{
  "best_metric": 1.1272780895233154,
  "best_model_checkpoint": "outputs/checkpoint-5000",
  "epoch": 1.6,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.8184,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.7858,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-05,
      "loss": 1.7218,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.7218,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.7009,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.6714,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 7e-05,
      "loss": 1.6582,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.5659,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 9e-05,
      "loss": 1.5343,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.5252,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.414,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.3919,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.352,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.3762,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3238,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016,
      "loss": 1.3306,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017,
      "loss": 1.3423,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018,
      "loss": 1.3199,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019,
      "loss": 1.3506,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3315,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001998921832884097,
      "loss": 1.3142,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019978436657681943,
      "loss": 1.2994,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019967654986522912,
      "loss": 1.2972,
      "step": 115
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019956873315363883,
      "loss": 1.3135,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019946091644204851,
      "loss": 1.2903,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019935309973045823,
      "loss": 1.2783,
      "step": 130
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019924528301886794,
      "loss": 1.3044,
      "step": 135
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019913746630727762,
      "loss": 1.2947,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019902964959568736,
      "loss": 1.2759,
      "step": 145
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019892183288409705,
      "loss": 1.2746,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019881401617250676,
      "loss": 1.2869,
      "step": 155
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019870619946091644,
      "loss": 1.26,
      "step": 160
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019859838274932616,
      "loss": 1.258,
      "step": 165
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019849056603773587,
      "loss": 1.2649,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019838274932614555,
      "loss": 1.2549,
      "step": 175
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019827493261455526,
      "loss": 1.2859,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019816711590296498,
      "loss": 1.2934,
      "step": 185
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019805929919137466,
      "loss": 1.3011,
      "step": 190
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019795148247978437,
      "loss": 1.2304,
      "step": 195
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019784366576819408,
      "loss": 1.2849,
      "step": 200
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.2345943450927734,
      "eval_runtime": 710.2534,
      "eval_samples_per_second": 7.04,
      "eval_steps_per_second": 0.88,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001977358490566038,
      "loss": 1.2726,
      "step": 205
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019762803234501348,
      "loss": 1.2996,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001975202156334232,
      "loss": 1.2456,
      "step": 215
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001974123989218329,
      "loss": 1.2794,
      "step": 220
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001973045822102426,
      "loss": 1.2637,
      "step": 225
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001971967654986523,
      "loss": 1.252,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000197088948787062,
      "loss": 1.2492,
      "step": 235
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001969811320754717,
      "loss": 1.2972,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001968733153638814,
      "loss": 1.3023,
      "step": 245
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019676549865229112,
      "loss": 1.2682,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019665768194070083,
      "loss": 1.2981,
      "step": 255
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019654986522911052,
      "loss": 1.3084,
      "step": 260
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019644204851752023,
      "loss": 1.2666,
      "step": 265
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019633423180592994,
      "loss": 1.2623,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019622641509433963,
      "loss": 1.2406,
      "step": 275
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019611859838274934,
      "loss": 1.2623,
      "step": 280
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019601078167115905,
      "loss": 1.2562,
      "step": 285
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019590296495956873,
      "loss": 1.2166,
      "step": 290
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019579514824797845,
      "loss": 1.2931,
      "step": 295
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019568733153638813,
      "loss": 1.2354,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019557951482479787,
      "loss": 1.2246,
      "step": 305
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019547169811320755,
      "loss": 1.2236,
      "step": 310
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019536388140161727,
      "loss": 1.2442,
      "step": 315
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019525606469002698,
      "loss": 1.2779,
      "step": 320
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019514824797843666,
      "loss": 1.2285,
      "step": 325
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019504043126684637,
      "loss": 1.2157,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019493261455525606,
      "loss": 1.2405,
      "step": 335
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001948247978436658,
      "loss": 1.2335,
      "step": 340
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019471698113207548,
      "loss": 1.2401,
      "step": 345
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019460916442048517,
      "loss": 1.2521,
      "step": 350
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001945013477088949,
      "loss": 1.2386,
      "step": 355
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001943935309973046,
      "loss": 1.2196,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001942857142857143,
      "loss": 1.192,
      "step": 365
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000194177897574124,
      "loss": 1.1964,
      "step": 370
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001940700808625337,
      "loss": 1.2876,
      "step": 375
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001939622641509434,
      "loss": 1.2622,
      "step": 380
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001938544474393531,
      "loss": 1.2183,
      "step": 385
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019374663072776284,
      "loss": 1.206,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019363881401617252,
      "loss": 1.2697,
      "step": 395
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001935309973045822,
      "loss": 1.2515,
      "step": 400
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.207701563835144,
      "eval_runtime": 709.7794,
      "eval_samples_per_second": 7.044,
      "eval_steps_per_second": 0.881,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019342318059299192,
      "loss": 1.2596,
      "step": 405
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019331536388140163,
      "loss": 1.2537,
      "step": 410
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019320754716981134,
      "loss": 1.2545,
      "step": 415
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019309973045822103,
      "loss": 1.2473,
      "step": 420
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019299191374663074,
      "loss": 1.2308,
      "step": 425
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019288409703504045,
      "loss": 1.2482,
      "step": 430
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019277628032345013,
      "loss": 1.2342,
      "step": 435
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019266846361185985,
      "loss": 1.2101,
      "step": 440
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019256064690026956,
      "loss": 1.233,
      "step": 445
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019245283018867927,
      "loss": 1.2401,
      "step": 450
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019234501347708895,
      "loss": 1.2088,
      "step": 455
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019223719676549864,
      "loss": 1.2205,
      "step": 460
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019212938005390838,
      "loss": 1.218,
      "step": 465
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019202156334231806,
      "loss": 1.2208,
      "step": 470
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019191374663072777,
      "loss": 1.2783,
      "step": 475
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019180592991913749,
      "loss": 1.1886,
      "step": 480
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019169811320754717,
      "loss": 1.1939,
      "step": 485
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019159029649595688,
      "loss": 1.2079,
      "step": 490
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019148247978436657,
      "loss": 1.2473,
      "step": 495
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001913746630727763,
      "loss": 1.2295,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000191266846361186,
      "loss": 1.2064,
      "step": 505
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019115902964959568,
      "loss": 1.2138,
      "step": 510
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019105121293800541,
      "loss": 1.2618,
      "step": 515
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001909433962264151,
      "loss": 1.2495,
      "step": 520
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001908355795148248,
      "loss": 1.2553,
      "step": 525
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001907277628032345,
      "loss": 1.2334,
      "step": 530
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001906199460916442,
      "loss": 1.2442,
      "step": 535
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019051212938005392,
      "loss": 1.2301,
      "step": 540
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001904043126684636,
      "loss": 1.2678,
      "step": 545
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019029649595687334,
      "loss": 1.2116,
      "step": 550
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019018867924528303,
      "loss": 1.2556,
      "step": 555
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019008086253369274,
      "loss": 1.2427,
      "step": 560
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018997304582210242,
      "loss": 1.2138,
      "step": 565
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018986522911051214,
      "loss": 1.248,
      "step": 570
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018975741239892185,
      "loss": 1.2415,
      "step": 575
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018964959568733153,
      "loss": 1.2303,
      "step": 580
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018954177897574125,
      "loss": 1.1939,
      "step": 585
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018943396226415096,
      "loss": 1.1927,
      "step": 590
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018932614555256064,
      "loss": 1.1982,
      "step": 595
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018921832884097035,
      "loss": 1.1859,
      "step": 600
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.1948214769363403,
      "eval_runtime": 709.3061,
      "eval_samples_per_second": 7.049,
      "eval_steps_per_second": 0.881,
      "step": 600
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018911051212938007,
      "loss": 1.2265,
      "step": 605
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018900269541778978,
      "loss": 1.2402,
      "step": 610
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018889487870619946,
      "loss": 1.2261,
      "step": 615
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018878706199460917,
      "loss": 1.2264,
      "step": 620
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018867924528301889,
      "loss": 1.2044,
      "step": 625
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018857142857142857,
      "loss": 1.2203,
      "step": 630
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018846361185983828,
      "loss": 1.2258,
      "step": 635
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000188355795148248,
      "loss": 1.2475,
      "step": 640
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018824797843665768,
      "loss": 1.239,
      "step": 645
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001881401617250674,
      "loss": 1.2374,
      "step": 650
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001880323450134771,
      "loss": 1.2472,
      "step": 655
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018792452830188681,
      "loss": 1.2411,
      "step": 660
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001878167115902965,
      "loss": 1.1916,
      "step": 665
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001877088948787062,
      "loss": 1.2043,
      "step": 670
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018760107816711592,
      "loss": 1.2087,
      "step": 675
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001874932614555256,
