{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.273972602739725,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00684931506849315,
      "grad_norm": 3.5625,
      "learning_rate": 9.132420091324201e-07,
      "loss": 3.0017,
      "step": 1
    },
    {
      "epoch": 0.03424657534246575,
      "grad_norm": 2.9375,
      "learning_rate": 4.566210045662101e-06,
      "loss": 3.0725,
      "step": 5
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 3.078125,
      "learning_rate": 9.132420091324201e-06,
      "loss": 3.0374,
      "step": 10
    },
    {
      "epoch": 0.10273972602739725,
      "grad_norm": 2.515625,
      "learning_rate": 1.3698630136986302e-05,
      "loss": 3.0044,
      "step": 15
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 2.3125,
      "learning_rate": 1.8264840182648402e-05,
      "loss": 2.9373,
      "step": 20
    },
    {
      "epoch": 0.17123287671232876,
      "grad_norm": 4.90625,
      "learning_rate": 2.2831050228310503e-05,
      "loss": 2.7849,
      "step": 25
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 17.0,
      "learning_rate": 2.7397260273972603e-05,
      "loss": 2.6263,
      "step": 30
    },
    {
      "epoch": 0.23972602739726026,
      "grad_norm": 1.0859375,
      "learning_rate": 3.1963470319634704e-05,
      "loss": 2.4603,
      "step": 35
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 1.75,
      "learning_rate": 3.6529680365296805e-05,
      "loss": 2.3423,
      "step": 40
    },
    {
      "epoch": 0.3082191780821918,
      "grad_norm": 3.0,
      "learning_rate": 4.1095890410958905e-05,
      "loss": 2.2364,
      "step": 45
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 1.0546875,
      "learning_rate": 4.5662100456621006e-05,
      "loss": 2.0795,
      "step": 50
    },
    {
      "epoch": 0.3767123287671233,
      "grad_norm": 1.734375,
      "learning_rate": 5.0228310502283106e-05,
      "loss": 1.9497,
      "step": 55
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 1.25,
      "learning_rate": 5.479452054794521e-05,
      "loss": 1.8556,
      "step": 60
    },
    {
      "epoch": 0.4452054794520548,
      "grad_norm": 0.640625,
      "learning_rate": 5.936073059360731e-05,
      "loss": 1.759,
      "step": 65
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.97265625,
      "learning_rate": 6.392694063926941e-05,
      "loss": 1.6773,
      "step": 70
    },
    {
      "epoch": 0.5136986301369864,
      "grad_norm": 1.9296875,
      "learning_rate": 6.84931506849315e-05,
      "loss": 1.6105,
      "step": 75
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.51171875,
      "learning_rate": 7.305936073059361e-05,
      "loss": 1.5517,
      "step": 80
    },
    {
      "epoch": 0.5821917808219178,
      "grad_norm": 0.45703125,
      "learning_rate": 7.76255707762557e-05,
      "loss": 1.4895,
      "step": 85
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.326171875,
      "learning_rate": 8.219178082191781e-05,
      "loss": 1.466,
      "step": 90
    },
    {
      "epoch": 0.6506849315068494,
      "grad_norm": 0.283203125,
      "learning_rate": 8.67579908675799e-05,
      "loss": 1.4237,
      "step": 95
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.333984375,
      "learning_rate": 9.132420091324201e-05,
      "loss": 1.3836,
      "step": 100
    },
    {
      "epoch": 0.7191780821917808,
      "grad_norm": 0.578125,
      "learning_rate": 9.58904109589041e-05,
      "loss": 1.3655,
      "step": 105
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.484375,
      "learning_rate": 0.00010045662100456621,
      "loss": 1.3369,
      "step": 110
    },
    {
      "epoch": 0.7876712328767124,
      "grad_norm": 0.3671875,
      "learning_rate": 0.00010502283105022832,
      "loss": 1.3149,
      "step": 115
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00010958904109589041,
      "loss": 1.3051,
      "step": 120
    },
    {
      "epoch": 0.8561643835616438,
      "grad_norm": 0.74609375,
      "learning_rate": 0.00011415525114155252,
      "loss": 1.2835,
      "step": 125
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00011872146118721462,
      "loss": 1.2805,
      "step": 130
    },
    {
      "epoch": 0.9246575342465754,
      "grad_norm": 0.82421875,
      "learning_rate": 0.0001232876712328767,
      "loss": 1.2617,
      "step": 135
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.498046875,
      "learning_rate": 0.00012785388127853882,
      "loss": 1.2659,
      "step": 140
    },
    {
      "epoch": 0.9931506849315068,
      "grad_norm": 0.28125,
      "learning_rate": 0.00013242009132420092,
      "loss": 1.2474,
      "step": 145
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.523677110671997,
      "eval_runtime": 0.5573,
      "eval_samples_per_second": 17.944,
      "eval_steps_per_second": 1.794,
      "step": 146
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 0.58984375,
      "learning_rate": 0.000136986301369863,
      "loss": 1.2351,
      "step": 150
    },
    {
      "epoch": 1.0616438356164384,
      "grad_norm": 0.5234375,
      "learning_rate": 0.0001415525114155251,
      "loss": 1.2256,
      "step": 155
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00014611872146118722,
      "loss": 1.2203,
      "step": 160
    },
    {
      "epoch": 1.13013698630137,
      "grad_norm": 0.35546875,
      "learning_rate": 0.00015068493150684933,
      "loss": 1.1994,
      "step": 165
    },
    {
      "epoch": 1.1643835616438356,
      "grad_norm": 0.345703125,
      "learning_rate": 0.0001552511415525114,
      "loss": 1.2069,
      "step": 170
    },
    {
      "epoch": 1.1986301369863013,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00015981735159817351,
      "loss": 1.1912,
      "step": 175
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 0.365234375,
      "learning_rate": 0.00016438356164383562,
      "loss": 1.1879,
      "step": 180
    },
    {
      "epoch": 1.2671232876712328,
      "grad_norm": 0.42578125,
      "learning_rate": 0.00016894977168949773,
      "loss": 1.1983,
      "step": 185
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 0.63671875,
      "learning_rate": 0.0001735159817351598,
      "loss": 1.1872,
      "step": 190
    },
    {
      "epoch": 1.3356164383561644,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00017808219178082192,
