.6684,
      "step": 220
    },
    {
      "epoch": 0.5440567711413364,
      "grad_norm": 0.42377038905272263,
      "learning_rate": 5e-06,
      "loss": 0.6601,
      "step": 230
    },
    {
      "epoch": 0.5677114133648729,
      "grad_norm": 0.45358915803398175,
      "learning_rate": 5e-06,
      "loss": 0.6645,
      "step": 240
    },
    {
      "epoch": 0.5913660555884093,
      "grad_norm": 0.5561319066414647,
      "learning_rate": 5e-06,
      "loss": 0.6615,
      "step": 250
    },
    {
      "epoch": 0.6150206978119456,
      "grad_norm": 0.48146552840960954,
      "learning_rate": 5e-06,
      "loss": 0.6521,
      "step": 260
    },
    {
      "epoch": 0.638675340035482,
      "grad_norm": 0.6646986767108664,
      "learning_rate": 5e-06,
      "loss": 0.6636,
      "step": 270
    },
    {
      "epoch": 0.6623299822590183,
      "grad_norm": 0.6286029463531491,
      "learning_rate": 5e-06,
      "loss": 0.6653,
      "step": 280
    },
    {
      "epoch": 0.6859846244825547,
      "grad_norm": 0.47552147839170555,
      "learning_rate": 5e-06,
      "loss": 0.6594,
      "step": 290
    },
    {
      "epoch": 0.7096392667060911,
      "grad_norm": 0.5643579688885435,
      "learning_rate": 5e-06,
      "loss": 0.6532,
      "step": 300
    },
    {
      "epoch": 0.7332939089296274,
      "grad_norm": 0.47432297972285264,
      "learning_rate": 5e-06,
      "loss": 0.6615,
      "step": 310
    },
    {
      "epoch": 0.7569485511531638,
      "grad_norm": 0.4398747123335146,
      "learning_rate": 5e-06,
      "loss": 0.6555,
      "step": 320
    },
    {
      "epoch": 0.7806031933767001,
      "grad_norm": 0.5194948335540115,
      "learning_rate": 5e-06,
      "loss": 0.6537,
      "step": 330
    },
    {
      "epoch": 0.8042578356002366,
      "grad_norm": 0.5361623479539347,
      "learning_rate": 5e-06,
      "loss": 0.6535,
      "step": 340
    },
    {
      "epoch": 0.8279124778237729,
      "grad_norm": 0.5378540604132823,
      "learning_rate": 5e-06,
      "loss": 0.6598,
      "step": 350
    },
    {
      "epoch": 0.8515671200473093,
      "grad_norm": 0.43570116634348305,
      "learning_rate": 5e-06,
      "loss": 0.6533,
      "step": 360
    },
    {
      "epoch": 0.8752217622708457,
      "grad_norm": 0.4760030489635267,
      "learning_rate": 5e-06,
      "loss": 0.6567,
      "step": 370
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.5221489125969696,
      "learning_rate": 5e-06,
      "loss": 0.6475,
      "step": 380
    },
    {
      "epoch": 0.9225310467179184,
      "grad_norm": 0.6037987178986088,
      "learning_rate": 5e-06,
      "loss": 0.6548,
      "step": 390
    },
    {
      "epoch": 0.9461856889414547,
      "grad_norm": 0.4648850754901681,
      "learning_rate": 5e-06,
      "loss": 0.6464,
      "step": 400
    },
    {
      "epoch": 0.9698403311649911,
      "grad_norm": 0.4722370230360759,
      "learning_rate": 5e-06,
      "loss": 0.6489,
      "step": 410
    },
    {
      "epoch": 0.9934949733885275,
      "grad_norm": 0.506164447733558,
      "learning_rate": 5e-06,
      "loss": 0.6479,
      "step": 420
    },
    {
      "epoch": 0.9982259018332348,
      "eval_loss": 0.6500382423400879,
      "eval_runtime": 226.0859,
      "eval_samples_per_second": 50.375,
      "eval_steps_per_second": 0.394,
      "step": 422
    },
    {
      "epoch": 1.0171496156120639,
      "grad_norm": 0.5094563043289723,
      "learning_rate": 5e-06,
      "loss": 0.6364,
      "step": 430
    },
    {
      "epoch": 1.0408042578356003,
      "grad_norm": 0.5191261264055049,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 440
    },
    {
      "epoch": 1.0644589000591367,
      "grad_norm": 0.5080870756726318,
      "learning_rate": 5e-06,
      "loss": 0.6028,
      "step": 450
    },
    {
      "epoch": 1.0881135422826729,
      "grad_norm": 0.5071759369122493,
      "learning_rate": 5e-06,
      "loss": 0.6114,