      "loss": 1.2147,
      "step": 680
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018738544474393532,
      "loss": 1.1999,
      "step": 685
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018727762803234503,
      "loss": 1.2031,
      "step": 690
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018716981132075472,
      "loss": 1.268,
      "step": 695
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018706199460916443,
      "loss": 1.2181,
      "step": 700
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001869541778975741,
      "loss": 1.2187,
      "step": 705
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018684636118598385,
      "loss": 1.2475,
      "step": 710
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018673854447439354,
      "loss": 1.2043,
      "step": 715
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018663072776280325,
      "loss": 1.1833,
      "step": 720
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018652291105121296,
      "loss": 1.1899,
      "step": 725
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018641509433962264,
      "loss": 1.232,
      "step": 730
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018630727762803236,
      "loss": 1.1885,
      "step": 735
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018619946091644204,
      "loss": 1.2087,
      "step": 740
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018609164420485178,
      "loss": 1.2433,
      "step": 745
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018598382749326146,
      "loss": 1.2233,
      "step": 750
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018587601078167115,
      "loss": 1.2348,
      "step": 755
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001857681940700809,
      "loss": 1.1667,
      "step": 760
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018566037735849057,
      "loss": 1.2952,
      "step": 765
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018555256064690029,
      "loss": 1.1939,
      "step": 770
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018544474393530997,
      "loss": 1.1646,
      "step": 775
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018533692722371968,
      "loss": 1.2055,
      "step": 780
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001852291105121294,
      "loss": 1.183,
      "step": 785
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018512129380053908,
      "loss": 1.2367,
      "step": 790
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018501347708894882,
      "loss": 1.2265,
      "step": 795
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001849056603773585,
      "loss": 1.2007,
      "step": 800
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.184471845626831,
      "eval_runtime": 708.4336,
      "eval_samples_per_second": 7.058,
      "eval_steps_per_second": 0.882,
      "step": 800
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001847978436657682,
      "loss": 1.204,
      "step": 805
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001846900269541779,
      "loss": 1.2379,
      "step": 810
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001845822102425876,
      "loss": 1.157,
      "step": 815
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018447439353099732,
      "loss": 1.2072,
      "step": 820
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000184366576819407,
      "loss": 1.1764,
      "step": 825
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018425876010781672,
      "loss": 1.21,
      "step": 830
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018415094339622643,
      "loss": 1.19,
      "step": 835
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018404312668463612,
      "loss": 1.1923,
      "step": 840
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018393530997304583,
      "loss": 1.2367,
      "step": 845
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018382749326145554,
      "loss": 1.2394,
      "step": 850
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018371967654986525,
      "loss": 1.2275,
      "step": 855
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018361185983827494,
      "loss": 1.2206,
      "step": 860
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018350404312668465,
      "loss": 1.2017,
      "step": 865
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018339622641509436,
      "loss": 1.2277,
      "step": 870
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018328840970350404,
      "loss": 1.1958,
      "step": 875
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018318059299191376,
      "loss": 1.2317,
      "step": 880
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018307277628032347,
      "loss": 1.2339,
      "step": 885
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018296495956873315,
      "loss": 1.2408,
      "step": 890
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018285714285714286,
      "loss": 1.1818,
      "step": 895
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018274932614555258,
      "loss": 1.2051,
      "step": 900
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001826415094339623,
      "loss": 1.2304,
      "step": 905
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018253369272237197,
      "loss": 1.1717,
      "step": 910
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018242587601078168,
      "loss": 1.1811,
      "step": 915
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001823180592991914,
      "loss": 1.2127,
      "step": 920
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018221024258760108,
      "loss": 1.2278,
      "step": 925
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001821024258760108,
      "loss": 1.223,
      "step": 930
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001819946091644205,
      "loss": 1.233,
      "step": 935
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001818867924528302,
      "loss": 1.2321,
      "step": 940
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001817789757412399,
      "loss": 1.1894,
      "step": 945
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018167115902964959,
      "loss": 1.2213,
      "step": 950
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018156334231805933,
      "loss": 1.2444,
      "step": 955
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000181455525606469,
      "loss": 1.1988,
      "step": 960
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018134770889487872,
      "loss": 1.2039,
      "step": 965
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018123989218328843,
      "loss": 1.1972,
      "step": 970
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018113207547169812,
      "loss": 1.2146,
      "step": 975
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018102425876010783,
      "loss": 1.2346,
      "step": 980
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018091644204851751,
      "loss": 1.2283,
      "step": 985
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018080862533692723,
      "loss": 1.201,
      "step": 990
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018070080862533694,
      "loss": 1.2149,
      "step": 995
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018059299191374662,
      "loss": 1.2085,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "eval_loss": 1.176331877708435,
      "eval_runtime": 709.1565,
      "eval_samples_per_second": 7.051,
      "eval_steps_per_second": 0.881,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018048517520215636,
      "loss": 1.2484,
      "step": 1005
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018037735849056605,
      "loss": 1.2193,
      "step": 1010
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018026954177897576,
      "loss": 1.1733,
      "step": 1015
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018016172506738544,
      "loss": 1.2152,
      "step": 1020
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018005390835579516,
      "loss": 1.1688,
      "step": 1025
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017994609164420487,
      "loss": 1.1893,
      "step": 1030
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017983827493261455,
      "loss": 1.1483,
      "step": 1035
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001797304582210243,
      "loss": 1.189,
      "step": 1040
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017962264150943398,
      "loss": 1.1873,
      "step": 1045
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017951482479784366,
      "loss": 1.1883,
      "step": 1050
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017940700808625337,
      "loss": 1.1741,
      "step": 1055
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017929919137466308,
      "loss": 1.2546,
      "step": 1060
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001791913746630728,
      "loss": 1.2194,
      "step": 1065
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017908355795148248,
      "loss": 1.1945,
      "step": 1070
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001789757412398922,
      "loss": 1.2011,
      "step": 1075
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001788679245283019,
      "loss": 1.1836,
      "step": 1080
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001787601078167116,
      "loss": 1.2116,
      "step": 1085
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001786522911051213,
      "loss": 1.1983,
      "step": 1090
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000178544474393531,
      "loss": 1.2095,
      "step": 1095
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001784366576819407,
      "loss": 1.2007,
      "step": 1100
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001783288409703504,
      "loss": 1.1936,
      "step": 1105
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001782210242587601,
      "loss": 1.2207,
      "step": 1110
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017811320754716983,
      "loss": 1.2016,
      "step": 1115
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017800539083557952,
      "loss": 1.2013,
      "step": 1120
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017789757412398923,
      "loss": 1.1794,
      "step": 1125
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017778975741239894,
      "loss": 1.235,
      "step": 1130
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017768194070080863,
      "loss": 1.1865,
      "step": 1135
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017757412398921834,
      "loss": 1.2159,
      "step": 1140
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017746630727762802,
      "loss": 1.1887,
      "step": 1145
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017735849056603776,
      "loss": 1.1923,
      "step": 1150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017725067385444745,
      "loss": 1.1894,
      "step": 1155
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017714285714285713,
      "loss": 1.1863,
      "step": 1160
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017703504043126687,
      "loss": 1.2128,
      "step": 1165
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017692722371967655,
      "loss": 1.214,
      "step": 1170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017681940700808627,
      "loss": 1.2083,
      "step": 1175
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017671159029649595,
      "loss": 1.2252,
      "step": 1180
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017660377358490566,
      "loss": 1.1818,
      "step": 1185
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017649595687331538,
      "loss": 1.2334,
      "step": 1190
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017638814016172506,
      "loss": 1.1752,
      "step": 1195
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001762803234501348,
      "loss": 1.2036,
      "step": 1200
    },
    {
      "epoch": 0.38,
      "eval_loss": 1.1710153818130493,
      "eval_runtime": 708.8537,
      "eval_samples_per_second": 7.054,
      "eval_steps_per_second": 0.882,
      "step": 1200
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017617250673854448,
      "loss": 1.2283,
      "step": 1205
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001760646900269542,
      "loss": 1.2464,
      "step": 1210
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017595687331536388,
      "loss": 1.2126,
      "step": 1215
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001758490566037736,
      "loss": 1.2217,
      "step": 1220
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001757412398921833,
      "loss": 1.2245,
      "step": 1225
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000175633423180593,
      "loss": 1.1941,
      "step": 1230
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001755256064690027,
      "loss": 1.2041,
      "step": 1235
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001754177897574124,
      "loss": 1.2076,
      "step": 1240
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001753099730458221,
      "loss": 1.2154,
      "step": 1245
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001752021563342318,
      "loss": 1.2247,
      "step": 1250
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017509433962264152,
      "loss": 1.1822,
      "step": 1255
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017498652291105123,
      "loss": 1.2015,
      "step": 1260
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017487870619946092,
      "loss": 1.2111,
      "step": 1265
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017477088948787063,
      "loss": 1.1946,
      "step": 1270
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017466307277628034,
      "loss": 1.1365,
      "step": 1275
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017455525606469003,
      "loss": 1.1742,
      "step": 1280
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017444743935309974,
      "loss": 1.2442,
      "step": 1285
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017433962264150945,
      "loss": 1.2095,
      "step": 1290
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017423180592991913,
      "loss": 1.1727,
      "step": 1295
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017412398921832885,
      "loss": 1.1948,
