{
  "best_metric": 1.004758358001709,
  "best_model_checkpoint": "output/morgenshtern/checkpoint-1300",
  "epoch": 13.0,
  "global_step": 1300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.00013638815138477438,
      "loss": 2.534,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013397182122930294,
      "loss": 2.1207,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001300082017869573,
      "loss": 1.9437,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012459110818763681,
      "loss": 2.0463,
      "step": 20
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.9048744440078735,
      "eval_runtime": 2.5437,
      "eval_samples_per_second": 44.03,
      "eval_steps_per_second": 5.504,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00011784875792222071,
      "loss": 1.953,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000109940736055617,
      "loss": 2.0751,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001010542179989503,
      "loss": 1.9436,
      "step": 35
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.139953924430466e-05,
      "loss": 1.8745,
      "step": 40
    },
    {
      "epoch": 0.39,
      "eval_loss": 1.7966899871826172,
      "eval_runtime": 2.5987,
      "eval_samples_per_second": 43.099,
      "eval_steps_per_second": 5.387,
      "step": 40
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.120521692221673e-05,
      "loss": 1.8989,
      "step": 45
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.071254101695329e-05,
      "loss": 1.8346,
      "step": 50
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.016986326040062e-05,
      "loss": 1.8576,
      "step": 55
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.982671888105512e-05,
      "loss": 1.8876,
      "step": 60
    },
    {
      "epoch": 0.59,
      "eval_loss": 1.760327935218811,
      "eval_runtime": 2.6932,
      "eval_samples_per_second": 41.586,
      "eval_steps_per_second": 5.198,
      "step": 60
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.992792034076668e-05,
      "loss": 1.7386,
      "step": 65
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0707762854909304e-05,
      "loss": 1.9309,
      "step": 70
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.2384478845846175e-05,
      "loss": 1.6283,
      "step": 75
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.5155072587539005e-05,
      "loss": 1.9742,
      "step": 80
    },
    {
      "epoch": 0.78,
      "eval_loss": 1.7276561260223389,
      "eval_runtime": 2.6936,
      "eval_samples_per_second": 41.581,
      "eval_steps_per_second": 5.198,
      "step": 80
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.190657300387505e-06,
      "loss": 1.8267,
      "step": 85
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.6324050628611986e-06,
      "loss": 1.7887,
      "step": 90
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5882054016913933e-06,
      "loss": 1.8381,
      "step": 95
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3011164863877445e-07,
      "loss": 1.8954,
      "step": 100
    },
    {
      "epoch": 0.98,
      "eval_loss": 1.7208999395370483,
      "eval_runtime": 2.7574,
      "eval_samples_per_second": 40.618,
      "eval_steps_per_second": 5.077,
      "step": 100
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.0216830127274476e-06,
      "loss": 1.8376,
      "step": 105
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.037005536513067e-07,
      "loss": 1.7024,
      "step": 110
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.515656508272057e-08,
      "loss": 1.7911,
      "step": 115
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.0213613921093164e-07,
      "loss": 1.8512,
      "step": 120
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.0277372298297e-06,
      "loss": 1.7573,
      "step": 125
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.8721970205680935e-06,
      "loss": 1.7902,
      "step": 130
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.88343684654658e-06,
      "loss": 1.7602,
      "step": 135
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.3988015692592823e-05,
      "loss": 1.8606,
      "step": 140
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.009247481060283e-05,
      "loss": 1.6102,
      "step": 145