      "loss": 1.1806,
      "step": 195
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00018264840182648402,
      "loss": 1.1849,
      "step": 200
    },
    {
      "epoch": 1.404109589041096,
      "grad_norm": 1.046875,
      "learning_rate": 0.00018721461187214613,
      "loss": 1.1782,
      "step": 205
    },
    {
      "epoch": 1.4383561643835616,
      "grad_norm": 0.373046875,
      "learning_rate": 0.0001917808219178082,
      "loss": 1.1727,
      "step": 210
    },
    {
      "epoch": 1.4726027397260273,
      "grad_norm": 0.482421875,
      "learning_rate": 0.00019634703196347032,
      "loss": 1.1725,
      "step": 215
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00019999987297289245,
      "loss": 1.1611,
      "step": 220
    },
    {
      "epoch": 1.541095890410959,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00019999542705801296,
      "loss": 1.1642,
      "step": 225
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 0.361328125,
      "learning_rate": 0.00019998463011046926,
      "loss": 1.1608,
      "step": 230
    },
    {
      "epoch": 1.6095890410958904,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00019996748281601038,
      "loss": 1.1563,
      "step": 235
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00019994398626371643,
      "loss": 1.1457,
      "step": 240
    },
    {
      "epoch": 1.678082191780822,
      "grad_norm": 0.45703125,
      "learning_rate": 0.0001999141419459293,
      "loss": 1.1609,
      "step": 245
    },
    {
      "epoch": 1.7123287671232876,
      "grad_norm": 0.70703125,
      "learning_rate": 0.00019987795175815807,
      "loss": 1.1479,
      "step": 250
    },
    {
      "epoch": 1.7465753424657535,
      "grad_norm": 0.451171875,
      "learning_rate": 0.0001998354179989585,
      "loss": 1.148,
      "step": 255
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.421875,
      "learning_rate": 0.0001997865433697871,
      "loss": 1.1513,
      "step": 260
    },
    {
      "epoch": 1.8150684931506849,
      "grad_norm": 0.64453125,
      "learning_rate": 0.00019973133097482947,
      "loss": 1.1327,
      "step": 265
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00019966978432080316,
      "loss": 1.1424,
      "step": 270
    },
    {
      "epoch": 1.8835616438356164,
      "grad_norm": 0.4375,
      "learning_rate": 0.00019960190731673505,
      "loss": 1.1387,
      "step": 275
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00019952770427371304,
      "loss": 1.1258,
      "step": 280
    },
    {
      "epoch": 1.952054794520548,
      "grad_norm": 0.447265625,
      "learning_rate": 0.00019944717990461207,
      "loss": 1.1226,
      "step": 285
    },
    {
      "epoch": 1.9863013698630136,
      "grad_norm": 0.427734375,
      "learning_rate": 0.00019936033932379504,
      "loss": 1.1269,
      "step": 290
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.4804677963256836,
      "eval_runtime": 0.5614,
      "eval_samples_per_second": 17.814,
      "eval_steps_per_second": 1.781,
      "step": 292
    },
    {
      "epoch": 2.0205479452054793,
      "grad_norm": 0.4609375,
      "learning_rate": 0.00019926718804678785,
      "loss": 1.1225,
      "step": 295
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 0.435546875,
      "learning_rate": 0.000199167731989929,
      "loss": 1.1022,
      "step": 300
    },
    {
      "epoch": 2.089041095890411,
      "grad_norm": 0.4140625,
      "learning_rate": 0.00019906197746999408,
      "loss": 1.1012,
      "step": 305
    },
    {
      "epoch": 2.1232876712328768,
      "grad_norm": 0.3515625,
      "learning_rate": 0.00019894993120379435,
      "loss": 1.0928,
      "step": 310
    },
    {
      "epoch": 2.1575342465753424,
      "grad_norm": 0.43359375,
      "learning_rate": 0.00019883160030775016,
      "loss": 1.1032,
      "step": 315
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00019870699229743911,
      "loss": 1.0966,
      "step": 320
    },
    {
      "epoch": 2.2260273972602738,
      "grad_norm": 0.81640625,
      "learning_rate": 0.0001985761150871185,
      "loss": 1.0952,
      "step": 325
    },
    {
      "epoch": 2.26027397260274,
      "grad_norm": 0.462890625,
      "learning_rate": 0.00019843897698922284,
      "loss": 1.0936,
      "step": 330
    },
    {
      "epoch": 2.2945205479452055,
      "grad_norm": 0.3203125,
      "learning_rate": 0.00019829558671383585,
      "loss": 1.0938,
      "step": 335
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 0.494140625,
      "learning_rate": 0.00019814595336813725,
      "loss": 1.0856,
      "step": 340
    },
    {
      "epoch": 2.363013698630137,
      "grad_norm": 0.353515625,
      "learning_rate": 0.0001979900864558242,
      "loss": 1.0851,
      "step": 345
    },
    {
      "epoch": 2.3972602739726026,
      "grad_norm": 0.3359375,
      "learning_rate": 0.00019782799587650805,
      "loss": 1.1018,
      "step": 350
    },
    {
      "epoch": 2.4315068493150687,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00019765969192508508,
      "loss": 1.0882,
      "step": 355
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.341796875,
      "learning_rate": 0.00019748518529108316,
      "loss": 1.0932,
      "step": 360
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.404296875,
      "learning_rate": 0.00019730448705798239,
      "loss": 1.0945,
      "step": 365
    },
    {
      "epoch": 2.5342465753424657,
      "grad_norm": 0.35546875,
      "learning_rate": 0.00019711760870251143,
      "loss": 1.0881,
      "step": 370
    },
    {
      "epoch": 2.5684931506849313,
      "grad_norm": 0.40234375,
      "learning_rate": 0.00019692456209391846,
      "loss": 1.0802,
      "step": 375
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 0.52734375,
      "learning_rate": 0.0001967253594932173,
      "loss": 1.0822,
      "step": 380
    },
    {
      "epoch": 2.636986301369863,
      "grad_norm": 0.337890625,
      "learning_rate": 0.00019652001355240878,
      "loss": 1.0907,
      "step": 385
    },
    {
      "epoch": 2.671232876712329,
      "grad_norm": 0.373046875,
      "learning_rate": 0.00019630853731367713,
      "loss": 1.0868,
      "step": 390
    },
    {
      "epoch": 2.7054794520547945,