      "step": 460
    },
    {
      "epoch": 1.1117681845062093,
      "grad_norm": 0.44639682629606836,
      "learning_rate": 5e-06,
      "loss": 0.6104,
      "step": 470
    },
    {
      "epoch": 1.1354228267297457,
      "grad_norm": 0.4671904061290404,
      "learning_rate": 5e-06,
      "loss": 0.6105,
      "step": 480
    },
    {
      "epoch": 1.1590774689532821,
      "grad_norm": 0.47682156648938734,
      "learning_rate": 5e-06,
      "loss": 0.6076,
      "step": 490
    },
    {
      "epoch": 1.1827321111768185,
      "grad_norm": 0.46620317831305,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 500
    },
    {
      "epoch": 1.2063867534003547,
      "grad_norm": 0.5319219132983622,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 510
    },
    {
      "epoch": 1.2300413956238911,
      "grad_norm": 0.5376832276402331,
      "learning_rate": 5e-06,
      "loss": 0.6095,
      "step": 520
    },
    {
      "epoch": 1.2536960378474276,
      "grad_norm": 0.5612860356721774,
      "learning_rate": 5e-06,
      "loss": 0.6106,
      "step": 530
    },
    {
      "epoch": 1.277350680070964,
      "grad_norm": 0.5310917873879784,
      "learning_rate": 5e-06,
      "loss": 0.611,
      "step": 540
    },
    {
      "epoch": 1.3010053222945004,
      "grad_norm": 0.5263300247672861,
      "learning_rate": 5e-06,
      "loss": 0.6091,
      "step": 550
    },
    {
      "epoch": 1.3246599645180366,
      "grad_norm": 0.46491345435473175,
      "learning_rate": 5e-06,
      "loss": 0.6073,
      "step": 560
    },
    {
      "epoch": 1.348314606741573,
      "grad_norm": 0.7395109471227356,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 570
    },
    {
      "epoch": 1.3719692489651094,
      "grad_norm": 0.46119094942392375,
      "learning_rate": 5e-06,
      "loss": 0.6109,
      "step": 580
    },
    {
      "epoch": 1.3956238911886458,
      "grad_norm": 0.4450854938398166,
      "learning_rate": 5e-06,
      "loss": 0.6115,
      "step": 590
    },
    {
      "epoch": 1.4192785334121822,
      "grad_norm": 0.5551565902862219,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 600
    },
    {
      "epoch": 1.4429331756357184,
      "grad_norm": 0.4018778370206095,
      "learning_rate": 5e-06,
      "loss": 0.6004,
      "step": 610
    },
    {
      "epoch": 1.4665878178592548,
      "grad_norm": 0.44942300591311213,
      "learning_rate": 5e-06,
      "loss": 0.603,
      "step": 620
    },
    {
      "epoch": 1.4902424600827913,
      "grad_norm": 0.4465193449169376,
      "learning_rate": 5e-06,
      "loss": 0.6136,
      "step": 630
    },
    {
      "epoch": 1.5138971023063275,
      "grad_norm": 0.43030425922494153,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 640
    },
    {
      "epoch": 1.537551744529864,
      "grad_norm": 0.48189491125310013,
      "learning_rate": 5e-06,
      "loss": 0.6029,
      "step": 650
    },
    {
      "epoch": 1.5612063867534003,
      "grad_norm": 0.6004161164250926,
      "learning_rate": 5e-06,
      "loss": 0.6071,
      "step": 660
    },
    {
      "epoch": 1.5848610289769367,
      "grad_norm": 0.5769771492223703,
      "learning_rate": 5e-06,
      "loss": 0.6039,
      "step": 670
    },
    {
      "epoch": 1.6085156712004731,
      "grad_norm": 0.5178134406863251,
      "learning_rate": 5e-06,
      "loss": 0.6082,
      "step": 680
    },
    {
      "epoch": 1.6321703134240093,
      "grad_norm": 0.544609037335345,
      "learning_rate": 5e-06,
      "loss": 0.6015,
      "step": 690
    },
    {
      "epoch": 1.655824955647546,
      "grad_norm": 0.4825223518027102,
      "learning_rate": 5e-06,
      "loss": 0.6088,
      "step": 700
    },
    {
      "epoch": 1.6794795978710821,
      "grad_norm": 0.4914541229221081,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 710
    },
    {
      "epoch": 1.7031342400946186,
      "grad_norm": 0.5142329564921958,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 720