      "step": 1300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017401617250673856,
      "loss": 1.1737,
      "step": 1305
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017390835579514827,
      "loss": 1.198,
      "step": 1310
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017380053908355795,
      "loss": 1.2152,
      "step": 1315
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017369272237196767,
      "loss": 1.2061,
      "step": 1320
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017358490566037738,
      "loss": 1.1925,
      "step": 1325
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017347708894878706,
      "loss": 1.2067,
      "step": 1330
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017336927223719677,
      "loss": 1.1964,
      "step": 1335
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001732614555256065,
      "loss": 1.2062,
      "step": 1340
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017315363881401617,
      "loss": 1.2208,
      "step": 1345
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017304582210242588,
      "loss": 1.167,
      "step": 1350
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017293800539083557,
      "loss": 1.1802,
      "step": 1355
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001728301886792453,
      "loss": 1.2193,
      "step": 1360
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000172722371967655,
      "loss": 1.2015,
      "step": 1365
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001726145552560647,
      "loss": 1.2183,
      "step": 1370
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017250673854447442,
      "loss": 1.1986,
      "step": 1375
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001723989218328841,
      "loss": 1.1575,
      "step": 1380
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001722911051212938,
      "loss": 1.1949,
      "step": 1385
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001721832884097035,
      "loss": 1.2103,
      "step": 1390
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017207547169811324,
      "loss": 1.2141,
      "step": 1395
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017196765498652292,
      "loss": 1.2134,
      "step": 1400
    },
    {
      "epoch": 0.45,
      "eval_loss": 1.1655155420303345,
      "eval_runtime": 709.3424,
      "eval_samples_per_second": 7.049,
      "eval_steps_per_second": 0.881,
      "step": 1400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001718598382749326,
      "loss": 1.1573,
      "step": 1405
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017175202156334234,
      "loss": 1.1694,
      "step": 1410
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017164420485175203,
      "loss": 1.226,
      "step": 1415
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017153638814016174,
      "loss": 1.1758,
      "step": 1420
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.185,
      "step": 1425
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017132075471698114,
      "loss": 1.1878,
      "step": 1430
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017121293800539085,
      "loss": 1.2108,
      "step": 1435
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017110512129380053,
      "loss": 1.254,
      "step": 1440
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017099730458221027,
      "loss": 1.2071,
      "step": 1445
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017088948787061996,
      "loss": 1.1914,
      "step": 1450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017078167115902964,
      "loss": 1.1936,
      "step": 1455
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017067385444743935,
      "loss": 1.2369,
      "step": 1460
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017056603773584907,
      "loss": 1.1627,
      "step": 1465
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017045822102425878,
      "loss": 1.216,
      "step": 1470
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017035040431266846,
      "loss": 1.1931,
      "step": 1475
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00017024258760107817,
      "loss": 1.1859,
      "step": 1480
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017013477088948789,
      "loss": 1.1769,
      "step": 1485
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017002695417789757,
      "loss": 1.1376,
      "step": 1490
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016991913746630728,
      "loss": 1.1692,
      "step": 1495
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000169811320754717,
      "loss": 1.1948,
      "step": 1500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001697035040431267,
      "loss": 1.183,
      "step": 1505
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001695956873315364,
      "loss": 1.1687,
      "step": 1510
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001694878706199461,
      "loss": 1.1754,
      "step": 1515
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016938005390835581,
      "loss": 1.2051,
      "step": 1520
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001692722371967655,
      "loss": 1.1862,
      "step": 1525
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001691644204851752,
      "loss": 1.2014,
      "step": 1530
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016905660377358492,
      "loss": 1.1992,
      "step": 1535
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001689487870619946,
      "loss": 1.2253,
      "step": 1540
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016884097035040432,
      "loss": 1.2125,
      "step": 1545
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016873315363881403,
      "loss": 1.1838,
      "step": 1550
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016862533692722374,
      "loss": 1.2048,
      "step": 1555
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016851752021563343,
      "loss": 1.1855,
      "step": 1560
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001684097035040431,
      "loss": 1.1646,
      "step": 1565
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016830188679245285,
      "loss": 1.2024,
      "step": 1570
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016819407008086254,
      "loss": 1.2162,
      "step": 1575
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016808625336927225,
      "loss": 1.1909,
      "step": 1580
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016797843665768196,
      "loss": 1.1807,
      "step": 1585
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016787061994609164,
      "loss": 1.1803,
      "step": 1590
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016776280323450136,
      "loss": 1.1894,
      "step": 1595
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016765498652291104,
      "loss": 1.1869,
      "step": 1600
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.1610257625579834,
      "eval_runtime": 709.4343,
      "eval_samples_per_second": 7.048,
      "eval_steps_per_second": 0.881,
      "step": 1600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016754716981132078,
      "loss": 1.1832,
      "step": 1605
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016743935309973047,
      "loss": 1.1553,
      "step": 1610
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016733153638814018,
      "loss": 1.1788,
      "step": 1615
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001672237196765499,
      "loss": 1.1896,
      "step": 1620
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016711590296495957,
      "loss": 1.1839,
      "step": 1625
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016700808625336929,
      "loss": 1.2063,
      "step": 1630
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016690026954177897,
      "loss": 1.1756,
      "step": 1635
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016679245283018868,
      "loss": 1.1903,
      "step": 1640
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001666846361185984,
      "loss": 1.1901,
      "step": 1645
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016657681940700808,
      "loss": 1.1852,
      "step": 1650
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016646900269541782,
      "loss": 1.1824,
      "step": 1655
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001663611859838275,
      "loss": 1.1514,
      "step": 1660
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016625336927223721,
      "loss": 1.1835,
      "step": 1665
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001661455525606469,
      "loss": 1.1564,
      "step": 1670
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001660377358490566,
      "loss": 1.2315,
      "step": 1675
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016592991913746632,
      "loss": 1.2016,
      "step": 1680
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000165822102425876,
      "loss": 1.2058,
      "step": 1685
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016571428571428575,
      "loss": 1.2109,
      "step": 1690
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016560646900269543,
      "loss": 1.2114,
      "step": 1695
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016549865229110512,
      "loss": 1.1754,
      "step": 1700
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016539083557951483,
      "loss": 1.1659,
      "step": 1705
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016528301886792454,
      "loss": 1.2003,
      "step": 1710
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016517520215633425,
      "loss": 1.2209,
      "step": 1715
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016506738544474394,
      "loss": 1.173,
      "step": 1720
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016495956873315365,
      "loss": 1.2318,
      "step": 1725
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016485175202156336,
      "loss": 1.2312,
      "step": 1730
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016474393530997304,
      "loss": 1.1828,
      "step": 1735
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016463611859838276,
      "loss": 1.1994,
      "step": 1740
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016452830188679247,
      "loss": 1.1953,
      "step": 1745
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016442048517520215,
      "loss": 1.1821,
      "step": 1750
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016431266846361186,
      "loss": 1.2484,
      "step": 1755
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016420485175202155,
      "loss": 1.1838,
      "step": 1760
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001640970350404313,
      "loss": 1.1851,
      "step": 1765
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016398921832884097,
      "loss": 1.2036,
      "step": 1770
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016388140161725068,
      "loss": 1.2104,
      "step": 1775
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001637735849056604,
      "loss": 1.1789,
      "step": 1780
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016366576819407008,
      "loss": 1.2007,
      "step": 1785
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001635579514824798,
      "loss": 1.1963,
      "step": 1790
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016345013477088948,
      "loss": 1.1817,
      "step": 1795
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016334231805929922,
      "loss": 1.2017,
      "step": 1800
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.157345175743103,
      "eval_runtime": 708.5342,
      "eval_samples_per_second": 7.057,
      "eval_steps_per_second": 0.882,
      "step": 1800
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001632345013477089,
      "loss": 1.1706,
      "step": 1805
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001631266846361186,
      "loss": 1.2104,
      "step": 1810
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016301886792452833,
      "loss": 1.1855,
      "step": 1815
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000162911051212938,
      "loss": 1.1485,
      "step": 1820
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016280323450134772,
      "loss": 1.1951,
      "step": 1825
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001626954177897574,
      "loss": 1.1655,
      "step": 1830
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016258760107816712,
      "loss": 1.153,
      "step": 1835
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016247978436657683,
      "loss": 1.1635,
      "step": 1840
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016237196765498652,
      "loss": 1.2176,
      "step": 1845
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016226415094339625,
      "loss": 1.1589,
      "step": 1850
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016215633423180594,
      "loss": 1.2518,
      "step": 1855
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016204851752021562,
      "loss": 1.1931,
      "step": 1860
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016194070080862534,
      "loss": 1.1886,
      "step": 1865
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016183288409703505,
      "loss": 1.1653,
      "step": 1870
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016172506738544476,
      "loss": 1.1975,
      "step": 1875
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016161725067385444,
      "loss": 1.2009,
      "step": 1880
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016150943396226416,
      "loss": 1.2339,
      "step": 1885
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016140161725067387,
      "loss": 1.1958,
      "step": 1890
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016129380053908355,
      "loss": 1.1811,
      "step": 1895
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016118598382749326,
      "loss": 1.1835,
      "step": 1900
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016107816711590298,
      "loss": 1.1767,
      "step": 1905
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001609703504043127,
      "loss": 1.1796,
      "step": 1910
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016086253369272237,
      "loss": 1.2022,
      "step": 1915
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016075471698113208,
      "loss": 1.1926,
      "step": 1920