      "grad_norm": 0.40234375,
      "learning_rate": 0.0001960909442085615,
      "loss": 1.086,
      "step": 395
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.384765625,
      "learning_rate": 0.00019586724805710306,
      "loss": 1.0746,
      "step": 400
    },
    {
      "epoch": 2.7739726027397262,
      "grad_norm": 0.353515625,
      "learning_rate": 0.0001956374630669672,
      "loss": 1.0832,
      "step": 405
    },
    {
      "epoch": 2.808219178082192,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00019540160383254107,
      "loss": 1.0753,
      "step": 410
    },
    {
      "epoch": 2.8424657534246576,
      "grad_norm": 0.328125,
      "learning_rate": 0.00019515968533400673,
      "loss": 1.0844,
      "step": 415
    },
    {
      "epoch": 2.8767123287671232,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00019491172293638968,
      "loss": 1.083,
      "step": 420
    },
    {
      "epoch": 2.910958904109589,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00019465773238858298,
      "loss": 1.0757,
      "step": 425
    },
    {
      "epoch": 2.9452054794520546,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00019439772982234697,
      "loss": 1.075,
      "step": 430
    },
    {
      "epoch": 2.9794520547945207,
      "grad_norm": 3.71875,
      "learning_rate": 0.00019413173175128473,
      "loss": 1.0909,
      "step": 435
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.4892916679382324,
      "eval_runtime": 0.5522,
      "eval_samples_per_second": 18.108,
      "eval_steps_per_second": 1.811,
      "step": 438
    },
    {
      "epoch": 3.0136986301369864,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0001938597550697932,
      "loss": 1.0635,
      "step": 440
    },
    {
      "epoch": 3.047945205479452,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00019358181705199015,
      "loss": 1.0518,
      "step": 445
    },
    {
      "epoch": 3.0821917808219177,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00019329793535061723,
      "loss": 1.0509,
      "step": 450
    },
    {
      "epoch": 3.1164383561643834,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00019300812799591846,
      "loss": 1.0529,
      "step": 455
    },
    {
      "epoch": 3.1506849315068495,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00019271241339449536,
      "loss": 1.0416,
      "step": 460
    },
    {
      "epoch": 3.184931506849315,
      "grad_norm": 0.89453125,
      "learning_rate": 0.00019241081032813772,
      "loss": 1.0488,
      "step": 465
    },
    {
      "epoch": 3.219178082191781,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00019210333795263075,
      "loss": 1.0402,
      "step": 470
    },
    {
      "epoch": 3.2534246575342465,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00019179001579653853,
      "loss": 1.0568,
      "step": 475
    },
    {
      "epoch": 3.287671232876712,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001914708637599636,
      "loss": 1.0487,
      "step": 480
    },
    {
      "epoch": 3.3219178082191783,
      "grad_norm": 0.400390625,
      "learning_rate": 0.00019114590211328288,
      "loss": 1.0468,
      "step": 485
    },
    {
      "epoch": 3.356164383561644,
      "grad_norm": 0.439453125,
      "learning_rate": 0.0001908151514958606,
      "loss": 1.0538,
      "step": 490
    },
    {
      "epoch": 3.3904109589041096,
      "grad_norm": 0.37109375,
      "learning_rate": 0.00019047863291473717,
      "loss": 1.0441,
      "step": 495
    },
    {
      "epoch": 3.4246575342465753,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00019013636774329495,
      "loss": 1.0521,
      "step": 500
    },
    {
      "epoch": 3.458904109589041,
      "grad_norm": 0.4140625,
      "learning_rate": 0.00018978837771990085,
      "loss": 1.0405,
      "step": 505
    },
    {
      "epoch": 3.493150684931507,
      "grad_norm": 0.4375,
      "learning_rate": 0.0001894346849465257,
      "loss": 1.0439,
      "step": 510
    },
    {
      "epoch": 3.5273972602739727,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00018907531188734026,
      "loss": 1.0525,
      "step": 515
    },
    {
      "epoch": 3.5616438356164384,
      "grad_norm": 0.47265625,
      "learning_rate": 0.00018871028136728874,
      "loss": 1.0493,
      "step": 520
    },
    {
      "epoch": 3.595890410958904,
      "grad_norm": 0.35546875,
      "learning_rate": 0.00018833961657063885,
      "loss": 1.0405,
      "step": 525
    },
    {
      "epoch": 3.6301369863013697,
      "grad_norm": 0.50390625,
      "learning_rate": 0.0001879633410395095,
      "loss": 1.0452,
      "step": 530
    },
    {
      "epoch": 3.6643835616438354,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00018758147867237548,
      "loss": 1.0515,
      "step": 535
    },
    {
      "epoch": 3.6986301369863015,
      "grad_norm": 0.421875,
      "learning_rate": 0.00018719405372254948,
      "loss": 1.0453,
      "step": 540
    },
    {
      "epoch": 3.732876712328767,
      "grad_norm": 0.3359375,
      "learning_rate": 0.00018680109079664188,
      "loss": 1.0356,
      "step": 545
    },
    {
      "epoch": 3.767123287671233,
      "grad_norm": 0.333984375,
      "learning_rate": 0.0001864026148529978,
      "loss": 1.0355,
      "step": 550
    },
    {
      "epoch": 3.8013698630136985,
      "grad_norm": 0.427734375,
      "learning_rate": 0.00018599865120011192,
      "loss": 1.0452,
      "step": 555
    },
    {
      "epoch": 3.8356164383561646,
      "grad_norm": 0.34375,
      "learning_rate": 0.00018558922549502107,
      "loss": 1.0258,
      "step": 560
    },
    {
      "epoch": 3.8698630136986303,
      "grad_norm": 0.412109375,
      "learning_rate": 0.0001851743637416747,
      "loss": 1.0423,
      "step": 565
    },
    {
      "epoch": 3.904109589041096,
      "grad_norm": 0.31640625,
      "learning_rate": 0.00018475409228928312,
      "loss": 1.0238,
      "step": 570
    },
    {
      "epoch": 3.9383561643835616,
      "grad_norm": 0.400390625,
      "learning_rate": 0.00018432843783064429,
      "loss": 1.041,
      "step": 575
    },
    {
      "epoch": 3.9726027397260273,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00018389742740044813,
      "loss": 1.0354,
      "step": 580
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.5017333030700684,
