{
  "best_metric": 1.153731107711792,
  "best_model_checkpoint": "outputs/checkpoint-2000",
  "epoch": 0.64,
  "global_step": 2000,
  "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
    }
  ],
  "max_steps": 9375,
  "num_train_epochs": 3,
  "total_flos": 1.19119709995008e+17,
  "trial_name": null,
  "trial_params": null
}