    },
    {
      "epoch": 1.726788882318155,
      "grad_norm": 0.4827136360568082,
      "learning_rate": 5e-06,
      "loss": 0.6091,
      "step": 730
    },
    {
      "epoch": 1.7504435245416912,
      "grad_norm": 0.6337370950629847,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 740
    },
    {
      "epoch": 1.7740981667652278,
      "grad_norm": 0.44154103246732906,
      "learning_rate": 5e-06,
      "loss": 0.6095,
      "step": 750
    },
    {
      "epoch": 1.797752808988764,
      "grad_norm": 0.45443332352805516,
      "learning_rate": 5e-06,
      "loss": 0.6142,
      "step": 760
    },
    {
      "epoch": 1.8214074512123004,
      "grad_norm": 0.4163069710397612,
      "learning_rate": 5e-06,
      "loss": 0.615,
      "step": 770
    },
    {
      "epoch": 1.8450620934358368,
      "grad_norm": 0.4161179540449698,
      "learning_rate": 5e-06,
      "loss": 0.6068,
      "step": 780
    },
    {
      "epoch": 1.868716735659373,
      "grad_norm": 0.5280163972542002,
      "learning_rate": 5e-06,
      "loss": 0.6056,
      "step": 790
    },
    {
      "epoch": 1.8923713778829097,
      "grad_norm": 0.46668538311447527,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 800
    },
    {
      "epoch": 1.9160260201064458,
      "grad_norm": 0.42346894046836875,
      "learning_rate": 5e-06,
      "loss": 0.6118,
      "step": 810
    },
    {
      "epoch": 1.9396806623299823,
      "grad_norm": 0.41896781546766526,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 820
    },
    {
      "epoch": 1.9633353045535187,
      "grad_norm": 0.4633335148255916,
      "learning_rate": 5e-06,
      "loss": 0.6111,
      "step": 830
    },
    {
      "epoch": 1.9869899467770549,
      "grad_norm": 0.476695749395824,
      "learning_rate": 5e-06,
      "loss": 0.596,
      "step": 840
    },
    {
      "epoch": 1.9988172678888232,
      "eval_loss": 0.6398171186447144,
      "eval_runtime": 226.8946,
      "eval_samples_per_second": 50.195,
      "eval_steps_per_second": 0.392,
      "step": 845
    },
    {
      "epoch": 2.0106445890005915,
      "grad_norm": 0.6169607703828688,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 850
    },
    {
      "epoch": 2.0342992312241277,
      "grad_norm": 0.5426446180098695,
      "learning_rate": 5e-06,
      "loss": 0.5657,
      "step": 860
    },
    {
      "epoch": 2.057953873447664,
      "grad_norm": 0.5390790167711137,
      "learning_rate": 5e-06,
      "loss": 0.5657,
      "step": 870
    },
    {
      "epoch": 2.0816085156712005,
      "grad_norm": 0.578360411177351,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 880
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.5197231353776123,
      "learning_rate": 5e-06,
      "loss": 0.5602,
      "step": 890
    },
    {
      "epoch": 2.1289178001182734,
      "grad_norm": 0.4859072638645338,
      "learning_rate": 5e-06,
      "loss": 0.5657,
      "step": 900
    },
    {
      "epoch": 2.1525724423418096,
      "grad_norm": 0.4779934502377749,
      "learning_rate": 5e-06,
      "loss": 0.5603,
      "step": 910
    },
    {
      "epoch": 2.1762270845653457,
      "grad_norm": 0.4708802789385491,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 920
    },
    {
      "epoch": 2.1998817267888824,
      "grad_norm": 0.5551422131481033,
      "learning_rate": 5e-06,
      "loss": 0.5615,
      "step": 930
    },
    {
      "epoch": 2.2235363690124186,
      "grad_norm": 0.6102253316948937,
      "learning_rate": 5e-06,
      "loss": 0.5631,
      "step": 940
    },
    {
      "epoch": 2.247191011235955,
      "grad_norm": 0.5515235751158143,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 950
    },
    {
      "epoch": 2.2708456534594914,
      "grad_norm": 0.5435816919940853,
      "learning_rate": 5e-06,
      "loss": 0.5628,
      "step": 960
    },
    {
      "epoch": 2.2945002956830276,
      "grad_norm": 0.5029810305754802,