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001606469002695418,
      "loss": 1.1882,
      "step": 1925
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00016053908355795148,
      "loss": 1.1504,
      "step": 1930
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001604312668463612,
      "loss": 1.1927,
      "step": 1935
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001603234501347709,
      "loss": 1.1601,
      "step": 1940
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001602156334231806,
      "loss": 1.1726,
      "step": 1945
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001601078167115903,
      "loss": 1.2053,
      "step": 1950
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00016,
      "loss": 1.1919,
      "step": 1955
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015989218328840972,
      "loss": 1.1814,
      "step": 1960
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001597843665768194,
      "loss": 1.1838,
      "step": 1965
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015967654986522912,
      "loss": 1.1954,
      "step": 1970
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015956873315363883,
      "loss": 1.196,
      "step": 1975
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015946091644204852,
      "loss": 1.1877,
      "step": 1980
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015935309973045823,
      "loss": 1.1853,
      "step": 1985
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015924528301886794,
      "loss": 1.197,
      "step": 1990
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015913746630727763,
      "loss": 1.1484,
      "step": 1995
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015902964959568734,
      "loss": 1.2139,
      "step": 2000
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.153731107711792,
      "eval_runtime": 709.6014,
      "eval_samples_per_second": 7.046,
      "eval_steps_per_second": 0.881,
      "step": 2000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015892183288409702,
      "loss": 1.219,
      "step": 2005
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015881401617250676,
      "loss": 1.209,
      "step": 2010
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015870619946091645,
      "loss": 1.1925,
      "step": 2015
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015859838274932616,
      "loss": 1.168,
      "step": 2020
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015849056603773587,
      "loss": 1.1759,
      "step": 2025
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015838274932614556,
      "loss": 1.1815,
      "step": 2030
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015827493261455527,
      "loss": 1.17,
      "step": 2035
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015816711590296495,
      "loss": 1.1778,
      "step": 2040
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015805929919137466,
      "loss": 1.1832,
      "step": 2045
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015795148247978438,
      "loss": 1.2256,
      "step": 2050
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015784366576819406,
      "loss": 1.1694,
      "step": 2055
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001577358490566038,
      "loss": 1.1549,
      "step": 2060
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015762803234501348,
      "loss": 1.1811,
      "step": 2065
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001575202156334232,
      "loss": 1.1529,
      "step": 2070
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015741239892183288,
      "loss": 1.1677,
      "step": 2075
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001573045822102426,
      "loss": 1.1657,
      "step": 2080
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001571967654986523,
      "loss": 1.1673,
      "step": 2085
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000157088948787062,
      "loss": 1.1806,
      "step": 2090
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015698113207547173,
      "loss": 1.209,
      "step": 2095
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001568733153638814,
      "loss": 1.2106,
      "step": 2100
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001567654986522911,
      "loss": 1.1588,
      "step": 2105
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001566576819407008,
      "loss": 1.178,
      "step": 2110
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015654986522911052,
      "loss": 1.1232,
      "step": 2115
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015644204851752023,
      "loss": 1.2007,
      "step": 2120
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015633423180592992,
      "loss": 1.1999,
      "step": 2125
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015622641509433963,
      "loss": 1.1888,
      "step": 2130
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015611859838274934,
      "loss": 1.2105,
      "step": 2135
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015601078167115903,
      "loss": 1.1689,
      "step": 2140
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015590296495956874,
      "loss": 1.1656,
      "step": 2145
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015579514824797845,
      "loss": 1.1385,
      "step": 2150
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015568733153638813,
      "loss": 1.1773,
      "step": 2155
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015557951482479785,
      "loss": 1.1612,
      "step": 2160
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015547169811320756,
      "loss": 1.1687,
      "step": 2165
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015536388140161727,
      "loss": 1.1593,
      "step": 2170
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015525606469002695,
      "loss": 1.1624,
      "step": 2175
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015514824797843667,
      "loss": 1.1935,
      "step": 2180
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015504043126684638,
      "loss": 1.1696,
      "step": 2185
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015493261455525606,
      "loss": 1.2212,
      "step": 2190
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015482479784366577,
      "loss": 1.1608,
      "step": 2195
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001547169811320755,
      "loss": 1.1302,
      "step": 2200
    },
    {
      "epoch": 0.7,
      "eval_loss": 1.1510419845581055,
      "eval_runtime": 708.6685,
      "eval_samples_per_second": 7.055,
      "eval_steps_per_second": 0.882,
      "step": 2200
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001546091644204852,
      "loss": 1.2165,
      "step": 2205
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015450134770889488,
      "loss": 1.1766,
      "step": 2210
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015439353099730457,
      "loss": 1.1762,
      "step": 2215
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001542857142857143,
      "loss": 1.1523,
      "step": 2220
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000154177897574124,
      "loss": 1.1889,
      "step": 2225
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001540700808625337,
      "loss": 1.1314,
      "step": 2230
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015396226415094342,
      "loss": 1.2006,
      "step": 2235
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001538544474393531,
      "loss": 1.2,
      "step": 2240
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001537466307277628,
      "loss": 1.1558,
      "step": 2245
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001536388140161725,
      "loss": 1.1979,
      "step": 2250
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015353099730458224,
      "loss": 1.1782,
      "step": 2255
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015342318059299192,
      "loss": 1.192,
      "step": 2260
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015331536388140163,
      "loss": 1.1937,
      "step": 2265
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015320754716981134,
      "loss": 1.1627,
      "step": 2270
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015309973045822103,
      "loss": 1.1617,
      "step": 2275
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015299191374663074,
      "loss": 1.2053,
      "step": 2280
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015288409703504043,
      "loss": 1.1716,
      "step": 2285
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015277628032345014,
      "loss": 1.214,
      "step": 2290
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015266846361185985,
      "loss": 1.1908,
      "step": 2295
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015256064690026953,
      "loss": 1.1819,
      "step": 2300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015245283018867927,
      "loss": 1.1544,
      "step": 2305
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015234501347708896,
      "loss": 1.1634,
      "step": 2310
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015223719676549867,
      "loss": 1.1831,
      "step": 2315
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015212938005390835,
      "loss": 1.2191,
      "step": 2320
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015202156334231807,
      "loss": 1.1716,
      "step": 2325
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015191374663072778,
      "loss": 1.1385,
      "step": 2330
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015180592991913746,
      "loss": 1.2081,
      "step": 2335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015169811320754717,
      "loss": 1.1674,
      "step": 2340
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015159029649595689,
      "loss": 1.1078,
      "step": 2345
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015148247978436657,
      "loss": 1.1987,
      "step": 2350
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015137466307277628,
      "loss": 1.1827,
      "step": 2355
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000151266846361186,
      "loss": 1.1991,
      "step": 2360
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001511590296495957,
      "loss": 1.1718,
      "step": 2365
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001510512129380054,
      "loss": 1.187,
      "step": 2370
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001509433962264151,
      "loss": 1.1596,
      "step": 2375
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015083557951482481,
      "loss": 1.2077,
      "step": 2380
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001507277628032345,
      "loss": 1.1955,
      "step": 2385
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001506199460916442,
      "loss": 1.1653,
      "step": 2390
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015051212938005392,
      "loss": 1.2213,
      "step": 2395
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001504043126684636,
      "loss": 1.1799,
      "step": 2400
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.1479781866073608,
      "eval_runtime": 709.5516,
      "eval_samples_per_second": 7.047,
      "eval_steps_per_second": 0.881,
      "step": 2400
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015029649595687332,
      "loss": 1.1505,
      "step": 2405
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015018867924528303,
      "loss": 1.1371,
      "step": 2410
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015008086253369274,
      "loss": 1.1523,
      "step": 2415
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014997304582210243,
      "loss": 1.1613,
      "step": 2420
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014986522911051214,
      "loss": 1.1648,
      "step": 2425
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014975741239892185,
      "loss": 1.1729,
      "step": 2430
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014964959568733154,
      "loss": 1.1626,
      "step": 2435
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014954177897574125,
      "loss": 1.1489,
      "step": 2440
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014943396226415093,
      "loss": 1.1673,
      "step": 2445
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014932614555256067,
      "loss": 1.1718,
      "step": 2450
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014921832884097036,
      "loss": 1.1807,
      "step": 2455
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014911051212938004,
      "loss": 1.2018,
      "step": 2460
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014900269541778978,
      "loss": 1.2019,
      "step": 2465
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014889487870619947,
      "loss": 1.2028,
      "step": 2470
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014878706199460918,
      "loss": 1.1865,
      "step": 2475
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014867924528301886,
      "loss": 1.1472,
      "step": 2480
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014857142857142857,
      "loss": 1.1894,
      "step": 2485
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014846361185983829,
      "loss": 1.165,
      "step": 2490
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014835579514824797,
      "loss": 1.2207,
      "step": 2495
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001482479784366577,
      "loss": 1.1673,
      "step": 2500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001481401617250674,
      "loss": 1.145,
      "step": 2505
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014803234501347708,
      "loss": 1.1389,
      "step": 2510
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001479245283018868,
      "loss": 1.1875,
      "step": 2515
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001478167115902965,
      "loss": 1.1756,
      "step": 2520
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014770889487870621,
      "loss": 1.1974,
      "step": 2525
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001476010781671159,
      "loss": 1.1955,
      "step": 2530
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001474932614555256,
      "loss": 1.1493,
      "step": 2535
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014738544474393532,
      "loss": 1.1846,
      "step": 2540