      "eval_runtime": 0.5568,
      "eval_samples_per_second": 17.961,
      "eval_steps_per_second": 1.796,
      "step": 584
    },
    {
      "epoch": 4.006849315068493,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00018346108837355972,
      "loss": 1.0411,
      "step": 585
    },
    {
      "epoch": 4.041095890410959,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00018301944846328049,
      "loss": 0.9963,
      "step": 590
    },
    {
      "epoch": 4.075342465753424,
      "grad_norm": 0.36328125,
      "learning_rate": 0.0001825725357195881,
      "loss": 1.0137,
      "step": 595
    },
    {
      "epoch": 4.109589041095891,
      "grad_norm": 0.48046875,
      "learning_rate": 0.00018212037852735486,
      "loss": 1.006,
      "step": 600
    },
    {
      "epoch": 4.1438356164383565,
      "grad_norm": 0.4140625,
      "learning_rate": 0.0001816630056045451,
      "loss": 1.0075,
      "step": 605
    },
    {
      "epoch": 4.178082191780822,
      "grad_norm": 0.353515625,
      "learning_rate": 0.0001812004460003909,
      "loss": 0.9975,
      "step": 610
    },
    {
      "epoch": 4.212328767123288,
      "grad_norm": 0.365234375,
      "learning_rate": 0.00018073272909354727,
      "loss": 1.0171,
      "step": 615
    },
    {
      "epoch": 4.2465753424657535,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001802598845902262,
      "loss": 0.9953,
      "step": 620
    },
    {
      "epoch": 4.280821917808219,
      "grad_norm": 0.38671875,
      "learning_rate": 0.00017978194252230985,
      "loss": 1.008,
      "step": 625
    },
    {
      "epoch": 4.315068493150685,
      "grad_norm": 0.359375,
      "learning_rate": 0.00017929893324544332,
      "loss": 0.9993,
      "step": 630
    },
    {
      "epoch": 4.3493150684931505,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001788108874371063,
      "loss": 1.0119,
      "step": 635
    },
    {
      "epoch": 4.383561643835616,
      "grad_norm": 0.33203125,
      "learning_rate": 0.00017831783609466504,
      "loss": 1.0047,
      "step": 640
    },
    {
      "epoch": 4.417808219178082,
      "grad_norm": 0.341796875,
      "learning_rate": 0.00017781981053340337,
      "loss": 1.0143,
      "step": 645
    },
    {
      "epoch": 4.4520547945205475,
      "grad_norm": 0.345703125,
      "learning_rate": 0.00017731684238453385,
      "loss": 1.0023,
      "step": 650
    },
    {
      "epoch": 4.486301369863014,
      "grad_norm": 0.37890625,
      "learning_rate": 0.0001768089635931887,
      "loss": 1.0125,
      "step": 655
    },
    {
      "epoch": 4.52054794520548,
      "grad_norm": 0.609375,
      "learning_rate": 0.00017629620641639103,
      "loss": 1.0074,
      "step": 660
    },
    {
      "epoch": 4.554794520547945,
      "grad_norm": 0.36328125,
      "learning_rate": 0.00017577860342100579,
      "loss": 1.0124,
      "step": 665
    },
    {
      "epoch": 4.589041095890411,
      "grad_norm": 0.65625,
      "learning_rate": 0.0001752561874816717,
      "loss": 1.015,
      "step": 670
    },
    {
      "epoch": 4.623287671232877,
      "grad_norm": 0.38671875,
      "learning_rate": 0.00017472899177871297,
      "loss": 1.0066,
      "step": 675
    },
    {
      "epoch": 4.657534246575342,
      "grad_norm": 0.32421875,
      "learning_rate": 0.00017419704979603214,
      "loss": 1.0182,
      "step": 680
    },
    {
      "epoch": 4.691780821917808,
      "grad_norm": 0.34375,
      "learning_rate": 0.00017366039531898326,
      "loss": 1.0139,
      "step": 685
    },
    {
      "epoch": 4.726027397260274,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00017311906243222614,
      "loss": 1.0162,
      "step": 690
    },
    {
      "epoch": 4.760273972602739,
      "grad_norm": 0.3359375,
      "learning_rate": 0.0001725730855175615,
      "loss": 1.019,
      "step": 695
    },
    {
      "epoch": 4.794520547945205,
      "grad_norm": 0.431640625,
      "learning_rate": 0.00017202249925174723,
      "loss": 1.0051,
      "step": 700
    },
    {
      "epoch": 4.828767123287671,
      "grad_norm": 0.4140625,
      "learning_rate": 0.00017146733860429612,
      "loss": 1.0174,
      "step": 705
    },
    {
      "epoch": 4.863013698630137,
      "grad_norm": 0.408203125,
      "learning_rate": 0.0001709076388352546,
      "loss": 1.0065,
      "step": 710
    },
    {
      "epoch": 4.897260273972603,
      "grad_norm": 0.359375,
      "learning_rate": 0.00017034343549296346,
      "loss": 1.0262,
      "step": 715
    },
    {
      "epoch": 4.931506849315069,
      "grad_norm": 0.44140625,
      "learning_rate": 0.00016977476441179992,
      "loss": 1.0023,
      "step": 720
    },
    {
      "epoch": 4.965753424657534,
      "grad_norm": 0.357421875,
      "learning_rate": 0.0001692016617099018,
      "loss": 1.0048,
      "step": 725
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.431640625,
      "learning_rate": 0.0001686241637868734,
      "loss": 1.0016,
      "step": 730
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.5294971466064453,
      "eval_runtime": 0.5501,
      "eval_samples_per_second": 18.178,
      "eval_steps_per_second": 1.818,
      "step": 730
    },
    {
      "epoch": 5.034246575342466,
      "grad_norm": 0.380859375,
      "learning_rate": 0.0001680423073214737,
      "loss": 0.9822,
      "step": 735
    },
    {
      "epoch": 5.068493150684931,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00016745612926928694,
      "loss": 0.9842,
      "step": 740
    },
    {
      "epoch": 5.102739726027397,
      "grad_norm": 0.38671875,
      "learning_rate": 0.0001668656668603751,
      "loss": 0.9717,
      "step": 745
    },
    {
      "epoch": 5.136986301369863,
      "grad_norm": 0.375,
      "learning_rate": 0.00016627095759691362,
      "loss": 0.9685,
      "step": 750
    },
    {
      "epoch": 5.171232876712328,
      "grad_norm": 0.353515625,
      "learning_rate": 0.0001656720392508094,
      "loss": 0.9744,
      "step": 755
    },
    {
      "epoch": 5.205479452054795,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00016506894986130171,
      "loss": 0.9736,
      "step": 760
    },
    {
      "epoch": 5.239726027397261,
      "grad_norm": 0.486328125,
      "learning_rate": 0.00016446172773254629,
      "loss": 0.972,
      "step": 765