      "learning_rate": 5e-06,
      "loss": 0.5646,
      "step": 970
    },
    {
      "epoch": 2.3181549379065642,
      "grad_norm": 0.5615005267431546,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 980
    },
    {
      "epoch": 2.3418095801301004,
      "grad_norm": 0.49168169351440816,
      "learning_rate": 5e-06,
      "loss": 0.5662,
      "step": 990
    },
    {
      "epoch": 2.365464222353637,
      "grad_norm": 0.5771081751524688,
      "learning_rate": 5e-06,
      "loss": 0.5665,
      "step": 1000
    },
    {
      "epoch": 2.3891188645771733,
      "grad_norm": 0.4680061355705797,
      "learning_rate": 5e-06,
      "loss": 0.5646,
      "step": 1010
    },
    {
      "epoch": 2.4127735068007095,
      "grad_norm": 0.564004480266281,
      "learning_rate": 5e-06,
      "loss": 0.5621,
      "step": 1020
    },
    {
      "epoch": 2.436428149024246,
      "grad_norm": 0.4778290387931295,
      "learning_rate": 5e-06,
      "loss": 0.5651,
      "step": 1030
    },
    {
      "epoch": 2.4600827912477823,
      "grad_norm": 0.6235579512913804,
      "learning_rate": 5e-06,
      "loss": 0.5658,
      "step": 1040
    },
    {
      "epoch": 2.483737433471319,
      "grad_norm": 0.5224755229558726,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 1050
    },
    {
      "epoch": 2.507392075694855,
      "grad_norm": 0.5155806397749756,
      "learning_rate": 5e-06,
      "loss": 0.5676,
      "step": 1060
    },
    {
      "epoch": 2.5310467179183913,
      "grad_norm": 0.4957936150342283,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 1070
    },
    {
      "epoch": 2.554701360141928,
      "grad_norm": 0.5154987387729463,
      "learning_rate": 5e-06,
      "loss": 0.5707,
      "step": 1080
    },
    {
      "epoch": 2.578356002365464,
      "grad_norm": 0.5044551175485149,
      "learning_rate": 5e-06,
      "loss": 0.565,
      "step": 1090
    },
    {
      "epoch": 2.6020106445890008,
      "grad_norm": 0.4516076390737273,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 1100
    },
    {
      "epoch": 2.625665286812537,
      "grad_norm": 0.5045929619515908,
      "learning_rate": 5e-06,
      "loss": 0.5649,
      "step": 1110
    },
    {
      "epoch": 2.649319929036073,
      "grad_norm": 0.580462719659177,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 1120
    },
    {
      "epoch": 2.67297457125961,
      "grad_norm": 0.575884289754489,
      "learning_rate": 5e-06,
      "loss": 0.5635,
      "step": 1130
    },
    {
      "epoch": 2.696629213483146,
      "grad_norm": 0.45389440525574193,
      "learning_rate": 5e-06,
      "loss": 0.5642,
      "step": 1140
    },
    {
      "epoch": 2.7202838557066826,
      "grad_norm": 0.5500836980193272,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 1150
    },
    {
      "epoch": 2.743938497930219,
      "grad_norm": 0.5317230345652454,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 1160
    },
    {
      "epoch": 2.767593140153755,
      "grad_norm": 0.5423217141987767,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 1170
    },
    {
      "epoch": 2.7912477823772917,
      "grad_norm": 0.45026276354942224,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1180
    },
    {
      "epoch": 2.814902424600828,
      "grad_norm": 0.4729801358724606,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 1190
    },
    {
      "epoch": 2.8385570668243645,
      "grad_norm": 0.4541256119629826,
      "learning_rate": 5e-06,
      "loss": 0.5666,
      "step": 1200
    },
    {
      "epoch": 2.8622117090479007,
      "grad_norm": 0.5065447399632258,
      "learning_rate": 5e-06,
      "loss": 0.568,
      "step": 1210
    },
    {
      "epoch": 2.885866351271437,
      "grad_norm": 0.46787373309179847,
      "learning_rate": 5e-06,
      "loss": 0.562,
      "step": 1220
    },
    {
      "epoch": 2.9095209934949735,