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000147277628032345,
      "loss": 1.1558,
      "step": 2545
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014716981132075472,
      "loss": 1.1677,
      "step": 2550
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014706199460916443,
      "loss": 1.1772,
      "step": 2555
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014695417789757414,
      "loss": 1.2155,
      "step": 2560
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014684636118598383,
      "loss": 1.2052,
      "step": 2565
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014673854447439354,
      "loss": 1.1814,
      "step": 2570
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014663072776280325,
      "loss": 1.2011,
      "step": 2575
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014652291105121294,
      "loss": 1.1852,
      "step": 2580
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014641509433962265,
      "loss": 1.1847,
      "step": 2585
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014630727762803236,
      "loss": 1.1983,
      "step": 2590
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014619946091644204,
      "loss": 1.1576,
      "step": 2595
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014609164420485176,
      "loss": 1.1518,
      "step": 2600
    },
    {
      "epoch": 0.83,
      "eval_loss": 1.146146535873413,
      "eval_runtime": 709.2392,
      "eval_samples_per_second": 7.05,
      "eval_steps_per_second": 0.881,
      "step": 2600
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014598382749326147,
      "loss": 1.1805,
      "step": 2605
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014587601078167118,
      "loss": 1.2067,
      "step": 2610
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014576819407008086,
      "loss": 1.1257,
      "step": 2615
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014566037735849055,
      "loss": 1.1683,
      "step": 2620
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001455525606469003,
      "loss": 1.1763,
      "step": 2625
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014544474393530997,
      "loss": 1.1747,
      "step": 2630
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014533692722371969,
      "loss": 1.1658,
      "step": 2635
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001452291105121294,
      "loss": 1.2061,
      "step": 2640
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014512129380053908,
      "loss": 1.1888,
      "step": 2645
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001450134770889488,
      "loss": 1.1822,
      "step": 2650
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014490566037735848,
      "loss": 1.164,
      "step": 2655
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014479784366576822,
      "loss": 1.2047,
      "step": 2660
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001446900269541779,
      "loss": 1.1296,
      "step": 2665
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014458221024258761,
      "loss": 1.1748,
      "step": 2670
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014447439353099733,
      "loss": 1.1199,
      "step": 2675
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000144366576819407,
      "loss": 1.1819,
      "step": 2680
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014425876010781672,
      "loss": 1.1801,
      "step": 2685
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001441509433962264,
      "loss": 1.1667,
      "step": 2690
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014404312668463612,
      "loss": 1.1823,
      "step": 2695
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014393530997304583,
      "loss": 1.2095,
      "step": 2700
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014382749326145552,
      "loss": 1.1903,
      "step": 2705
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014371967654986525,
      "loss": 1.1857,
      "step": 2710
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014361185983827494,
      "loss": 1.2016,
      "step": 2715
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014350404312668465,
      "loss": 1.2046,
      "step": 2720
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014339622641509434,
      "loss": 1.2048,
      "step": 2725
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014328840970350405,
      "loss": 1.1859,
      "step": 2730
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014318059299191376,
      "loss": 1.2309,
      "step": 2735
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014307277628032344,
      "loss": 1.1893,
      "step": 2740
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014296495956873318,
      "loss": 1.1932,
      "step": 2745
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.192,
      "step": 2750
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014274932614555255,
      "loss": 1.188,
      "step": 2755
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014264150943396226,
      "loss": 1.1345,
      "step": 2760
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014253369272237198,
      "loss": 1.1902,
      "step": 2765
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001424258760107817,
      "loss": 1.1644,
      "step": 2770
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014231805929919137,
      "loss": 1.1259,
      "step": 2775
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014221024258760108,
      "loss": 1.1694,
      "step": 2780
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001421024258760108,
      "loss": 1.1837,
      "step": 2785
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014199460916442048,
      "loss": 1.153,
      "step": 2790
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001418867924528302,
      "loss": 1.1925,
      "step": 2795
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001417789757412399,
      "loss": 1.1752,
      "step": 2800
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.143415093421936,
      "eval_runtime": 708.8805,
      "eval_samples_per_second": 7.053,
      "eval_steps_per_second": 0.882,
      "step": 2800
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001416711590296496,
      "loss": 1.154,
      "step": 2805
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001415633423180593,
      "loss": 1.1811,
      "step": 2810
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000141455525606469,
      "loss": 1.1962,
      "step": 2815
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014134770889487873,
      "loss": 1.1968,
      "step": 2820
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001412398921832884,
      "loss": 1.1964,
      "step": 2825
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00014113207547169812,
      "loss": 1.1485,
      "step": 2830
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00014102425876010783,
      "loss": 1.1518,
      "step": 2835
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00014091644204851752,
      "loss": 1.1405,
      "step": 2840
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00014080862533692723,
      "loss": 1.1588,
      "step": 2845
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00014070080862533694,
      "loss": 1.1797,
      "step": 2850
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00014059299191374665,
      "loss": 1.1405,
      "step": 2855
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014048517520215634,
      "loss": 1.1603,
      "step": 2860
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014037735849056602,
      "loss": 1.2069,
      "step": 2865
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014026954177897576,
      "loss": 1.1864,
      "step": 2870
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014016172506738545,
      "loss": 1.1567,
      "step": 2875
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014005390835579516,
      "loss": 1.1836,
      "step": 2880
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013994609164420487,
      "loss": 1.2095,
      "step": 2885
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013983827493261456,
      "loss": 1.1931,
      "step": 2890
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013973045822102427,
      "loss": 1.2025,
      "step": 2895
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013962264150943395,
      "loss": 1.192,
      "step": 2900
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001395148247978437,
      "loss": 1.2305,
      "step": 2905
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013940700808625338,
      "loss": 1.1856,
      "step": 2910
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013929919137466306,
      "loss": 1.208,
      "step": 2915
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001391913746630728,
      "loss": 1.1751,
      "step": 2920
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013908355795148248,
      "loss": 1.119,
      "step": 2925
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001389757412398922,
      "loss": 1.1694,
      "step": 2930
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013886792452830188,
      "loss": 1.1712,
      "step": 2935
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001387601078167116,
      "loss": 1.1328,
      "step": 2940
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001386522911051213,
      "loss": 1.1756,
      "step": 2945
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000138544474393531,
      "loss": 1.2139,
      "step": 2950
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013843665768194073,
      "loss": 1.1559,
      "step": 2955
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001383288409703504,
      "loss": 1.1384,
      "step": 2960
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013822102425876012,
      "loss": 1.1647,
      "step": 2965
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001381132075471698,
      "loss": 1.183,
      "step": 2970
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013800539083557952,
      "loss": 1.1357,
      "step": 2975
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013789757412398923,
      "loss": 1.1835,
      "step": 2980
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013778975741239892,
      "loss": 1.1927,
      "step": 2985
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013768194070080863,
      "loss": 1.1908,
      "step": 2990
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013757412398921834,
      "loss": 1.1586,
      "step": 2995
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013746630727762803,
      "loss": 1.1584,
      "step": 3000
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.1414791345596313,
      "eval_runtime": 705.1717,
      "eval_samples_per_second": 7.09,
      "eval_steps_per_second": 0.886,
      "step": 3000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013735849056603774,
      "loss": 1.2006,
      "step": 3005
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013725067385444745,
      "loss": 1.1835,
      "step": 3010
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013714285714285716,
      "loss": 1.1773,
      "step": 3015
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013703504043126685,
      "loss": 1.1719,
      "step": 3020
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013692722371967656,
      "loss": 1.1736,
      "step": 3025
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013681940700808627,
      "loss": 1.1536,
      "step": 3030
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013671159029649595,
      "loss": 1.1845,
      "step": 3035
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013660377358490567,
      "loss": 1.2087,
      "step": 3040
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013649595687331538,
      "loss": 1.1516,
      "step": 3045
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013638814016172506,
      "loss": 1.1443,
      "step": 3050
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013628032345013478,
      "loss": 1.1609,
      "step": 3055
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001361725067385445,
      "loss": 1.1798,
      "step": 3060
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001360646900269542,
      "loss": 1.215,
      "step": 3065
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013595687331536388,
      "loss": 1.1845,
      "step": 3070
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001358490566037736,
      "loss": 1.1515,
      "step": 3075
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001357412398921833,
      "loss": 1.18,
      "step": 3080
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000135633423180593,
      "loss": 1.1741,
      "step": 3085
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001355256064690027,
      "loss": 1.1609,
      "step": 3090
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001354177897574124,
      "loss": 1.1581,
      "step": 3095
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001353099730458221,
      "loss": 1.2023,
      "step": 3100
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001352021563342318,
      "loss": 1.1553,
      "step": 3105
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001350943396226415,
      "loss": 1.1721,
      "step": 3110
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013498652291105124,
      "loss": 1.2398,
      "step": 3115
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013487870619946092,
      "loss": 1.1656,
      "step": 3120
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013477088948787063,
      "loss": 1.1591,
      "step": 3125
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013466307277628032,
      "loss": 1.1791,
      "step": 3130
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013455525606469003,
      "loss": 1.1315,
      "step": 3135
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013444743935309974,
      "loss": 1.1538,
      "step": 3140
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013433962264150943,
      "loss": 1.1189,
      "step": 3145
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013423180592991916,
      "loss": 1.1305,
      "step": 3150
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013412398921832885,
      "loss": 1.1633,
      "step": 3155
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013401617250673853,
      "loss": 1.1274,
      "step": 3160