    },
    {
      "epoch": 5.273972602739726,
      "grad_norm": 0.470703125,
      "learning_rate": 0.00016385041143118255,
      "loss": 0.9813,
      "step": 770
    },
    {
      "epoch": 5.308219178082192,
      "grad_norm": 0.5546875,
      "learning_rate": 0.000163235039783884,
      "loss": 0.9855,
      "step": 775
    },
    {
      "epoch": 5.342465753424658,
      "grad_norm": 0.462890625,
      "learning_rate": 0.0001626156518748922,
      "loss": 0.9765,
      "step": 780
    },
    {
      "epoch": 5.376712328767123,
      "grad_norm": 0.59375,
      "learning_rate": 0.00016199228704353455,
      "loss": 0.9876,
      "step": 785
    },
    {
      "epoch": 5.410958904109589,
      "grad_norm": 0.53125,
      "learning_rate": 0.00016136498488172568,
      "loss": 0.9772,
      "step": 790
    },
    {
      "epoch": 5.445205479452055,
      "grad_norm": 0.3984375,
      "learning_rate": 0.0001607337852314527,
      "loss": 0.9861,
      "step": 795
    },
    {
      "epoch": 5.47945205479452,
      "grad_norm": 0.3671875,
      "learning_rate": 0.00016009872818224485,
      "loss": 0.9879,
      "step": 800
    },
    {
      "epoch": 5.513698630136986,
      "grad_norm": 0.357421875,
      "learning_rate": 0.00015945985406862721,
      "loss": 0.9821,
      "step": 805
    },
    {
      "epoch": 5.5479452054794525,
      "grad_norm": 0.4375,
      "learning_rate": 0.00015881720346755905,
      "loss": 0.9748,
      "step": 810
    },
    {
      "epoch": 5.582191780821918,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00015817081719585643,
      "loss": 0.9726,
      "step": 815
    },
    {
      "epoch": 5.616438356164384,
      "grad_norm": 0.37890625,
      "learning_rate": 0.00015752073630759998,
      "loss": 0.9918,
      "step": 820
    },
    {
      "epoch": 5.6506849315068495,
      "grad_norm": 0.419921875,
      "learning_rate": 0.00015686700209152738,
      "loss": 0.9775,
      "step": 825
    },
    {
      "epoch": 5.684931506849315,
      "grad_norm": 0.33203125,
      "learning_rate": 0.00015620965606841098,
      "loss": 0.9734,
      "step": 830
    },
    {
      "epoch": 5.719178082191781,
      "grad_norm": 0.37890625,
      "learning_rate": 0.0001555487399884206,
      "loss": 0.9753,
      "step": 835
    },
    {
      "epoch": 5.7534246575342465,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00015488429582847192,
      "loss": 0.9701,
      "step": 840
    },
    {
      "epoch": 5.787671232876712,
      "grad_norm": 0.357421875,
      "learning_rate": 0.0001542163657895605,
      "loss": 0.9726,
      "step": 845
    },
    {
      "epoch": 5.821917808219178,
      "grad_norm": 0.4375,
      "learning_rate": 0.00015354499229408114,
      "loss": 0.9755,
      "step": 850
    },
    {
      "epoch": 5.8561643835616435,
      "grad_norm": 0.50390625,
      "learning_rate": 0.0001528702179831338,
      "loss": 0.9733,
      "step": 855
    },
    {
      "epoch": 5.890410958904109,
      "grad_norm": 0.419921875,
      "learning_rate": 0.00015219208571381525,
      "loss": 0.9795,
      "step": 860
    },
    {
      "epoch": 5.924657534246576,
      "grad_norm": 0.466796875,
      "learning_rate": 0.00015151063855649698,
      "loss": 0.9906,
      "step": 865
    },
    {
      "epoch": 5.958904109589041,
      "grad_norm": 0.35546875,
      "learning_rate": 0.00015082591979208976,
      "loss": 0.983,
      "step": 870
    },
    {
      "epoch": 5.993150684931507,
      "grad_norm": 0.51953125,
      "learning_rate": 0.00015013797290929466,
      "loss": 0.9823,
      "step": 875
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.5500409603118896,
      "eval_runtime": 0.5455,
      "eval_samples_per_second": 18.332,
      "eval_steps_per_second": 1.833,
      "step": 876
    },
    {
      "epoch": 6.027397260273973,
      "grad_norm": 0.380859375,
      "learning_rate": 0.00014944684160184108,
      "loss": 0.9588,
      "step": 880
    },
    {
      "epoch": 6.061643835616438,
      "grad_norm": 0.435546875,
      "learning_rate": 0.00014875256976571135,
      "loss": 0.9449,
      "step": 885
    },
    {
      "epoch": 6.095890410958904,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00014805520149635307,
      "loss": 0.9336,
      "step": 890
    },
    {
      "epoch": 6.13013698630137,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00014735478108587828,
      "loss": 0.9428,
      "step": 895
    },
    {
      "epoch": 6.164383561643835,
      "grad_norm": 0.578125,
      "learning_rate": 0.00014665135302025035,
      "loss": 0.9457,
      "step": 900
    },
    {
      "epoch": 6.198630136986301,
      "grad_norm": 0.375,
      "learning_rate": 0.00014594496197645852,
      "loss": 0.9425,
      "step": 905
    },
    {
      "epoch": 6.232876712328767,
      "grad_norm": 0.361328125,
      "learning_rate": 0.0001452356528196804,
      "loss": 0.9492,
      "step": 910
    },
    {
      "epoch": 6.267123287671233,
      "grad_norm": 0.34375,
      "learning_rate": 0.00014452347060043237,
      "loss": 0.9542,
      "step": 915
    },
    {
      "epoch": 6.301369863013699,
      "grad_norm": 0.375,
      "learning_rate": 0.00014380846055170828,
      "loss": 0.9488,
      "step": 920
    },
    {
      "epoch": 6.335616438356165,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00014309066808610655,
      "loss": 0.9532,
      "step": 925
    },
    {
      "epoch": 6.36986301369863,
      "grad_norm": 0.451171875,
      "learning_rate": 0.0001423701387929459,
      "loss": 0.954,
      "step": 930
    },
    {
      "epoch": 6.404109589041096,
      "grad_norm": 0.361328125,
      "learning_rate": 0.00014164691843536982,
      "loss": 0.9513,
      "step": 935
    },
    {
      "epoch": 6.438356164383562,
      "grad_norm": 0.4375,
      "learning_rate": 0.00014092105294744,
      "loss": 0.954,
      "step": 940
    },
    {
      "epoch": 6.472602739726027,
      "grad_norm": 0.404296875,
      "learning_rate": 0.00014019258843121893,
      "loss": 0.9549,
      "step": 945
    },
    {
      "epoch": 6.506849315068493,
      "grad_norm": 0.38671875,
      "learning_rate": 0.0001394615711538417,
      "loss": 0.9509,
      "step": 950
    },
    {
      "epoch": 6.541095890410959,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00013872804754457759,
      "loss": 0.9556,