      "grad_norm": 0.5140600861948555,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 1230
    },
    {
      "epoch": 2.9331756357185097,
      "grad_norm": 0.4924658786836096,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1240
    },
    {
      "epoch": 2.9568302779420463,
      "grad_norm": 0.43768785522082726,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 1250
    },
    {
      "epoch": 2.9804849201655825,
      "grad_norm": 0.49992037039861137,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 1260
    },
    {
      "epoch": 2.9994086339444115,
      "eval_loss": 0.6412045359611511,
      "eval_runtime": 227.4087,
      "eval_samples_per_second": 50.082,
      "eval_steps_per_second": 0.391,
      "step": 1268
    },
    {
      "epoch": 3.0041395623891187,
      "grad_norm": 0.7997038665721562,
      "learning_rate": 5e-06,
      "loss": 0.5734,
      "step": 1270
    },
    {
      "epoch": 3.0277942046126554,
      "grad_norm": 0.7087021533978439,
      "learning_rate": 5e-06,
      "loss": 0.5192,
      "step": 1280
    },
    {
      "epoch": 3.0514488468361916,
      "grad_norm": 0.6369517216502235,
      "learning_rate": 5e-06,
      "loss": 0.5252,
      "step": 1290
    },
    {
      "epoch": 3.075103489059728,
      "grad_norm": 0.5422250793349076,
      "learning_rate": 5e-06,
      "loss": 0.518,
      "step": 1300
    },
    {
      "epoch": 3.0987581312832644,
      "grad_norm": 0.4983982055937172,
      "learning_rate": 5e-06,
      "loss": 0.523,
      "step": 1310
    },
    {
      "epoch": 3.1224127735068006,
      "grad_norm": 0.5243425125520329,
      "learning_rate": 5e-06,
      "loss": 0.5206,
      "step": 1320
    },
    {
      "epoch": 3.146067415730337,
      "grad_norm": 0.4867213185448702,
      "learning_rate": 5e-06,
      "loss": 0.5243,
      "step": 1330
    },
    {
      "epoch": 3.1697220579538734,
      "grad_norm": 0.5758407627499461,
      "learning_rate": 5e-06,
      "loss": 0.5252,
      "step": 1340
    },
    {
      "epoch": 3.19337670017741,
      "grad_norm": 0.5312930409261694,
      "learning_rate": 5e-06,
      "loss": 0.5239,
      "step": 1350
    },
    {
      "epoch": 3.2170313424009462,
      "grad_norm": 0.5655992541782802,
      "learning_rate": 5e-06,
      "loss": 0.5284,
      "step": 1360
    },
    {
      "epoch": 3.2406859846244824,
      "grad_norm": 0.5600254916460519,
      "learning_rate": 5e-06,
      "loss": 0.5247,
      "step": 1370
    },
    {
      "epoch": 3.264340626848019,
      "grad_norm": 0.5493705668694846,
      "learning_rate": 5e-06,
      "loss": 0.5256,
      "step": 1380
    },
    {
      "epoch": 3.2879952690715553,
      "grad_norm": 0.5454062241643639,
      "learning_rate": 5e-06,
      "loss": 0.5251,
      "step": 1390
    },
    {
      "epoch": 3.311649911295092,
      "grad_norm": 0.5317414152397003,
      "learning_rate": 5e-06,
      "loss": 0.5264,
      "step": 1400
    },
    {
      "epoch": 3.335304553518628,
      "grad_norm": 0.522262224626374,
      "learning_rate": 5e-06,
      "loss": 0.5246,
      "step": 1410
    },
    {
      "epoch": 3.3589591957421643,
      "grad_norm": 0.5296232089165864,
      "learning_rate": 5e-06,
      "loss": 0.5337,
      "step": 1420
    },
    {
      "epoch": 3.382613837965701,
      "grad_norm": 0.5272756646376445,
      "learning_rate": 5e-06,
      "loss": 0.5293,
      "step": 1430
    },
    {
      "epoch": 3.406268480189237,
      "grad_norm": 0.55914181485459,
      "learning_rate": 5e-06,
      "loss": 0.5237,
      "step": 1440
    },
    {
      "epoch": 3.4299231224127738,
      "grad_norm": 0.4921288128015139,
      "learning_rate": 5e-06,
      "loss": 0.5271,
      "step": 1450
    },
    {
      "epoch": 3.45357776463631,
      "grad_norm": 0.5365784280337929,
      "learning_rate": 5e-06,
      "loss": 0.5257,
      "step": 1460
    },
    {
      "epoch": 3.477232406859846,
      "grad_norm": 0.5463822390250614,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 1470