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013390835579514825,
      "loss": 1.145,
      "step": 3165
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013380053908355796,
      "loss": 1.183,
      "step": 3170
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013369272237196767,
      "loss": 1.1849,
      "step": 3175
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013358490566037735,
      "loss": 1.1461,
      "step": 3180
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013347708894878707,
      "loss": 1.2046,
      "step": 3185
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013336927223719678,
      "loss": 1.1395,
      "step": 3190
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013326145552560646,
      "loss": 1.1611,
      "step": 3195
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013315363881401617,
      "loss": 1.1311,
      "step": 3200
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.140012264251709,
      "eval_runtime": 701.8342,
      "eval_samples_per_second": 7.124,
      "eval_steps_per_second": 0.891,
      "step": 3200
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001330458221024259,
      "loss": 1.1558,
      "step": 3205
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001329380053908356,
      "loss": 1.1512,
      "step": 3210
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013283018867924528,
      "loss": 1.1567,
      "step": 3215
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000132722371967655,
      "loss": 1.1612,
      "step": 3220
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001326145552560647,
      "loss": 1.1874,
      "step": 3225
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001325067385444744,
      "loss": 1.1561,
      "step": 3230
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001323989218328841,
      "loss": 1.1272,
      "step": 3235
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013229110512129382,
      "loss": 1.1693,
      "step": 3240
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001321832884097035,
      "loss": 1.1922,
      "step": 3245
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001320754716981132,
      "loss": 1.1438,
      "step": 3250
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013196765498652292,
      "loss": 1.173,
      "step": 3255
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013185983827493264,
      "loss": 1.216,
      "step": 3260
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013175202156334232,
      "loss": 1.1613,
      "step": 3265
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000131644204851752,
      "loss": 1.183,
      "step": 3270
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013153638814016174,
      "loss": 1.1592,
      "step": 3275
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013142857142857143,
      "loss": 1.1487,
      "step": 3280
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013132075471698114,
      "loss": 1.1542,
      "step": 3285
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013121293800539085,
      "loss": 1.1404,
      "step": 3290
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013110512129380054,
      "loss": 1.192,
      "step": 3295
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00013099730458221025,
      "loss": 1.1616,
      "step": 3300
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00013088948787061993,
      "loss": 1.1554,
      "step": 3305
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00013078167115902967,
      "loss": 1.1501,
      "step": 3310
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00013067385444743936,
      "loss": 1.1444,
      "step": 3315
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00013056603773584907,
      "loss": 1.1486,
      "step": 3320
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00013045822102425878,
      "loss": 1.1683,
      "step": 3325
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013035040431266847,
      "loss": 1.1676,
      "step": 3330
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013024258760107818,
      "loss": 1.1348,
      "step": 3335
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013013477088948786,
      "loss": 1.196,
      "step": 3340
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013002695417789757,
      "loss": 1.1632,
      "step": 3345
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012991913746630729,
      "loss": 1.1347,
      "step": 3350
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012981132075471697,
      "loss": 1.1729,
      "step": 3355
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001297035040431267,
      "loss": 1.1397,
      "step": 3360
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001295956873315364,
      "loss": 1.1299,
      "step": 3365
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001294878706199461,
      "loss": 1.1473,
      "step": 3370
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001293800539083558,
      "loss": 1.182,
      "step": 3375
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001292722371967655,
      "loss": 1.1584,
      "step": 3380
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00012916442048517521,
      "loss": 1.1567,
      "step": 3385
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001290566037735849,
      "loss": 1.1754,
      "step": 3390
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001289487870619946,
      "loss": 1.1705,
      "step": 3395
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012884097035040432,
      "loss": 1.1595,
      "step": 3400
    },
    {
      "epoch": 1.09,
      "eval_loss": 1.1373599767684937,
      "eval_runtime": 707.276,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 0.884,
      "step": 3400
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000128733153638814,
      "loss": 1.1678,
      "step": 3405
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012862533692722372,
      "loss": 1.1624,
      "step": 3410
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012851752021563343,
      "loss": 1.1587,
      "step": 3415
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012840970350404314,
      "loss": 1.1972,
      "step": 3420
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012830188679245283,
      "loss": 1.1342,
      "step": 3425
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012819407008086254,
      "loss": 1.1575,
      "step": 3430
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012808625336927225,
      "loss": 1.1345,
      "step": 3435
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012797843665768194,
      "loss": 1.1628,
      "step": 3440
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012787061994609165,
      "loss": 1.1448,
      "step": 3445
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012776280323450136,
      "loss": 1.1618,
      "step": 3450
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012765498652291104,
      "loss": 1.1748,
      "step": 3455
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012754716981132076,
      "loss": 1.1441,
      "step": 3460
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012743935309973047,
      "loss": 1.1295,
      "step": 3465
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012733153638814018,
      "loss": 1.1516,
      "step": 3470
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012722371967654987,
      "loss": 1.1544,
      "step": 3475
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012711590296495958,
      "loss": 1.1614,
      "step": 3480
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001270080862533693,
      "loss": 1.1111,
      "step": 3485
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012690026954177897,
      "loss": 1.1604,
      "step": 3490
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012679245283018869,
      "loss": 1.1578,
      "step": 3495
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001266846361185984,
      "loss": 1.1796,
      "step": 3500
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001265768194070081,
      "loss": 1.1302,
      "step": 3505
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001264690026954178,
      "loss": 1.1551,
      "step": 3510
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012636118598382748,
      "loss": 1.1396,
      "step": 3515
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012625336927223722,
      "loss": 1.1993,
      "step": 3520
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001261455525606469,
      "loss": 1.153,
      "step": 3525
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012603773584905661,
      "loss": 1.1839,
      "step": 3530
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012592991913746633,
      "loss": 1.1693,
      "step": 3535
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.000125822102425876,
      "loss": 1.1559,
      "step": 3540
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012571428571428572,
      "loss": 1.1438,
      "step": 3545
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001256064690026954,
      "loss": 1.1634,
      "step": 3550
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012549865229110515,
      "loss": 1.1733,
      "step": 3555
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012539083557951483,
      "loss": 1.1699,
      "step": 3560
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012528301886792452,
      "loss": 1.1223,
      "step": 3565
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012517520215633425,
      "loss": 1.1479,
      "step": 3570
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012506738544474394,
      "loss": 1.1594,
      "step": 3575
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012495956873315365,
      "loss": 1.188,
      "step": 3580
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012485175202156334,
      "loss": 1.1451,
      "step": 3585
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012474393530997305,
      "loss": 1.1168,
      "step": 3590
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012463611859838276,
      "loss": 1.1582,
      "step": 3595
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012452830188679244,
      "loss": 1.1721,
      "step": 3600
    },
    {
      "epoch": 1.15,
      "eval_loss": 1.1364716291427612,
      "eval_runtime": 707.3467,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 0.884,
      "step": 3600
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012442048517520218,
      "loss": 1.1667,
      "step": 3605
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012431266846361187,
      "loss": 1.1731,
      "step": 3610
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012420485175202158,
      "loss": 1.1318,
      "step": 3615
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012409703504043126,
      "loss": 1.1717,
      "step": 3620
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012398921832884098,
      "loss": 1.1834,
      "step": 3625
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001238814016172507,
      "loss": 1.1426,
      "step": 3630
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012377358490566037,
      "loss": 1.1699,
      "step": 3635
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012366576819407009,
      "loss": 1.1116,
      "step": 3640
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001235579514824798,
      "loss": 1.1386,
      "step": 3645
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012345013477088948,
      "loss": 1.1674,
      "step": 3650
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001233423180592992,
      "loss": 1.1717,
      "step": 3655
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001232345013477089,
      "loss": 1.1575,
      "step": 3660
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012312668463611862,
      "loss": 1.154,
      "step": 3665
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001230188679245283,
      "loss": 1.1679,
      "step": 3670
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012291105121293801,
      "loss": 1.1936,
      "step": 3675
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012280323450134773,
      "loss": 1.1326,
      "step": 3680
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001226954177897574,
      "loss": 1.1841,
      "step": 3685
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012258760107816712,
      "loss": 1.1508,
      "step": 3690
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012247978436657683,
      "loss": 1.1581,
      "step": 3695
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012237196765498652,
      "loss": 1.1439,
      "step": 3700
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012226415094339623,
      "loss": 1.1153,
      "step": 3705
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012215633423180594,
      "loss": 1.1526,
      "step": 3710
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012204851752021564,
      "loss": 1.1678,
      "step": 3715
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012194070080862534,
      "loss": 1.1265,
      "step": 3720
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012183288409703504,
      "loss": 1.1766,
      "step": 3725
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012172506738544476,
      "loss": 1.1777,
      "step": 3730
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012161725067385446,
      "loss": 1.1883,
      "step": 3735
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012150943396226415,
      "loss": 1.2069,
      "step": 3740
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012140161725067384,
      "loss": 1.1264,
      "step": 3745
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012129380053908357,
      "loss": 1.1968,
      "step": 3750
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012118598382749327,
      "loss": 1.1553,
      "step": 3755
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012107816711590297,
      "loss": 1.1365,
      "step": 3760
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012097035040431268,
      "loss": 1.1957,
      "step": 3765
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012086253369272238,
      "loss": 1.165,
      "step": 3770
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012075471698113207,
      "loss": 1.1731,
      "step": 3775
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012064690026954177,
      "loss": 1.1722,
