{
  "best_metric": 2.005824327468872,
  "best_model_checkpoint": "saves/ChineseLLaMA2-7B-Chat/lora/SFT/checkpoint-1500",
  "epoch": 2.0547945205479454,
  "eval_steps": 100,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.000999995369868095,
      "loss": 4.0099,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009999670749281082,
      "loss": 2.887,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000999913058797528,
      "loss": 2.6742,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009998333242552556,
      "loss": 2.7939,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009997278754032958,
      "loss": 2.6062,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009995967176665461,
      "loss": 2.7508,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009994398577925167,
      "loss": 2.547,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009992573038509849,
      "loss": 2.5281,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0009990490652335784,
      "loss": 2.6397,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000998815152653293,
      "loss": 2.608,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000998555578143941,
      "loss": 2.4076,
      "step": 55
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009982703550595329,
      "loss": 2.5914,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009979594980735896,
      "loss": 2.3517,
      "step": 65
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009976230231783876,
      "loss": 2.4019,
      "step": 70
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009972609476841367,
      "loss": 2.4481,
      "step": 75
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000996873290218089,
      "loss": 2.3244,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000996460070723581,
      "loss": 2.4821,
      "step": 85
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009960213104590074,
      "loss": 2.438,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0009955570319967273,
      "loss": 2.2925,
      "step": 95
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009950672592219031,
      "loss": 2.3052,
      "step": 100
    },
    {
      "epoch": 0.14,
      "eval_loss": 2.3112449645996094,
      "eval_runtime": 8.9668,
      "eval_samples_per_second": 13.16,
      "eval_steps_per_second": 1.673,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000994552017331272,
      "loss": 2.5839,
      "step": 105
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009940113328318488,
      "loss": 2.4983,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0009934452335395637,
      "loss": 2.4598,
      "step": 115
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0009928537485778299,
      "loss": 2.4336,
      "step": 120
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009922369083760461,
      "loss": 2.3799,
      "step": 125
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0009915947446680307,
      "loss": 2.5443,
      "step": 130
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0009909272904903897,
      "loss": 2.3701,
      "step": 135
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0009902345801808161,
      "loss": 2.2718,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009895166493763246,
      "loss": 2.3402,
      "step": 145
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0009887735350114174,
      "loss": 2.4072,
      "step": 150
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000988005275316184,
      "loss": 2.3807,
      "step": 155
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000987211909814336,
      "loss": 2.2149,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000986393479321171,
      "loss": 2.2713,
      "step": 165
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009855500259414753,
      "loss": 2.08,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0009846815930673563,
      "loss": 2.4682,
      "step": 175
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000983788225376011,
      "loss": 2.3328,
      "step": 180
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0009828699688274275,
      "loss": 2.3671,
      "step": 185
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0009819268706620196,
      "loss": 2.3251,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009809589793981978,
      "loss": 2.4429,
      "step": 195
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009799663448298724,
      "loss": 2.2499,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 2.234222650527954,
      "eval_runtime": 8.8394,
      "eval_samples_per_second": 13.349,
      "eval_steps_per_second": 1.697,
      "step": 200
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0009789490180238916,
      "loss": 2.2279,
      "step": 205
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009779070513174157,
      "loss": 2.4875,
      "step": 210
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009768404983152227,
      "loss": 2.3507,
      "step": 215
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0009757494138869523,
      "loss": 2.2189,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009746338541642812,
      "loss": 2.2597,
      "step": 225
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0009734938765380377,
      "loss": 2.334,
      "step": 230
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000972329539655247,
      "loss": 2.3133,
      "step": 235
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0009711409034161151,
      "loss": 2.2286,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009699280289709478,
      "loss": 2.224,
      "step": 245
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009686909787170031,
      "loss": 2.3772,
      "step": 250
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0009674298162952826,
      "loss": 2.3606,
      "step": 255
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0009661446065872568,
      "loss": 2.3207,
      "step": 260
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0009648354157115271,
      "loss": 2.2505,
      "step": 265
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0009635023110204253,
      "loss": 2.2192,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009621453610965467,
      "loss": 2.3082,
      "step": 275
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009607646357492237,
      "loss": 2.2913,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009593602060109334,
      "loss": 2.1133,
      "step": 285
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009579321441336436,
      "loss": 2.1855,
      "step": 290
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009564805235850955,
      "loss": 2.3691,
      "step": 295
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0009550054190450246,
      "loss": 2.1942,
      "step": 300
    },
    {
      "epoch": 0.41,
      "eval_loss": 2.184567451477051,
      "eval_runtime": 8.8391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000953506906401318,
      "loss": 2.2661,
      "step": 305
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009519850627461109,
      "loss": 2.1222,
      "step": 310
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009504399663718202,
      "loss": 2.2852,