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.708504883770769e-05,
      "loss": 1.8574,
      "step": 150
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.483771208671411e-05,
      "loss": 1.6927,
      "step": 155
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.320852254368187e-05,
      "loss": 1.7203,
      "step": 160
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.204422065684016e-05,
      "loss": 1.8592,
      "step": 165
    },
    {
      "epoch": 1.47,
      "learning_rate": 6.118303533611755e-05,
      "loss": 1.7338,
      "step": 170
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.045764578878282e-05,
      "loss": 1.7386,
      "step": 175
    },
    {
      "epoch": 1.55,
      "learning_rate": 7.969824496351964e-05,
      "loss": 1.6874,
      "step": 180
    },
    {
      "epoch": 1.59,
      "learning_rate": 8.873564851492995e-05,
      "loss": 1.8691,
      "step": 185
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.740439236703416e-05,
      "loss": 1.7808,
      "step": 190
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00010554576216307802,
      "loss": 1.8296,
      "step": 195
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00011301069913603334,
      "loss": 1.737,
      "step": 200
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001196625291967717,
      "loss": 1.8,
      "step": 205
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00012537946527356269,
      "loss": 1.6787,
      "step": 210
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.000130056837088046,
      "loss": 1.664,
      "step": 215
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00013360900754314024,
      "loss": 1.5839,
      "step": 220
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001359709406361119,
      "loss": 1.8525,
      "step": 225
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001370993921901871,
      "loss": 1.7228,
      "step": 230
    },
    {
      "epoch": 2.4,
      "learning_rate": 9.021642375642038e-05,
      "loss": 1.6079,
      "step": 235
    },
    {
      "epoch": 2.45,
      "learning_rate": 7.954855279928984e-05,
      "loss": 1.6691,
      "step": 240
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 1.7047,
      "step": 245
    },
    {
      "epoch": 2.55,
      "learning_rate": 5.765144720071019e-05,
      "loss": 1.6921,
      "step": 250
    },
    {
      "epoch": 2.6,
      "learning_rate": 4.698357624357961e-05,
      "loss": 1.5894,
      "step": 255
    },
    {
      "epoch": 2.65,
      "learning_rate": 3.686987328947878e-05,
      "loss": 1.6388,
      "step": 260
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.7569617608302645e-05,
      "loss": 1.6748,
      "step": 265
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.932123458329584e-05,
      "loss": 1.6765,
      "step": 270
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.233618333464885e-05,
      "loss": 1.6658,
      "step": 275
    },
    {
      "epoch": 2.86,
      "learning_rate": 6.793535661894062e-06,
      "loss": 1.5677,
      "step": 280
    },
    {
      "epoch": 2.91,
      "learning_rate": 2.8353852816850843e-06,
      "loss": 1.6118,
      "step": 285
    },
    {
      "epoch": 2.96,
      "learning_rate": 5.632050517253132e-07,
      "loss": 1.552,
      "step": 290
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.546966552734375,
      "eval_runtime": 6.307,
      "eval_samples_per_second": 22.99,
      "eval_steps_per_second": 3.013,
      "step": 294
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.52455686328105e-08,
      "loss": 1.4805,
      "step": 295
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.2650418304129032e-06,
      "loss": 1.6327,
      "step": 300
    },
    {
      "epoch": 3.11,
      "learning_rate": 4.221066247386418e-06,
      "loss": 1.7416,
      "step": 305
    },
    {
      "epoch": 3.16,
      "learning_rate": 8.827536897135471e-06,
      "loss": 1.6078,
      "step": 310
    },
    {
      "epoch": 3.21,
      "learning_rate": 1.496636030269314e-05,
      "loss": 1.5727,
      "step": 315
    },
    {
      "epoch": 3.27,
      "learning_rate": 2.2480158928073662e-05,
      "loss": 1.6548,
      "step": 320
    },
    {
      "epoch": 3.32,
      "learning_rate": 3.117630577695637e-05,
      "loss": 1.596,