      "step": 955
    },
    {
      "epoch": 6.575342465753424,
      "grad_norm": 0.400390625,
      "learning_rate": 0.00013799206419188103,
      "loss": 0.9596,
      "step": 960
    },
    {
      "epoch": 6.609589041095891,
      "grad_norm": 0.37890625,
      "learning_rate": 0.00013725366784043288,
      "loss": 0.9532,
      "step": 965
    },
    {
      "epoch": 6.6438356164383565,
      "grad_norm": 0.361328125,
      "learning_rate": 0.00013651290538817113,
      "loss": 0.9547,
      "step": 970
    },
    {
      "epoch": 6.678082191780822,
      "grad_norm": 0.392578125,
      "learning_rate": 0.0001357698238833126,
      "loss": 0.9619,
      "step": 975
    },
    {
      "epoch": 6.712328767123288,
      "grad_norm": 0.38671875,
      "learning_rate": 0.00013502447052136455,
      "loss": 0.9457,
      "step": 980
    },
    {
      "epoch": 6.7465753424657535,
      "grad_norm": 0.384765625,
      "learning_rate": 0.00013427689264212738,
      "loss": 0.9595,
      "step": 985
    },
    {
      "epoch": 6.780821917808219,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00013352713772668765,
      "loss": 0.9501,
      "step": 990
    },
    {
      "epoch": 6.815068493150685,
      "grad_norm": 0.404296875,
      "learning_rate": 0.0001327752533944025,
      "loss": 0.9542,
      "step": 995
    },
    {
      "epoch": 6.8493150684931505,
      "grad_norm": 0.5546875,
      "learning_rate": 0.00013202128739987532,
      "loss": 0.957,
      "step": 1000
    },
    {
      "epoch": 6.883561643835616,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00013126528762992247,
      "loss": 0.9597,
      "step": 1005
    },
    {
      "epoch": 6.917808219178082,
      "grad_norm": 0.4140625,
      "learning_rate": 0.0001305073021005321,
      "loss": 0.9525,
      "step": 1010
    },
    {
      "epoch": 6.9520547945205475,
      "grad_norm": 0.400390625,
      "learning_rate": 0.0001297473789538142,
      "loss": 0.9554,
      "step": 1015
    },
    {
      "epoch": 6.986301369863014,
      "grad_norm": 0.37890625,
      "learning_rate": 0.00012898556645494325,
      "loss": 0.955,
      "step": 1020
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.5866098403930664,
      "eval_runtime": 0.5603,
      "eval_samples_per_second": 17.847,
      "eval_steps_per_second": 1.785,
      "step": 1022
    },
    {
      "epoch": 7.02054794520548,
      "grad_norm": 0.380859375,
      "learning_rate": 0.0001282219129890925,
      "loss": 0.9357,
      "step": 1025
    },
    {
      "epoch": 7.054794520547945,
      "grad_norm": 0.373046875,
      "learning_rate": 0.00012745646705836097,
      "loss": 0.9228,
      "step": 1030
    },
    {
      "epoch": 7.089041095890411,
      "grad_norm": 0.5390625,
      "learning_rate": 0.0001266892772786929,
      "loss": 0.9121,
      "step": 1035
    },
    {
      "epoch": 7.123287671232877,
      "grad_norm": 0.37109375,
      "learning_rate": 0.0001259203923767901,
      "loss": 0.9181,
      "step": 1040
    },
    {
      "epoch": 7.157534246575342,
      "grad_norm": 0.37109375,
      "learning_rate": 0.00012514986118701695,
      "loss": 0.9176,
      "step": 1045
    },
    {
      "epoch": 7.191780821917808,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00012437773264829897,
      "loss": 0.9241,
      "step": 1050
    },
    {
      "epoch": 7.226027397260274,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00012360405580101448,
      "loss": 0.9287,
      "step": 1055
    },
    {
      "epoch": 7.260273972602739,
      "grad_norm": 0.375,
      "learning_rate": 0.00012282887978387976,
      "loss": 0.9347,
      "step": 1060
    },
    {
      "epoch": 7.294520547945205,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00012205225383082843,
      "loss": 0.9275,
      "step": 1065
    },
    {
      "epoch": 7.328767123287671,
      "grad_norm": 0.404296875,
      "learning_rate": 0.000121274227267884,
      "loss": 0.923,
      "step": 1070
    },
    {
      "epoch": 7.363013698630137,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00012049484951002739,
      "loss": 0.9332,
      "step": 1075
    },
    {
      "epoch": 7.397260273972603,
      "grad_norm": 0.37890625,
      "learning_rate": 0.00011971417005805818,
      "loss": 0.9238,
      "step": 1080
    },
    {
      "epoch": 7.431506849315069,
      "grad_norm": 0.37109375,
      "learning_rate": 0.00011893223849545084,
      "loss": 0.9278,
      "step": 1085
    },
    {
      "epoch": 7.465753424657534,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00011814910448520536,
      "loss": 0.9268,
      "step": 1090
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.404296875,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.931,
      "step": 1095
    },
    {
      "epoch": 7.534246575342466,
      "grad_norm": 0.390625,
      "learning_rate": 0.00011657942815249754,
      "loss": 0.9283,
      "step": 1100
    },
    {
      "epoch": 7.568493150684931,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00011579298552525084,
      "loss": 0.9246,
      "step": 1105
    },
    {
      "epoch": 7.602739726027397,
      "grad_norm": 0.390625,
      "learning_rate": 0.00011500553983446527,
      "loss": 0.9293,
      "step": 1110
    },
    {
      "epoch": 7.636986301369863,
      "grad_norm": 0.365234375,
      "learning_rate": 0.00011421714109336097,
      "loss": 0.9335,
      "step": 1115
    },
    {
      "epoch": 7.671232876712329,
      "grad_norm": 0.453125,
      "learning_rate": 0.00011342783937568926,
      "loss": 0.9359,
      "step": 1120
    },
    {
      "epoch": 7.705479452054795,
      "grad_norm": 0.416015625,
      "learning_rate": 0.00011263768481255264,
      "loss": 0.9295,
      "step": 1125
    },
    {
      "epoch": 7.739726027397261,
      "grad_norm": 0.380859375,
      "learning_rate": 0.00011184672758922034,
      "loss": 0.9404,
      "step": 1130
    },
    {
      "epoch": 7.773972602739726,
      "grad_norm": 0.396484375,
      "learning_rate": 0.00011105501794194131,
      "loss": 0.9289,
      "step": 1135
    },
    {
      "epoch": 7.808219178082192,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00011026260615475333,
      "loss": 0.9409,
      "step": 1140
    },
    {
      "epoch": 7.842465753424658,
      "grad_norm": 0.396484375,