      "step": 3780
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001205390835579515,
      "loss": 1.1643,
      "step": 3785
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001204312668463612,
      "loss": 1.1166,
      "step": 3790
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012032345013477088,
      "loss": 1.1508,
      "step": 3795
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001202156334231806,
      "loss": 1.1597,
      "step": 3800
    },
    {
      "epoch": 1.22,
      "eval_loss": 1.1354634761810303,
      "eval_runtime": 707.7384,
      "eval_samples_per_second": 7.065,
      "eval_steps_per_second": 0.883,
      "step": 3800
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001201078167115903,
      "loss": 1.1863,
      "step": 3805
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00012,
      "loss": 1.1569,
      "step": 3810
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001198921832884097,
      "loss": 1.1685,
      "step": 3815
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011978436657681941,
      "loss": 1.1185,
      "step": 3820
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011967654986522911,
      "loss": 1.1784,
      "step": 3825
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011956873315363881,
      "loss": 1.1922,
      "step": 3830
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011946091644204854,
      "loss": 1.152,
      "step": 3835
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011935309973045823,
      "loss": 1.1643,
      "step": 3840
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011924528301886793,
      "loss": 1.1586,
      "step": 3845
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011913746630727762,
      "loss": 1.1564,
      "step": 3850
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011902964959568734,
      "loss": 1.0981,
      "step": 3855
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011892183288409704,
      "loss": 1.1387,
      "step": 3860
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011881401617250674,
      "loss": 1.1637,
      "step": 3865
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011870619946091645,
      "loss": 1.1779,
      "step": 3870
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011859838274932615,
      "loss": 1.1363,
      "step": 3875
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011849056603773585,
      "loss": 1.1414,
      "step": 3880
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011838274932614555,
      "loss": 1.1384,
      "step": 3885
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011827493261455527,
      "loss": 1.1393,
      "step": 3890
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011816711590296497,
      "loss": 1.1296,
      "step": 3895
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011805929919137467,
      "loss": 1.1504,
      "step": 3900
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011795148247978438,
      "loss": 1.18,
      "step": 3905
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011784366576819408,
      "loss": 1.1383,
      "step": 3910
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011773584905660378,
      "loss": 1.166,
      "step": 3915
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011762803234501347,
      "loss": 1.1275,
      "step": 3920
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011752021563342319,
      "loss": 1.1321,
      "step": 3925
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011741239892183288,
      "loss": 1.1589,
      "step": 3930
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011730458221024258,
      "loss": 1.1128,
      "step": 3935
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011719676549865231,
      "loss": 1.1594,
      "step": 3940
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000117088948787062,
      "loss": 1.1498,
      "step": 3945
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001169811320754717,
      "loss": 1.1294,
      "step": 3950
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001168733153638814,
      "loss": 1.1314,
      "step": 3955
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011676549865229111,
      "loss": 1.1602,
      "step": 3960
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011665768194070081,
      "loss": 1.1773,
      "step": 3965
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011654986522911051,
      "loss": 1.169,
      "step": 3970
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011644204851752024,
      "loss": 1.1976,
      "step": 3975
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011633423180592992,
      "loss": 1.1487,
      "step": 3980
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011622641509433962,
      "loss": 1.1847,
      "step": 3985
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011611859838274932,
      "loss": 1.2022,
      "step": 3990
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011601078167115904,
      "loss": 1.1604,
      "step": 3995
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011590296495956874,
      "loss": 1.1718,
      "step": 4000
    },
    {
      "epoch": 1.28,
      "eval_loss": 1.1334933042526245,
      "eval_runtime": 707.5579,
      "eval_samples_per_second": 7.067,
      "eval_steps_per_second": 0.883,
      "step": 4000
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011579514824797844,
      "loss": 1.1294,
      "step": 4005
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011568733153638815,
      "loss": 1.1297,
      "step": 4010
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011557951482479785,
      "loss": 1.1582,
      "step": 4015
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011547169811320755,
      "loss": 1.1615,
      "step": 4020
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011536388140161725,
      "loss": 1.1682,
      "step": 4025
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011525606469002697,
      "loss": 1.1441,
      "step": 4030
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011514824797843666,
      "loss": 1.1028,
      "step": 4035
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011504043126684635,
      "loss": 1.1539,
      "step": 4040
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011493261455525608,
      "loss": 1.1719,
      "step": 4045
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011482479784366578,
      "loss": 1.2023,
      "step": 4050
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011471698113207548,
      "loss": 1.128,
      "step": 4055
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011460916442048518,
      "loss": 1.1649,
      "step": 4060
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011450134770889489,
      "loss": 1.1482,
      "step": 4065
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011439353099730459,
      "loss": 1.1421,
      "step": 4070
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.1656,
      "step": 4075
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011417789757412401,
      "loss": 1.136,
      "step": 4080
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011407008086253371,
      "loss": 1.1679,
      "step": 4085
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011396226415094339,
      "loss": 1.1591,
      "step": 4090
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011385444743935309,
      "loss": 1.1228,
      "step": 4095
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011374663072776282,
      "loss": 1.1393,
      "step": 4100
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011363881401617251,
      "loss": 1.1544,
      "step": 4105
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011353099730458221,
      "loss": 1.1307,
      "step": 4110
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011342318059299192,
      "loss": 1.1437,
      "step": 4115
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011331536388140162,
      "loss": 1.1607,
      "step": 4120
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011320754716981132,
      "loss": 1.1565,
      "step": 4125
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011309973045822102,
      "loss": 1.1418,
      "step": 4130
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011299191374663074,
      "loss": 1.151,
      "step": 4135
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011288409703504044,
      "loss": 1.1593,
      "step": 4140
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011277628032345014,
      "loss": 1.1928,
      "step": 4145
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011266846361185985,
      "loss": 1.1668,
      "step": 4150
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011256064690026955,
      "loss": 1.1321,
      "step": 4155
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011245283018867925,
      "loss": 1.1389,
      "step": 4160
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011234501347708895,
      "loss": 1.1438,
      "step": 4165
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011223719676549866,
      "loss": 1.136,
      "step": 4170
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011212938005390836,
      "loss": 1.1436,
      "step": 4175
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011202156334231806,
      "loss": 1.2055,
      "step": 4180
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011191374663072778,
      "loss": 1.1936,
      "step": 4185
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011180592991913748,
      "loss": 1.1591,
      "step": 4190
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011169811320754718,
      "loss": 1.144,
      "step": 4195
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011159029649595688,
      "loss": 1.1639,
      "step": 4200
    },
    {
      "epoch": 1.34,
      "eval_loss": 1.1315429210662842,
      "eval_runtime": 707.0979,
      "eval_samples_per_second": 7.071,
      "eval_steps_per_second": 0.884,
      "step": 4200
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011148247978436659,
      "loss": 1.1696,
      "step": 4205
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011137466307277629,
      "loss": 1.1316,
      "step": 4210
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011126684636118598,
      "loss": 1.1535,
      "step": 4215
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001111590296495957,
      "loss": 1.1378,
      "step": 4220
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001110512129380054,
      "loss": 1.159,
      "step": 4225
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011094339622641509,
      "loss": 1.171,
      "step": 4230
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011083557951482479,
      "loss": 1.1284,
      "step": 4235
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011072776280323452,
      "loss": 1.1462,
      "step": 4240
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011061994609164422,
      "loss": 1.1774,
      "step": 4245
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011051212938005391,
      "loss": 1.1677,
      "step": 4250
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011040431266846363,
      "loss": 1.1548,
      "step": 4255
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011029649595687332,
      "loss": 1.1967,
      "step": 4260
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011018867924528302,
      "loss": 1.1485,
      "step": 4265
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011008086253369272,
      "loss": 1.1481,
      "step": 4270
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010997304582210243,
      "loss": 1.1543,
      "step": 4275
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010986522911051213,
      "loss": 1.1812,
      "step": 4280
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010975741239892183,
      "loss": 1.0901,
      "step": 4285
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010964959568733155,
      "loss": 1.1405,
      "step": 4290
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010954177897574125,
      "loss": 1.17,
      "step": 4295
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010943396226415095,
      "loss": 1.1344,
      "step": 4300
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010932614555256065,
      "loss": 1.1109,
      "step": 4305
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010921832884097036,
      "loss": 1.1368,
      "step": 4310
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010911051212938006,
      "loss": 1.1534,
      "step": 4315
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010900269541778976,
      "loss": 1.1668,
      "step": 4320
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010889487870619948,
      "loss": 1.1145,
      "step": 4325
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010878706199460917,
      "loss": 1.1337,
      "step": 4330
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010867924528301887,
      "loss": 1.1432,
      "step": 4335
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010857142857142856,
      "loss": 1.1403,
      "step": 4340
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010846361185983829,
      "loss": 1.1239,
      "step": 4345
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010835579514824799,
      "loss": 1.1274,
      "step": 4350
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010824797843665769,
      "loss": 1.1574,
      "step": 4355
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001081401617250674,
      "loss": 1.1353,
      "step": 4360
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001080323450134771,
      "loss": 1.1426,
      "step": 4365
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001079245283018868,
      "loss": 1.1307,
      "step": 4370
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010781671159029649,
      "loss": 1.1896,
      "step": 4375
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010770889487870622,
      "loss": 1.1772,
      "step": 4380
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010760107816711592,
      "loss": 1.1649,
      "step": 4385
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001074932614555256,
      "loss": 1.1832,
      "step": 4390
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010738544474393533,
      "loss": 1.1893,
      "step": 4395
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010727762803234502,
      "loss": 1.1448,
      "step": 4400