      "step": 325
    },
    {
      "epoch": 3.37,
      "learning_rate": 4.08318626618038e-05,
      "loss": 1.4367,
      "step": 330
    },
    {
      "epoch": 3.42,
      "learning_rate": 5.119929554380771e-05,
      "loss": 1.621,
      "step": 335
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.201282042273297e-05,
      "loss": 1.7111,
      "step": 340
    },
    {
      "epoch": 3.52,
      "learning_rate": 7.299521709067686e-05,
      "loss": 1.6959,
      "step": 345
    },
    {
      "epoch": 3.57,
      "learning_rate": 8.386493606940314e-05,
      "loss": 1.7452,
      "step": 350
    },
    {
      "epoch": 3.62,
      "learning_rate": 9.434331653472505e-05,
      "loss": 1.6352,
      "step": 355
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.00010416173018610202,
      "loss": 1.5285,
      "step": 360
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.00011306846791811431,
      "loss": 1.7379,
      "step": 365
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.00012083519274412256,
      "loss": 1.7212,
      "step": 370
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0001272627935421667,
      "loss": 1.6984,
      "step": 375
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.00013218648955393709,
      "loss": 1.5563,
      "step": 380
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001354800547756731,
      "loss": 1.6133,
      "step": 385
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00013705905394267309,
      "loss": 1.6524,
      "step": 390
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.4850682020187378,
      "eval_runtime": 6.9944,
      "eval_samples_per_second": 21.303,
      "eval_steps_per_second": 2.716,
      "step": 392
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.000136883007148315,
      "loss": 1.6487,
      "step": 395
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00013495642760447742,
      "loss": 1.5179,
      "step": 400
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.00013132870593888477,
      "loss": 1.3698,
      "step": 405
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00012609284399558033,
      "loss": 1.6439,
      "step": 410
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.00011938307059936668,
      "loss": 1.5471,
      "step": 415
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.00011137140040750914,
      "loss": 1.6368,
      "step": 420
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.00010226322406747016,
      "loss": 1.5678,
      "step": 425
    },
    {
      "epoch": 4.39,
      "learning_rate": 9.229204273330182e-05,
      "loss": 1.6766,
      "step": 430
    },
    {
      "epoch": 4.44,
      "learning_rate": 8.171348192891424e-05,
      "loss": 1.6611,
      "step": 435
    },
    {
      "epoch": 4.49,
      "learning_rate": 7.079873822141565e-05,
      "loss": 1.6183,
      "step": 440
    },
    {
      "epoch": 4.54,
      "learning_rate": 5.982762670844296e-05,
      "loss": 1.5438,
      "step": 445
    },
    {
      "epoch": 4.59,
      "learning_rate": 4.908140755711112e-05,
      "loss": 1.6215,
      "step": 450
    },
    {
      "epoch": 4.64,
      "learning_rate": 3.883557549653544e-05,
      "loss": 1.5207,
      "step": 455
    },
    {
      "epoch": 4.69,
      "learning_rate": 2.9352797115619177e-05,
      "loss": 1.4362,
      "step": 460
    },
    {
      "epoch": 4.74,
      "learning_rate": 2.0876177028600835e-05,
      "loss": 1.5917,
      "step": 465
    },
    {
      "epoch": 4.8,
      "learning_rate": 1.3623025539858168e-05,
      "loss": 1.4801,
      "step": 470
    },
    {
      "epoch": 4.85,
      "learning_rate": 7.779287582812185e-06,
      "loss": 1.4835,
      "step": 475
    },
    {
      "epoch": 4.9,
      "learning_rate": 3.494775755068154e-06,
      "loss": 1.5351,
      "step": 480
    },
    {
      "epoch": 4.95,
      "learning_rate": 8.793296577687332e-07,
      "loss": 1.4665,
      "step": 485
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 1.5628,
      "step": 490
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.417140007019043,
      "eval_runtime": 6.9215,
      "eval_samples_per_second": 21.527,
      "eval_steps_per_second": 2.745,
      "step": 490
    },
    {
      "epoch": 5.05,
      "learning_rate": 8.79329657768718e-07,