      "step": 315
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009488716967671169,
      "loss": 2.2543,
      "step": 320
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009472803346128368,
      "loss": 2.4232,
      "step": 325
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009456659617778294,
      "loss": 2.3455,
      "step": 330
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009440286613147466,
      "loss": 2.2071,
      "step": 335
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009423685174557695,
      "loss": 2.2561,
      "step": 340
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009406856156082755,
      "loss": 2.2257,
      "step": 345
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009389800423504441,
      "loss": 2.0418,
      "step": 350
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000937251885426803,
      "loss": 2.1139,
      "step": 355
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0009355012337437138,
      "loss": 2.0349,
      "step": 360
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0009337281773647985,
      "loss": 2.1056,
      "step": 365
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009319328075063059,
      "loss": 2.0944,
      "step": 370
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009301152165324185,
      "loss": 2.0468,
      "step": 375
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009282754979505018,
      "loss": 2.4125,
      "step": 380
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009264137464062927,
      "loss": 2.14,
      "step": 385
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009245300576790309,
      "loss": 2.0077,
      "step": 390
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009226245286765316,
      "loss": 2.0926,
      "step": 395
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009206972574301991,
      "loss": 2.2612,
      "step": 400
    },
    {
      "epoch": 0.55,
      "eval_loss": 2.1513657569885254,
      "eval_runtime": 8.8395,
      "eval_samples_per_second": 13.349,
      "eval_steps_per_second": 1.697,
      "step": 400
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009187483430899845,
      "loss": 2.1961,
      "step": 405
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000916777885919285,
      "loss": 2.21,
      "step": 410
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009147859872897843,
      "loss": 2.1734,
      "step": 415
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009127727496762394,
      "loss": 2.2751,
      "step": 420
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009107382766512072,
      "loss": 2.165,
      "step": 425
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009086826728797165,
      "loss": 1.9987,
      "step": 430
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009066060441138841,
      "loss": 2.2766,
      "step": 435
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009045084971874737,
      "loss": 2.2556,
      "step": 440
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0009023901400103995,
      "loss": 2.2067,
      "step": 445
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0009002510815631754,
      "loss": 2.1062,
      "step": 450
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008980914318913078,
      "loss": 2.2781,
      "step": 455
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008959113020996348,
      "loss": 2.2977,
      "step": 460
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008937108043466098,
      "loss": 2.1739,
      "step": 465
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008914900518385314,
      "loss": 2.2108,
      "step": 470
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008892491588237203,
      "loss": 2.204,
      "step": 475
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0008869882405866404,
      "loss": 2.0958,
      "step": 480
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000884707413441969,
      "loss": 2.1794,
      "step": 485
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0008824067947286121,
      "loss": 2.2172,
      "step": 490
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0008800865028036685,
      "loss": 2.1321,
      "step": 495
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0008777466570363402,
      "loss": 2.1153,
      "step": 500
    },
    {
      "epoch": 0.68,
      "eval_loss": 2.1377201080322266,
      "eval_runtime": 8.8389,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0008753873778017918,
      "loss": 2.0652,
      "step": 505
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0008730087864749578,
      "loss": 2.1858,
      "step": 510
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0008706110054242979,
      "loss": 2.3533,
      "step": 515
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0008681941580055016,
      "loss": 2.0069,
      "step": 520
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0008657583685551429,
      "loss": 2.2022,
      "step": 525
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0008633037623842828,
      "loss": 2.2126,
      "step": 530
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0008608304657720232,
      "loss": 2.1354,
      "step": 535
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00085833860595901,
      "loss": 2.3017,
      "step": 540
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0008558283111408874,
      "loss": 2.1492,
      "step": 545
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0008532997104617022,
      "loss": 2.3461,
      "step": 550
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0008507529340072608,
      "loss": 2.2892,
      "step": 555
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0008481881127984361,
      "loss": 2.1384,
      "step": 560
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0008456053787844274,
      "loss": 2.2022,
      "step": 565
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0008430048648359713,
      "loss": 2.1867,
      "step": 570
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000840386704738508,
      "loss": 2.0888,
      "step": 575
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0008377510331852969,
      "loss": 2.1194,
      "step": 580
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0008350979857704872,
      "loss": 2.1946,
      "step": 585
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008324276989821433,
      "loss": 2.2366,
      "step": 590
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008297403101952221,
      "loss": 2.2807,
      "step": 595
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008270359576645061,
      "loss": 2.2787,
      "step": 600
    },
    {
      "epoch": 0.82,
      "eval_loss": 2.1165168285369873,
      "eval_runtime": 8.8529,
      "eval_samples_per_second": 13.329,
      "eval_steps_per_second": 1.694,
      "step": 600
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0008243147805174907,
      "loss": 2.1761,
      "step": 605
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0008215769187472266,
      "loss": 2.036,
      "step": 610
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0008188225132051175,
      "loss": 2.3055,
      "step": 615