      "learning_rate": 0.00010946954255628928,
      "loss": 0.9355,
      "step": 1145
    },
    {
      "epoch": 7.876712328767123,
      "grad_norm": 0.443359375,
      "learning_rate": 0.00010867587751658079,
      "loss": 0.9257,
      "step": 1150
    },
    {
      "epoch": 7.910958904109589,
      "grad_norm": 0.365234375,
      "learning_rate": 0.00010788166144385888,
      "loss": 0.924,
      "step": 1155
    },
    {
      "epoch": 7.945205479452055,
      "grad_norm": 0.427734375,
      "learning_rate": 0.0001070869447813525,
      "loss": 0.9202,
      "step": 1160
    },
    {
      "epoch": 7.97945205479452,
      "grad_norm": 0.3515625,
      "learning_rate": 0.0001062917780040847,
      "loss": 0.9214,
      "step": 1165
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.6224260330200195,
      "eval_runtime": 0.5566,
      "eval_samples_per_second": 17.965,
      "eval_steps_per_second": 1.797,
      "step": 1168
    },
    {
      "epoch": 8.013698630136986,
      "grad_norm": 0.388671875,
      "learning_rate": 0.0001054962116156667,
      "loss": 0.9133,
      "step": 1170
    },
    {
      "epoch": 8.047945205479452,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00010470029614509041,
      "loss": 0.8952,
      "step": 1175
    },
    {
      "epoch": 8.082191780821917,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00010390408214351892,
      "loss": 0.8963,
      "step": 1180
    },
    {
      "epoch": 8.116438356164384,
      "grad_norm": 0.388671875,
      "learning_rate": 0.0001031076201810762,
      "loss": 0.8996,
      "step": 1185
    },
    {
      "epoch": 8.150684931506849,
      "grad_norm": 0.38671875,
      "learning_rate": 0.00010231096084363483,
      "loss": 0.8898,
      "step": 1190
    },
    {
      "epoch": 8.184931506849315,
      "grad_norm": 0.390625,
      "learning_rate": 0.00010151415472960342,
      "loss": 0.9138,
      "step": 1195
    },
    {
      "epoch": 8.219178082191782,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00010071725244671282,
      "loss": 0.9023,
      "step": 1200
    },
    {
      "epoch": 8.253424657534246,
      "grad_norm": 0.388671875,
      "learning_rate": 9.992030460880181e-05,
      "loss": 0.8929,
      "step": 1205
    },
    {
      "epoch": 8.287671232876713,
      "grad_norm": 0.392578125,
      "learning_rate": 9.91233618326026e-05,
      "loss": 0.9089,
      "step": 1210
    },
    {
      "epoch": 8.321917808219178,
      "grad_norm": 0.41015625,
      "learning_rate": 9.83264747345259e-05,
      "loss": 0.9037,
      "step": 1215
    },
    {
      "epoch": 8.356164383561644,
      "grad_norm": 0.369140625,
      "learning_rate": 9.752969392744606e-05,
      "loss": 0.9062,
      "step": 1220
    },
    {
      "epoch": 8.39041095890411,
      "grad_norm": 0.40234375,
      "learning_rate": 9.673307001748661e-05,
      "loss": 0.8982,
      "step": 1225
    },
    {
      "epoch": 8.424657534246576,
      "grad_norm": 0.392578125,
      "learning_rate": 9.593665360080599e-05,
      "loss": 0.8994,
      "step": 1230
    },
    {
      "epoch": 8.45890410958904,
      "grad_norm": 0.4140625,
      "learning_rate": 9.514049526038418e-05,
      "loss": 0.9045,
      "step": 1235
    },
    {
      "epoch": 8.493150684931507,
      "grad_norm": 0.400390625,
      "learning_rate": 9.43446455628097e-05,
      "loss": 0.9062,
      "step": 1240
    },
    {
      "epoch": 8.527397260273972,
      "grad_norm": 0.427734375,
      "learning_rate": 9.354915505506839e-05,
      "loss": 0.9056,
      "step": 1245
    },
    {
      "epoch": 8.561643835616438,
      "grad_norm": 0.3828125,
      "learning_rate": 9.27540742613326e-05,
      "loss": 0.9078,
      "step": 1250
    },
    {
      "epoch": 8.595890410958905,
      "grad_norm": 0.431640625,
      "learning_rate": 9.195945367975256e-05,
      "loss": 0.8994,
      "step": 1255
    },
    {
      "epoch": 8.63013698630137,
      "grad_norm": 0.404296875,
      "learning_rate": 9.116534377924883e-05,
      "loss": 0.9088,
      "step": 1260
    },
    {
      "epoch": 8.664383561643836,
      "grad_norm": 0.44921875,
      "learning_rate": 9.037179499630703e-05,
      "loss": 0.9035,
      "step": 1265
    },
    {
      "epoch": 8.698630136986301,
      "grad_norm": 0.40625,
      "learning_rate": 8.957885773177438e-05,
      "loss": 0.9178,
      "step": 1270
    },
    {
      "epoch": 8.732876712328768,
      "grad_norm": 0.51953125,
      "learning_rate": 8.878658234765858e-05,
      "loss": 0.9062,
      "step": 1275
    },
    {
      "epoch": 8.767123287671232,
      "grad_norm": 0.486328125,
      "learning_rate": 8.799501916392912e-05,
      "loss": 0.9157,
      "step": 1280
    },
    {
      "epoch": 8.801369863013699,
      "grad_norm": 0.392578125,
      "learning_rate": 8.720421845532151e-05,
      "loss": 0.912,
      "step": 1285
    },
    {
      "epoch": 8.835616438356164,
      "grad_norm": 0.37109375,
      "learning_rate": 8.641423044814374e-05,
      "loss": 0.9085,
      "step": 1290
    },
    {
      "epoch": 8.86986301369863,
      "grad_norm": 0.396484375,
      "learning_rate": 8.562510531708677e-05,
      "loss": 0.9158,
      "step": 1295
    },
    {
      "epoch": 8.904109589041095,
      "grad_norm": 0.384765625,
      "learning_rate": 8.48368931820373e-05,
      "loss": 0.909,
      "step": 1300
    },
    {
      "epoch": 8.938356164383562,
      "grad_norm": 0.39453125,
      "learning_rate": 8.404964410489485e-05,
      "loss": 0.9121,
      "step": 1305
    },
    {
      "epoch": 8.972602739726028,
      "grad_norm": 0.39453125,
      "learning_rate": 8.32634080863919e-05,
      "loss": 0.913,
      "step": 1310
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.6512458324432373,
      "eval_runtime": 0.5534,
      "eval_samples_per_second": 18.07,
      "eval_steps_per_second": 1.807,
      "step": 1314
    },
    {
      "epoch": 9.006849315068493,
      "grad_norm": 0.408203125,
      "learning_rate": 8.247823506291844e-05,
      "loss": 0.9034,
      "step": 1315
    },
    {
      "epoch": 9.04109589041096,
      "grad_norm": 0.404296875,
      "learning_rate": 8.169417490335007e-05,
      "loss": 0.8821,
      "step": 1320
    },
    {
      "epoch": 9.075342465753424,
      "grad_norm": 0.416015625,
      "learning_rate": 8.091127740588094e-05,
      "loss": 0.8702,