      "loss": 1.3775,
      "step": 495
    },
    {
      "epoch": 5.1,
      "learning_rate": 3.4947757550681237e-06,
      "loss": 1.5294,
      "step": 500
    },
    {
      "epoch": 5.15,
      "learning_rate": 7.7792875828122e-06,
      "loss": 1.436,
      "step": 505
    },
    {
      "epoch": 5.2,
      "learning_rate": 1.3623025539858192e-05,
      "loss": 1.5282,
      "step": 510
    },
    {
      "epoch": 5.26,
      "learning_rate": 2.087617702860069e-05,
      "loss": 1.5277,
      "step": 515
    },
    {
      "epoch": 5.31,
      "learning_rate": 2.9352797115619008e-05,
      "loss": 1.6218,
      "step": 520
    },
    {
      "epoch": 5.36,
      "learning_rate": 3.8835575496535365e-05,
      "loss": 1.4628,
      "step": 525
    },
    {
      "epoch": 5.41,
      "learning_rate": 4.9081407557111025e-05,
      "loss": 1.4702,
      "step": 530
    },
    {
      "epoch": 5.46,
      "learning_rate": 5.9827626708442996e-05,
      "loss": 1.3757,
      "step": 535
    },
    {
      "epoch": 5.51,
      "learning_rate": 7.079873822141567e-05,
      "loss": 1.3535,
      "step": 540
    },
    {
      "epoch": 5.56,
      "learning_rate": 8.171348192891405e-05,
      "loss": 1.4668,
      "step": 545
    },
    {
      "epoch": 5.61,
      "learning_rate": 9.229204273330163e-05,
      "loss": 1.4463,
      "step": 550
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.00010226322406747008,
      "loss": 1.3922,
      "step": 555
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.00011137140040750908,
      "loss": 1.4607,
      "step": 560
    },
    {
      "epoch": 5.77,
      "learning_rate": 0.00011938307059936662,
      "loss": 1.533,
      "step": 565
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.00012609284399558025,
      "loss": 1.5392,
      "step": 570
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.00013132870593888474,
      "loss": 1.6347,
      "step": 575
    },
    {
      "epoch": 5.92,
      "learning_rate": 0.00013495642760447742,
      "loss": 1.6022,
      "step": 580
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.000136883007148315,
      "loss": 1.4927,
      "step": 585
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.4285378456115723,
      "eval_runtime": 6.9515,
      "eval_samples_per_second": 21.434,
      "eval_steps_per_second": 2.733,
      "step": 588
    },
    {
      "epoch": 6.02,
      "learning_rate": 0.00013705905394267309,
      "loss": 1.415,
      "step": 590
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00013548005477567314,
      "loss": 1.4139,
      "step": 595
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.00013218648955393714,
      "loss": 1.522,
      "step": 600
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00012726279354216682,
      "loss": 1.4313,
      "step": 605
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0001208351927441227,
      "loss": 1.3831,
      "step": 610
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00011306846791811419,
      "loss": 1.4225,
      "step": 615
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.0001041617301861021,
      "loss": 1.5253,
      "step": 620
    },
    {
      "epoch": 6.38,
      "learning_rate": 9.434331653472514e-05,
      "loss": 1.3459,
      "step": 625
    },
    {
      "epoch": 6.43,
      "learning_rate": 8.386493606940322e-05,
      "loss": 1.3962,
      "step": 630
    },
    {
      "epoch": 6.48,
      "learning_rate": 7.299521709067695e-05,
      "loss": 1.3858,
      "step": 635
    },
    {
      "epoch": 6.53,
      "learning_rate": 6.201282042273305e-05,
      "loss": 1.4634,
      "step": 640
    },
    {
      "epoch": 6.58,
      "learning_rate": 5.11992955438078e-05,
      "loss": 1.4289,
      "step": 645
    },
    {
      "epoch": 6.63,
      "learning_rate": 4.0831862661803776e-05,
      "loss": 1.4365,
      "step": 650
    },
    {
      "epoch": 6.68,
      "learning_rate": 3.1176305776956335e-05,
      "loss": 1.4483,
      "step": 655
    },
    {
      "epoch": 6.73,
      "learning_rate": 2.248015892807363e-05,
      "loss": 1.387,
      "step": 660
    },
    {
      "epoch": 6.79,
      "learning_rate": 1.496636030269327e-05,
      "loss": 1.4562,
      "step": 665
    },
    {
      "epoch": 6.84,
      "learning_rate": 8.827536897135571e-06,