    },
    {
      "epoch": 3.5008870490833828,
      "grad_norm": 0.5296060277501131,
      "learning_rate": 5e-06,
      "loss": 0.5307,
      "step": 1480
    },
    {
      "epoch": 3.524541691306919,
      "grad_norm": 0.5118534830144524,
      "learning_rate": 5e-06,
      "loss": 0.529,
      "step": 1490
    },
    {
      "epoch": 3.5481963335304556,
      "grad_norm": 0.4803120353260472,
      "learning_rate": 5e-06,
      "loss": 0.5339,
      "step": 1500
    },
    {
      "epoch": 3.571850975753992,
      "grad_norm": 0.4786671860417403,
      "learning_rate": 5e-06,
      "loss": 0.5304,
      "step": 1510
    },
    {
      "epoch": 3.595505617977528,
      "grad_norm": 0.5285834688732408,
      "learning_rate": 5e-06,
      "loss": 0.5284,
      "step": 1520
    },
    {
      "epoch": 3.619160260201064,
      "grad_norm": 0.584807508614226,
      "learning_rate": 5e-06,
      "loss": 0.5227,
      "step": 1530
    },
    {
      "epoch": 3.642814902424601,
      "grad_norm": 0.5839419610849975,
      "learning_rate": 5e-06,
      "loss": 0.5322,
      "step": 1540
    },
    {
      "epoch": 3.6664695446481375,
      "grad_norm": 0.4514003865869288,
      "learning_rate": 5e-06,
      "loss": 0.5277,
      "step": 1550
    },
    {
      "epoch": 3.6901241868716737,
      "grad_norm": 0.5330412676715586,
      "learning_rate": 5e-06,
      "loss": 0.5334,
      "step": 1560
    },
    {
      "epoch": 3.71377882909521,
      "grad_norm": 0.49755559197077215,
      "learning_rate": 5e-06,
      "loss": 0.536,
      "step": 1570
    },
    {
      "epoch": 3.737433471318746,
      "grad_norm": 0.5204717016848357,
      "learning_rate": 5e-06,
      "loss": 0.534,
      "step": 1580
    },
    {
      "epoch": 3.7610881135422827,
      "grad_norm": 0.49061356565453146,
      "learning_rate": 5e-06,
      "loss": 0.5281,
      "step": 1590
    },
    {
      "epoch": 3.7847427557658193,
      "grad_norm": 0.6053218200808435,
      "learning_rate": 5e-06,
      "loss": 0.5316,
      "step": 1600
    },
    {
      "epoch": 3.8083973979893555,
      "grad_norm": 0.6606016275554902,
      "learning_rate": 5e-06,
      "loss": 0.5353,
      "step": 1610
    },
    {
      "epoch": 3.8320520402128917,
      "grad_norm": 0.4907218140881002,
      "learning_rate": 5e-06,
      "loss": 0.5281,
      "step": 1620
    },
    {
      "epoch": 3.855706682436428,
      "grad_norm": 0.45979128640427186,
      "learning_rate": 5e-06,
      "loss": 0.5304,
      "step": 1630
    },
    {
      "epoch": 3.8793613246599645,
      "grad_norm": 0.46823925120727844,
      "learning_rate": 5e-06,
      "loss": 0.5349,
      "step": 1640
    },
    {
      "epoch": 3.903015966883501,
      "grad_norm": 0.4817910084064857,
      "learning_rate": 5e-06,
      "loss": 0.5306,
      "step": 1650
    },
    {
      "epoch": 3.9266706091070374,
      "grad_norm": 0.6114087825987051,
      "learning_rate": 5e-06,
      "loss": 0.5288,
      "step": 1660
    },
    {
      "epoch": 3.9503252513305736,
      "grad_norm": 0.48214763063708094,
      "learning_rate": 5e-06,
      "loss": 0.5289,
      "step": 1670
    },
    {
      "epoch": 3.9739798935541097,
      "grad_norm": 0.4984632076912188,
      "learning_rate": 5e-06,
      "loss": 0.5291,
      "step": 1680
    },
    {
      "epoch": 3.992903607332939,
      "eval_loss": 0.6530380845069885,
      "eval_runtime": 225.9522,
      "eval_samples_per_second": 50.404,
      "eval_steps_per_second": 0.394,
      "step": 1688
    },
    {
      "epoch": 3.992903607332939,
      "step": 1688,
      "total_flos": 2827044110991360.0,
      "train_loss": 0.5963167059478036,
      "train_runtime": 50350.8421,
      "train_samples_per_second": 17.189,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 10,
  "max_steps": 1688,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 2827044110991360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}