      "step": 1325
    },
    {
      "epoch": 9.10958904109589,
      "grad_norm": 0.39453125,
      "learning_rate": 8.012959229486061e-05,
      "loss": 0.8755,
      "step": 1330
    },
    {
      "epoch": 9.143835616438356,
      "grad_norm": 0.43359375,
      "learning_rate": 7.934916921763628e-05,
      "loss": 0.8783,
      "step": 1335
    },
    {
      "epoch": 9.178082191780822,
      "grad_norm": 0.421875,
      "learning_rate": 7.857005774139907e-05,
      "loss": 0.8794,
      "step": 1340
    },
    {
      "epoch": 9.212328767123287,
      "grad_norm": 0.400390625,
      "learning_rate": 7.779230735003628e-05,
      "loss": 0.8844,
      "step": 1345
    },
    {
      "epoch": 9.246575342465754,
      "grad_norm": 0.3984375,
      "learning_rate": 7.701596744098818e-05,
      "loss": 0.8775,
      "step": 1350
    },
    {
      "epoch": 9.280821917808218,
      "grad_norm": 0.404296875,
      "learning_rate": 7.624108732211081e-05,
      "loss": 0.8705,
      "step": 1355
    },
    {
      "epoch": 9.315068493150685,
      "grad_norm": 0.408203125,
      "learning_rate": 7.54677162085442e-05,
      "loss": 0.8897,
      "step": 1360
    },
    {
      "epoch": 9.349315068493151,
      "grad_norm": 0.3984375,
      "learning_rate": 7.469590321958662e-05,
      "loss": 0.882,
      "step": 1365
    },
    {
      "epoch": 9.383561643835616,
      "grad_norm": 0.43359375,
      "learning_rate": 7.392569737557474e-05,
      "loss": 0.8879,
      "step": 1370
    },
    {
      "epoch": 9.417808219178083,
      "grad_norm": 0.416015625,
      "learning_rate": 7.31571475947703e-05,
      "loss": 0.8827,
      "step": 1375
    },
    {
      "epoch": 9.452054794520548,
      "grad_norm": 0.412109375,
      "learning_rate": 7.239030269025311e-05,
      "loss": 0.8805,
      "step": 1380
    },
    {
      "epoch": 9.486301369863014,
      "grad_norm": 0.408203125,
      "learning_rate": 7.162521136682085e-05,
      "loss": 0.8966,
      "step": 1385
    },
    {
      "epoch": 9.520547945205479,
      "grad_norm": 0.431640625,
      "learning_rate": 7.08619222178954e-05,
      "loss": 0.8895,
      "step": 1390
    },
    {
      "epoch": 9.554794520547945,
      "grad_norm": 0.423828125,
      "learning_rate": 7.010048372243698e-05,
      "loss": 0.8907,
      "step": 1395
    },
    {
      "epoch": 9.58904109589041,
      "grad_norm": 0.42578125,
      "learning_rate": 6.934094424186459e-05,
      "loss": 0.8876,
      "step": 1400
    },
    {
      "epoch": 9.623287671232877,
      "grad_norm": 0.39453125,
      "learning_rate": 6.858335201698485e-05,
      "loss": 0.8936,
      "step": 1405
    },
    {
      "epoch": 9.657534246575342,
      "grad_norm": 0.451171875,
      "learning_rate": 6.782775516492771e-05,
      "loss": 0.8804,
      "step": 1410
    },
    {
      "epoch": 9.691780821917808,
      "grad_norm": 0.40234375,
      "learning_rate": 6.70742016760907e-05,
      "loss": 0.8907,
      "step": 1415
    },
    {
      "epoch": 9.726027397260275,
      "grad_norm": 0.4453125,
      "learning_rate": 6.632273941109064e-05,
      "loss": 0.8756,
      "step": 1420
    },
    {
      "epoch": 9.76027397260274,
      "grad_norm": 0.40625,
      "learning_rate": 6.5573416097724e-05,
      "loss": 0.8963,
      "step": 1425
    },
    {
      "epoch": 9.794520547945206,
      "grad_norm": 0.412109375,
      "learning_rate": 6.482627932793553e-05,
      "loss": 0.8998,
      "step": 1430
    },
    {
      "epoch": 9.82876712328767,
      "grad_norm": 0.419921875,
      "learning_rate": 6.408137655479554e-05,
      "loss": 0.9024,
      "step": 1435
    },
    {
      "epoch": 9.863013698630137,
      "grad_norm": 0.421875,
      "learning_rate": 6.333875508948593e-05,
      "loss": 0.8921,
      "step": 1440
    },
    {
      "epoch": 9.897260273972602,
      "grad_norm": 0.45703125,
      "learning_rate": 6.259846209829551e-05,
      "loss": 0.904,
      "step": 1445
    },
    {
      "epoch": 9.931506849315069,
      "grad_norm": 0.4140625,
      "learning_rate": 6.186054459962399e-05,
      "loss": 0.8899,
      "step": 1450
    },
    {
      "epoch": 9.965753424657533,
      "grad_norm": 0.40625,
      "learning_rate": 6.112504946099604e-05,
      "loss": 0.8875,
      "step": 1455
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.431640625,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.889,
      "step": 1460
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.6852145195007324,
      "eval_runtime": 0.5511,
      "eval_samples_per_second": 18.146,
      "eval_steps_per_second": 1.815,
      "step": 1460
    },
    {
      "epoch": 10.034246575342467,
      "grad_norm": 0.40625,
      "learning_rate": 5.966151296174268e-05,
      "loss": 0.8664,
      "step": 1465
    },
    {
      "epoch": 10.068493150684931,
      "grad_norm": 0.431640625,
      "learning_rate": 5.8933564555049105e-05,
      "loss": 0.8677,
      "step": 1470
    },
    {
      "epoch": 10.102739726027398,
      "grad_norm": 0.41796875,
      "learning_rate": 5.820822441035899e-05,
      "loss": 0.866,
      "step": 1475
    },
    {
      "epoch": 10.136986301369863,
      "grad_norm": 0.40625,
      "learning_rate": 5.7485538596368496e-05,
      "loss": 0.8664,
      "step": 1480
    },
    {
      "epoch": 10.17123287671233,
      "grad_norm": 0.41015625,
      "learning_rate": 5.6765553013188766e-05,
      "loss": 0.8645,
      "step": 1485
    },
    {
      "epoch": 10.205479452054794,
      "grad_norm": 0.400390625,
      "learning_rate": 5.6048313389430484e-05,
      "loss": 0.8624,
      "step": 1490
    },
    {
      "epoch": 10.23972602739726,
      "grad_norm": 0.408203125,
      "learning_rate": 5.533386527929962e-05,
      "loss": 0.874,
      "step": 1495
    },
    {
      "epoch": 10.273972602739725,
      "grad_norm": 0.40625,
      "learning_rate": 5.462225405970401e-05,
      "loss": 0.8708,
      "step": 1500
    },
    {
      "epoch": 10.273972602739725,
      "step": 1500,
      "total_flos": 8.853977907740017e+17,
      "train_loss": 0.0,
      "train_runtime": 2.8738,
      "train_samples_per_second": 24365.255,
      "train_steps_per_second": 508.044
    }
  ],
  "logging_steps": 5,
  "max_steps": 1460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.853977907740017e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}