      "loss": 1.4136,
      "step": 670
    },
    {
      "epoch": 6.89,
      "learning_rate": 4.221066247386487e-06,
      "loss": 1.3972,
      "step": 675
    },
    {
      "epoch": 6.94,
      "learning_rate": 1.2650418304129413e-06,
      "loss": 1.4283,
      "step": 680
    },
    {
      "epoch": 6.99,
      "learning_rate": 3.5245568632818114e-08,
      "loss": 1.4148,
      "step": 685
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.388408899307251,
      "eval_runtime": 6.9772,
      "eval_samples_per_second": 21.355,
      "eval_steps_per_second": 2.723,
      "step": 686
    },
    {
      "epoch": 7.04,
      "learning_rate": 5.632050517253056e-07,
      "loss": 1.4365,
      "step": 690
    },
    {
      "epoch": 7.09,
      "learning_rate": 2.8353852816850615e-06,
      "loss": 1.2923,
      "step": 695
    },
    {
      "epoch": 7.14,
      "learning_rate": 6.793535661894024e-06,
      "loss": 1.3917,
      "step": 700
    },
    {
      "epoch": 7.19,
      "learning_rate": 1.2336183334648805e-05,
      "loss": 1.4588,
      "step": 705
    },
    {
      "epoch": 7.24,
      "learning_rate": 1.932123458329587e-05,
      "loss": 1.3238,
      "step": 710
    },
    {
      "epoch": 7.3,
      "learning_rate": 2.7569617608302577e-05,
      "loss": 1.3604,
      "step": 715
    },
    {
      "epoch": 7.35,
      "learning_rate": 3.686987328947871e-05,
      "loss": 1.3916,
      "step": 720
    },
    {
      "epoch": 7.4,
      "learning_rate": 4.698357624357965e-05,
      "loss": 1.3839,
      "step": 725
    },
    {
      "epoch": 7.45,
      "learning_rate": 5.7651447200710234e-05,
      "loss": 1.3886,
      "step": 730
    },
    {
      "epoch": 7.5,
      "learning_rate": 6.859999999999982e-05,
      "loss": 1.3475,
      "step": 735
    },
    {
      "epoch": 7.55,
      "learning_rate": 7.954855279928965e-05,
      "loss": 1.3304,
      "step": 740
    },
    {
      "epoch": 7.6,
      "learning_rate": 9.021642375642024e-05,
      "loss": 1.3287,
      "step": 745
    },
    {
      "epoch": 7.65,
      "learning_rate": 0.00010033012671052118,
      "loss": 1.4354,
      "step": 750
    },
    {
      "epoch": 7.7,
      "learning_rate": 0.00010963038239169733,
      "loss": 1.3597,
      "step": 755
    },
    {
      "epoch": 7.76,
      "learning_rate": 0.00011787876541670406,
      "loss": 1.3221,
      "step": 760
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.00012486381666535114,
      "loss": 1.3458,
      "step": 765
    },
    {
      "epoch": 7.86,
      "learning_rate": 0.00013040646433810593,
      "loss": 1.4032,
      "step": 770
    },
    {
      "epoch": 7.91,
      "learning_rate": 0.00013436461471831492,
      "loss": 1.403,
      "step": 775
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.00013663679494827467,
      "loss": 1.4234,
      "step": 780
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.4104630947113037,
      "eval_runtime": 6.9539,
      "eval_samples_per_second": 21.427,
      "eval_steps_per_second": 2.732,
      "step": 784
    },
    {
      "epoch": 8.01,
      "learning_rate": 0.0001371647544313672,
      "loss": 1.1334,
      "step": 785
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.0001359349581695871,
      "loss": 1.2244,
      "step": 790
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.00013297893375261365,
      "loss": 1.361,
      "step": 795
    },
    {
      "epoch": 8.16,
      "learning_rate": 0.00012837246310286448,
      "loss": 1.3544,
      "step": 800
    },
    {
      "epoch": 8.21,
      "learning_rate": 0.00012223363969730697,
      "loss": 1.1642,
      "step": 805
    },
    {
      "epoch": 8.27,
      "learning_rate": 0.00011471984107192647,
      "loss": 1.3799,
      "step": 810
    },
    {
      "epoch": 8.32,
      "learning_rate": 0.00010602369422304377,
      "loss": 1.3705,
      "step": 815
    },
    {
      "epoch": 8.37,
      "learning_rate": 9.636813733819635e-05,
      "loss": 1.2818,
      "step": 820
    },
    {
      "epoch": 8.42,
      "learning_rate": 8.600070445619209e-05,
      "loss": 1.3989,
      "step": 825
    },
    {
      "epoch": 8.47,
      "learning_rate": 7.518717957726708e-05,
      "loss": 1.2671,
      "step": 830
    },
    {
      "epoch": 8.52,
      "learning_rate": 6.420478290932294e-05,