    },
    {
      "epoch": 1.41,
      "eval_loss": 1.1311901807785034,
      "eval_runtime": 707.1464,
      "eval_samples_per_second": 7.071,
      "eval_steps_per_second": 0.884,
      "step": 4400
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010716981132075472,
      "loss": 1.1392,
      "step": 4405
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010706199460916442,
      "loss": 1.1417,
      "step": 4410
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010695417789757413,
      "loss": 1.1543,
      "step": 4415
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010684636118598383,
      "loss": 1.1421,
      "step": 4420
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010673854447439353,
      "loss": 1.1545,
      "step": 4425
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010663072776280323,
      "loss": 1.1377,
      "step": 4430
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010652291105121295,
      "loss": 1.1899,
      "step": 4435
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010641509433962265,
      "loss": 1.1412,
      "step": 4440
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010630727762803234,
      "loss": 1.1707,
      "step": 4445
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010619946091644206,
      "loss": 1.1455,
      "step": 4450
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010609164420485176,
      "loss": 1.1832,
      "step": 4455
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010598382749326146,
      "loss": 1.1532,
      "step": 4460
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010587601078167116,
      "loss": 1.1417,
      "step": 4465
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010576819407008087,
      "loss": 1.1404,
      "step": 4470
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010566037735849057,
      "loss": 1.1674,
      "step": 4475
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010555256064690027,
      "loss": 1.1477,
      "step": 4480
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010544474393530999,
      "loss": 1.1428,
      "step": 4485
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010533692722371969,
      "loss": 1.1282,
      "step": 4490
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010522911051212939,
      "loss": 1.1439,
      "step": 4495
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010512129380053907,
      "loss": 1.1323,
      "step": 4500
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001050134770889488,
      "loss": 1.134,
      "step": 4505
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001049056603773585,
      "loss": 1.1319,
      "step": 4510
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001047978436657682,
      "loss": 1.1644,
      "step": 4515
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001046900269541779,
      "loss": 1.1127,
      "step": 4520
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001045822102425876,
      "loss": 1.1419,
      "step": 4525
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001044743935309973,
      "loss": 1.1282,
      "step": 4530
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.000104366576819407,
      "loss": 1.1282,
      "step": 4535
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010425876010781673,
      "loss": 1.1401,
      "step": 4540
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010415094339622642,
      "loss": 1.1314,
      "step": 4545
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010404312668463612,
      "loss": 1.1251,
      "step": 4550
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010393530997304583,
      "loss": 1.1312,
      "step": 4555
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010382749326145553,
      "loss": 1.1063,
      "step": 4560
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010371967654986523,
      "loss": 1.1342,
      "step": 4565
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010361185983827493,
      "loss": 1.174,
      "step": 4570
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010350404312668464,
      "loss": 1.1457,
      "step": 4575
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010339622641509434,
      "loss": 1.1475,
      "step": 4580
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010328840970350404,
      "loss": 1.1827,
      "step": 4585
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010318059299191376,
      "loss": 1.1191,
      "step": 4590
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010307277628032346,
      "loss": 1.2093,
      "step": 4595
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010296495956873316,
      "loss": 1.1645,
      "step": 4600
    },
    {
      "epoch": 1.47,
      "eval_loss": 1.1296443939208984,
      "eval_runtime": 706.9133,
      "eval_samples_per_second": 7.073,
      "eval_steps_per_second": 0.884,
      "step": 4600
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010285714285714286,
      "loss": 1.1572,
      "step": 4605
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010274932614555257,
      "loss": 1.1238,
      "step": 4610
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010264150943396227,
      "loss": 1.1377,
      "step": 4615
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010253369272237197,
      "loss": 1.1914,
      "step": 4620
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010242587601078169,
      "loss": 1.133,
      "step": 4625
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010231805929919138,
      "loss": 1.1717,
      "step": 4630
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010221024258760107,
      "loss": 1.1676,
      "step": 4635
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010210242587601077,
      "loss": 1.1174,
      "step": 4640
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001019946091644205,
      "loss": 1.1082,
      "step": 4645
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001018867924528302,
      "loss": 1.1938,
      "step": 4650
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001017789757412399,
      "loss": 1.1183,
      "step": 4655
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001016711590296496,
      "loss": 1.175,
      "step": 4660
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001015633423180593,
      "loss": 1.1243,
      "step": 4665
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.000101455525606469,
      "loss": 1.125,
      "step": 4670
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001013477088948787,
      "loss": 1.1506,
      "step": 4675
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010123989218328843,
      "loss": 1.1263,
      "step": 4680
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010113207547169811,
      "loss": 1.1393,
      "step": 4685
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010102425876010781,
      "loss": 1.1207,
      "step": 4690
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010091644204851754,
      "loss": 1.1945,
      "step": 4695
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010080862533692723,
      "loss": 1.1823,
      "step": 4700
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010070080862533693,
      "loss": 1.1524,
      "step": 4705
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010059299191374663,
      "loss": 1.2009,
      "step": 4710
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010048517520215634,
      "loss": 1.1033,
      "step": 4715
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010037735849056604,
      "loss": 1.1254,
      "step": 4720
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010026954177897574,
      "loss": 1.2103,
      "step": 4725
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010016172506738546,
      "loss": 1.2174,
      "step": 4730
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00010005390835579516,
      "loss": 1.1901,
      "step": 4735
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.994609164420485e-05,
      "loss": 1.1458,
      "step": 4740
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.983827493261456e-05,
      "loss": 1.1377,
      "step": 4745
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.973045822102426e-05,
      "loss": 1.1625,
      "step": 4750
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.962264150943397e-05,
      "loss": 1.1597,
      "step": 4755
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.951482479784368e-05,
      "loss": 1.1348,
      "step": 4760
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.940700808625338e-05,
      "loss": 1.1484,
      "step": 4765
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.929919137466308e-05,
      "loss": 1.1799,
      "step": 4770
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.919137466307278e-05,
      "loss": 1.1738,
      "step": 4775
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.908355795148249e-05,
      "loss": 1.1515,
      "step": 4780
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.897574123989219e-05,
      "loss": 1.1486,
      "step": 4785
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.88679245283019e-05,
      "loss": 1.1394,
      "step": 4790
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.87601078167116e-05,
      "loss": 1.1433,
      "step": 4795
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.86522911051213e-05,
      "loss": 1.1562,
      "step": 4800
    },
    {
      "epoch": 1.54,
      "eval_loss": 1.128167986869812,
      "eval_runtime": 707.3804,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 0.884,
      "step": 4800
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.8544474393531e-05,
      "loss": 1.12,
      "step": 4805
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.84366576819407e-05,
      "loss": 1.1696,
      "step": 4810
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.832884097035042e-05,
      "loss": 1.1363,
      "step": 4815
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.822102425876011e-05,
      "loss": 1.1891,
      "step": 4820
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.811320754716981e-05,
      "loss": 1.1303,
      "step": 4825
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.800539083557952e-05,
      "loss": 1.1488,
      "step": 4830
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.789757412398922e-05,
      "loss": 1.1169,
      "step": 4835
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.778975741239893e-05,
      "loss": 1.0968,
      "step": 4840
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.768194070080863e-05,
      "loss": 1.1275,
      "step": 4845
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.757412398921833e-05,
      "loss": 1.1252,
      "step": 4850
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.746630727762803e-05,
      "loss": 1.1488,
      "step": 4855
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.735849056603774e-05,
      "loss": 1.1267,
      "step": 4860
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.725067385444745e-05,
      "loss": 1.1264,
      "step": 4865
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.714285714285715e-05,
      "loss": 1.1256,
      "step": 4870
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.703504043126685e-05,
      "loss": 1.1534,
      "step": 4875
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.692722371967655e-05,
      "loss": 1.1283,
      "step": 4880
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.681940700808626e-05,
      "loss": 1.1439,
      "step": 4885
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.671159029649596e-05,
      "loss": 1.1406,
      "step": 4890
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.660377358490567e-05,
      "loss": 1.1333,
      "step": 4895
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.649595687331537e-05,
      "loss": 1.1718,
      "step": 4900
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.638814016172507e-05,
      "loss": 1.1617,
      "step": 4905
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.628032345013478e-05,
      "loss": 1.1754,
      "step": 4910
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.617250673854448e-05,
      "loss": 1.1204,
      "step": 4915
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.606469002695419e-05,
      "loss": 1.1385,
      "step": 4920
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.595687331536389e-05,
      "loss": 1.1249,
      "step": 4925
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.584905660377359e-05,
      "loss": 1.1681,
      "step": 4930
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.574123989218328e-05,
      "loss": 1.1449,
      "step": 4935
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.5633423180593e-05,
      "loss": 1.117,
      "step": 4940
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.552560646900271e-05,
      "loss": 1.1392,
      "step": 4945
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.54177897574124e-05,
      "loss": 1.1271,
      "step": 4950
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.53099730458221e-05,
      "loss": 1.157,
      "step": 4955
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.52021563342318e-05,
      "loss": 1.1708,
      "step": 4960
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.509433962264151e-05,
      "loss": 1.1373,
      "step": 4965
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.498652291105121e-05,
      "loss": 1.1687,
      "step": 4970
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.487870619946092e-05,
      "loss": 1.1701,
      "step": 4975
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.477088948787062e-05,
      "loss": 1.1579,
      "step": 4980
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.466307277628032e-05,
      "loss": 1.1384,
      "step": 4985
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.455525606469003e-05,
      "loss": 1.1591,
      "step": 4990
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.444743935309973e-05,
      "loss": 1.1136,
      "step": 4995
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.433962264150944e-05,
      "loss": 1.1619,
      "step": 5000
    },
    {
      "epoch": 1.6,
      "eval_loss": 1.1272780895233154,
      "eval_runtime": 707.2365,
      "eval_samples_per_second": 7.07,
      "eval_steps_per_second": 0.884,
      "step": 5000
    }
  ],
  "max_steps": 9375,
  "num_train_epochs": 3,
  "total_flos": 2.9779927498752e+17,
  "trial_name": null,
  "trial_params": null
}