      "loss": 1.359,
      "step": 835
    },
    {
      "epoch": 8.57,
      "learning_rate": 5.33350639305969e-05,
      "loss": 1.3868,
      "step": 840
    },
    {
      "epoch": 8.62,
      "learning_rate": 4.285668346527499e-05,
      "loss": 1.4007,
      "step": 845
    },
    {
      "epoch": 8.67,
      "learning_rate": 3.3038269813898015e-05,
      "loss": 1.351,
      "step": 850
    },
    {
      "epoch": 8.72,
      "learning_rate": 2.413153208188573e-05,
      "loss": 1.317,
      "step": 855
    },
    {
      "epoch": 8.78,
      "learning_rate": 1.636480725587754e-05,
      "loss": 1.2524,
      "step": 860
    },
    {
      "epoch": 8.83,
      "learning_rate": 9.937206457833243e-06,
      "loss": 1.3045,
      "step": 865
    },
    {
      "epoch": 8.88,
      "learning_rate": 5.013510446062984e-06,
      "loss": 1.4154,
      "step": 870
    },
    {
      "epoch": 8.93,
      "learning_rate": 1.719945224326892e-06,
      "loss": 1.2452,
      "step": 875
    },
    {
      "epoch": 8.98,
      "learning_rate": 1.4094605732693502e-07,
      "loss": 1.3688,
      "step": 880
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.3758981227874756,
      "eval_runtime": 6.9963,
      "eval_samples_per_second": 21.297,
      "eval_steps_per_second": 2.716,
      "step": 882
    },
    {
      "epoch": 9.03,
      "learning_rate": 3.169928516849862e-07,
      "loss": 1.4731,
      "step": 885
    },
    {
      "epoch": 9.08,
      "learning_rate": 2.2435723955225417e-06,
      "loss": 1.217,
      "step": 890
    },
    {
      "epoch": 9.13,
      "learning_rate": 5.8712940611152096e-06,
      "loss": 1.2492,
      "step": 895
    },
    {
      "epoch": 9.18,
      "learning_rate": 1.1107156004419803e-05,
      "loss": 1.2326,
      "step": 900
    },
    {
      "epoch": 9.23,
      "learning_rate": 1.7816929400633287e-05,
      "loss": 1.2444,
      "step": 905
    },
    {
      "epoch": 9.29,
      "learning_rate": 2.582859959249101e-05,
      "loss": 1.2759,
      "step": 910
    },
    {
      "epoch": 9.34,
      "learning_rate": 3.493677593252981e-05,
      "loss": 1.2315,
      "step": 915
    },
    {
      "epoch": 9.39,
      "learning_rate": 4.490795726669825e-05,
      "loss": 1.2353,
      "step": 920
    },
    {
      "epoch": 9.44,
      "learning_rate": 5.548651807108583e-05,
      "loss": 1.2733,
      "step": 925
    },
    {
      "epoch": 9.49,
      "learning_rate": 6.640126177858445e-05,
      "loss": 1.205,
      "step": 930
    },
    {
      "epoch": 9.54,
      "learning_rate": 7.737237329155688e-05,
      "loss": 1.2441,
      "step": 935
    },
    {
      "epoch": 9.59,
      "learning_rate": 8.811859244288885e-05,
      "loss": 1.2469,
      "step": 940
    },
    {
      "epoch": 9.64,
      "learning_rate": 9.83644245034643e-05,
      "loss": 1.2763,
      "step": 945
    },
    {
      "epoch": 9.69,
      "learning_rate": 0.00010784720288438088,
      "loss": 1.1781,
      "step": 950
    },
    {
      "epoch": 9.74,
      "learning_rate": 0.00011632382297139905,
      "loss": 1.2822,
      "step": 955
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.00012357697446014173,
      "loss": 1.2663,
      "step": 960
    },
    {
      "epoch": 9.85,
      "learning_rate": 0.00012942071241718773,
      "loss": 1.3906,
      "step": 965
    },
    {
      "epoch": 9.9,
      "learning_rate": 0.00013370522424493184,
      "loss": 1.3015,
      "step": 970
    },
    {
      "epoch": 9.95,
      "learning_rate": 0.00013632067034223124,
      "loss": 1.2348,
      "step": 975
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0001372,
      "loss": 1.2793,
      "step": 980
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.3976633548736572,
      "eval_runtime": 7.0041,
      "eval_samples_per_second": 21.273,
      "eval_steps_per_second": 2.713,
      "step": 980
    },
    {
      "epoch": 10.05,
      "learning_rate": 0.00013632067034223126,
      "loss": 1.2203,
      "step": 985
    },
    {
      "epoch": 10.1,
      "learning_rate": 0.0001337052242449319,
      "loss": 1.3016,
      "step": 990
    },
    {
      "epoch": 10.15,
      "learning_rate": 0.00012942071241718781,
      "loss": 1.2078,
      "step": 995
    },
    {
      "epoch": 10.2,
      "learning_rate": 0.00012357697446014183,
      "loss": 1.2408,
      "step": 1000
    },
    {
      "epoch": 10.26,
      "learning_rate": 0.00011632382297139899,
      "loss": 1.2247,
      "step": 1005
    },
    {
      "epoch": 10.31,
      "learning_rate": 0.00010784720288438083,
      "loss": 1.0939,
      "step": 1010
    },
    {
      "epoch": 10.36,
      "learning_rate": 9.836442450346467e-05,
      "loss": 1.1944,
      "step": 1015
    },
    {
      "epoch": 10.41,
      "learning_rate": 8.811859244288877e-05,
      "loss": 1.2171,
      "step": 1020
    },
    {
      "epoch": 10.46,
      "learning_rate": 7.737237329155728e-05,
      "loss": 1.2546,
      "step": 1025
    },
    {
      "epoch": 10.51,
      "learning_rate": 6.640126177858486e-05,
      "loss": 1.1607,
      "step": 1030
    },
    {
      "epoch": 10.56,
      "learning_rate": 5.5486518071086e-05,
      "loss": 1.2547,
      "step": 1035
    },
    {
      "epoch": 10.61,
      "learning_rate": 4.4907957266698644e-05,
      "loss": 1.2295,
      "step": 1040
    },
    {
      "epoch": 10.66,
      "learning_rate": 3.493677593252996e-05,
      "loss": 1.2566,
      "step": 1045
    },
    {
      "epoch": 10.71,
      "learning_rate": 2.5828599592491143e-05,
      "loss": 1.2949,
      "step": 1050
    },
    {
      "epoch": 10.77,
      "learning_rate": 1.7816929400633402e-05,
      "loss": 1.2886,
      "step": 1055
    },
    {
      "epoch": 10.82,
      "learning_rate": 1.1107156004419895e-05,
      "loss": 1.1858,
      "step": 1060
    },
    {
      "epoch": 10.87,
      "learning_rate": 5.871294061115278e-06,
      "loss": 1.2322,
      "step": 1065
    },
    {
      "epoch": 10.92,
      "learning_rate": 2.2435723955225265e-06,
      "loss": 1.0434,
      "step": 1070
    },
    {
      "epoch": 10.97,
      "learning_rate": 3.169928516850014e-07,
      "loss": 1.2505,
      "step": 1075
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.3747466802597046,
      "eval_runtime": 7.0127,
      "eval_samples_per_second": 21.247,
      "eval_steps_per_second": 2.709,
      "step": 1078
    },
    {
      "epoch": 11.37,
      "learning_rate": 4.1043693868806304e-05,
      "loss": 1.1875,
      "step": 1080
    },
    {
      "epoch": 11.42,
      "learning_rate": 5.17596955821411e-05,
      "loss": 1.3125,
      "step": 1085
    },
    {
      "epoch": 11.47,
      "learning_rate": 6.293505690059783e-05,
      "loss": 1.2444,
      "step": 1090
    },
    {
      "epoch": 11.53,
      "learning_rate": 7.426494309940222e-05,
      "loss": 1.3268,
      "step": 1095
    },
    {
      "epoch": 11.58,
      "learning_rate": 8.544030441785894e-05,
      "loss": 1.3066,
      "step": 1100
    },
    {
      "epoch": 11.63,
      "learning_rate": 9.615630613119375e-05,
      "loss": 1.2542,
      "step": 1105
    },
    {
      "epoch": 11.68,
      "learning_rate": 0.00010612064364719844,
      "loss": 1.246,
      "step": 1110
    },
    {
      "epoch": 11.74,
      "learning_rate": 0.00011506151581352574,
      "loss": 1.2672,
      "step": 1115
    },
    {
      "epoch": 11.79,
      "learning_rate": 0.00012273503894459246,
      "loss": 1.2702,
      "step": 1120
    },
    {
      "epoch": 11.84,
      "learning_rate": 0.00012893189933276523,
      "loss": 1.3417,
      "step": 1125
    },
    {
      "epoch": 11.89,
      "learning_rate": 0.00013348306278066356,
      "loss": 1.2473,
      "step": 1130
    },
    {
      "epoch": 11.95,
      "learning_rate": 0.00013626438541342674,
      "loss": 1.1708,
      "step": 1135
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.0001372,
      "loss": 1.1564,
      "step": 1140
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1428929567337036,
      "eval_runtime": 7.9608,
      "eval_samples_per_second": 21.48,
      "eval_steps_per_second": 2.764,
      "step": 1140
    },
    {
      "epoch": 11.8,
      "learning_rate": 0.00012461626728572456,
      "loss": 1.2708,
      "step": 1145
    },
    {
      "epoch": 11.86,
      "learning_rate": 0.000130268089438458,
      "loss": 1.2385,
      "step": 1150
    },
    {
      "epoch": 11.91,
      "learning_rate": 0.00013430626843929596,
      "loss": 1.2608,
      "step": 1155
    },
    {
      "epoch": 11.96,
      "learning_rate": 0.00013662513894413278,
      "loss": 1.2132,
      "step": 1160
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1082079410552979,
      "eval_runtime": 6.721,
      "eval_samples_per_second": 23.211,
      "eval_steps_per_second": 2.976,
      "step": 1164
    },
    {
      "epoch": 12.01,
      "learning_rate": 0.00013716402403652231,
      "loss": 1.2701,
      "step": 1165
    },
    {
      "epoch": 12.06,
      "learning_rate": 0.0001359088229352192,
      "loss": 1.2274,
      "step": 1170
    },
    {
      "epoch": 12.11,
      "learning_rate": 0.0001328923799634352,
      "loss": 1.1978,
      "step": 1175
    },
    {
      "epoch": 12.16,
      "learning_rate": 0.0001281936251251452,
      "loss": 1.0879,
      "step": 1180
    },
    {
      "epoch": 12.22,
      "learning_rate": 0.00012193550877662404,
      "loss": 1.2841,
      "step": 1185
    },
    {
      "epoch": 12.27,
      "learning_rate": 0.00011428178443580113,
      "loss": 1.166,
      "step": 1190
    },
    {
      "epoch": 12.32,
      "learning_rate": 0.0001054327239123201,
      "loss": 1.2385,
      "step": 1195
    },
    {
      "epoch": 12.37,
      "learning_rate": 9.561987687870095e-05,
      "loss": 1.1758,
      "step": 1200
    },
    {
      "epoch": 12.42,
      "learning_rate": 8.51000120067249e-05,
      "loss": 1.1698,
      "step": 1205
    },
    {
      "epoch": 12.47,
      "learning_rate": 7.414839820879227e-05,
      "loss": 1.3722,
      "step": 1210
    },
    {
      "epoch": 12.53,
      "learning_rate": 6.305160179120769e-05,
      "loss": 1.1787,
      "step": 1215
    },
    {
      "epoch": 12.58,
      "learning_rate": 5.209998799327507e-05,
      "loss": 1.2814,
      "step": 1220
    },
    {
      "epoch": 12.63,
      "learning_rate": 4.158012312129902e-05,
      "loss": 1.2154,
      "step": 1225
    },
    {
      "epoch": 12.68,
      "learning_rate": 3.176727608767987e-05,
      "loss": 1.2798,
      "step": 1230
    },
    {
      "epoch": 12.73,
      "learning_rate": 2.291821556419886e-05,
      "loss": 1.2241,
      "step": 1235
    },
    {
      "epoch": 12.78,
      "learning_rate": 1.5264491223375942e-05,
      "loss": 1.1194,
      "step": 1240
    },
    {
      "epoch": 12.84,
      "learning_rate": 9.006374874854777e-06,
      "loss": 1.1957,
      "step": 1245
    },
    {
      "epoch": 12.89,
      "learning_rate": 4.3076200365648044e-06,
      "loss": 1.1553,
      "step": 1250
    },
    {
      "epoch": 12.94,
      "learning_rate": 1.2911770647808012e-06,
      "loss": 1.1644,
      "step": 1255
    },
    {
      "epoch": 12.99,
      "learning_rate": 3.597596347767558e-08,
      "loss": 1.1646,
      "step": 1260
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.0746197700500488,
      "eval_runtime": 7.0141,
      "eval_samples_per_second": 22.241,
      "eval_steps_per_second": 2.851,
      "step": 1261
    },
    {
      "epoch": 12.91,
      "learning_rate": 2.835385281685176e-06,
      "loss": 1.0594,
      "step": 1265
    },
    {
      "epoch": 12.96,
      "learning_rate": 5.632050517253284e-07,
      "loss": 1.1527,
      "step": 1270
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.029100775718689,
      "eval_runtime": 6.9675,
      "eval_samples_per_second": 21.242,
      "eval_steps_per_second": 2.727,
      "step": 1274
    },
    {
      "epoch": 12.75,
      "learning_rate": 2.0092474810602958e-05,
      "loss": 1.2194,
      "step": 1275
    },
    {
      "epoch": 12.8,
      "learning_rate": 1.3101434185878674e-05,
      "loss": 1.0397,
      "step": 1280
    },
    {
      "epoch": 12.85,
      "learning_rate": 7.476952440677985e-06,
      "loss": 1.0537,
      "step": 1285
    },
    {
      "epoch": 12.9,
      "learning_rate": 3.35752298215246e-06,
      "loss": 1.2597,
      "step": 1290
    },
    {
      "epoch": 12.95,
      "learning_rate": 8.445798351736176e-07,
      "loss": 1.0949,
      "step": 1295
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.0,
      "loss": 1.1523,
      "step": 1300
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.004758358001709,
      "eval_runtime": 6.2971,
      "eval_samples_per_second": 20.803,
      "eval_steps_per_second": 2.7,
      "step": 1300
    }
  ],
  "max_steps": 1400,
  "num_train_epochs": 14,
  "total_flos": 1346568486912000.0,
  "trial_name": null,
  "trial_params": null
}