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0008160517055936743,
      "loss": 2.1386,
      "step": 620
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0008132646384592254,
      "loss": 2.2383,
      "step": 625
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0008104614551845823,
      "loss": 2.0414,
      "step": 630
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000807642299981664,
      "loss": 2.1539,
      "step": 635
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0008048073178840773,
      "loss": 2.2804,
      "step": 640
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0008019566547396563,
      "loss": 2.0363,
      "step": 645
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007990904572029582,
      "loss": 2.152,
      "step": 650
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0007962088727277193,
      "loss": 2.1571,
      "step": 655
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0007933120495592682,
      "loss": 2.1813,
      "step": 660
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0007904001367269004,
      "loss": 2.2906,
      "step": 665
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0007874732840362107,
      "loss": 2.2132,
      "step": 670
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0007845316420613859,
      "loss": 2.0774,
      "step": 675
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0007815753621374593,
      "loss": 2.1264,
      "step": 680
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0007786045963525249,
      "loss": 2.1156,
      "step": 685
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0007756194975399123,
      "loss": 2.0804,
      "step": 690
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0007726202192703255,
      "loss": 2.2225,
      "step": 695
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0007696069158439412,
      "loss": 2.0872,
      "step": 700
    },
    {
      "epoch": 0.96,
      "eval_loss": 2.0954582691192627,
      "eval_runtime": 8.8391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 700
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0007665797422824708,
      "loss": 2.0316,
      "step": 705
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0007635388543211861,
      "loss": 2.1545,
      "step": 710
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0007604844084009063,
      "loss": 2.082,
      "step": 715
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0007574165616599501,
      "loss": 2.1494,
      "step": 720
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0007543354719260522,
      "loss": 2.2864,
      "step": 725
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000751241297708243,
      "loss": 2.122,
      "step": 730
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0007481341981886942,
      "loss": 1.9816,
      "step": 735
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0007450143332145297,
      "loss": 1.8529,
      "step": 740
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0007418818632896017,
      "loss": 1.936,
      "step": 745
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0007387369495662343,
      "loss": 1.9031,
      "step": 750
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000735579753836932,
      "loss": 1.8006,
      "step": 755
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0007324104385260566,
      "loss": 1.9221,
      "step": 760
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0007292291666814713,
      "loss": 1.9734,
      "step": 765
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0007260361019661522,
      "loss": 2.0162,
      "step": 770
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0007228314086497686,
      "loss": 1.755,
      "step": 775
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0007196152516002323,
      "loss": 2.0059,
      "step": 780
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0007163877962752157,
      "loss": 2.0842,
      "step": 785
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0007131492087136393,
      "loss": 2.0298,
      "step": 790
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0007098996555271309,
      "loss": 2.0099,
      "step": 795
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0007066393038914522,
      "loss": 2.0318,
      "step": 800
    },
    {
      "epoch": 1.1,
      "eval_loss": 2.081965923309326,
      "eval_runtime": 8.8393,
      "eval_samples_per_second": 13.349,
      "eval_steps_per_second": 1.697,
      "step": 800
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0007033683215379002,
      "loss": 2.0159,
      "step": 805
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0007000868767446771,
      "loss": 2.0416,
      "step": 810
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0006967951383282334,
      "loss": 1.9853,
      "step": 815
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.000693493275634583,
      "loss": 2.0131,
      "step": 820
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0006901814585305909,
      "loss": 1.9054,
      "step": 825
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0006868598573952345,
      "loss": 1.9213,
      "step": 830
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0006835286431108383,
      "loss": 1.8538,
      "step": 835
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0006801879870542821,
      "loss": 2.0632,
      "step": 840
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0006768380610881859,
      "loss": 2.0617,
      "step": 845
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0006734790375520663,
      "loss": 1.9131,
      "step": 850
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0006701110892534723,
      "loss": 1.969,
      "step": 855
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0006667343894590934,
      "loss": 2.1041,
      "step": 860
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0006633491118858471,
      "loss": 1.9544,
      "step": 865
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0006599554306919408,
      "loss": 1.9392,
      "step": 870
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0006565535204679134,
      "loss": 1.9857,
      "step": 875
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0006531435562276514,
      "loss": 2.0771,
      "step": 880
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0006497257133993877,
      "loss": 1.9266,
      "step": 885
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0006463001678166743,
      "loss": 1.9898,
      "step": 890
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0006428670957093375,
      "loss": 1.9723,
      "step": 895
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0006394266736944118,
      "loss": 1.9746,
      "step": 900
    },
    {
      "epoch": 1.23,
      "eval_loss": 2.0750818252563477,
      "eval_runtime": 8.84,
      "eval_samples_per_second": 13.348,
      "eval_steps_per_second": 1.697,
      "step": 900
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0006359790787670527,
      "loss": 1.8354,
      "step": 905
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0006325244882914327,
      "loss": 1.8571,
      "step": 910
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0006290630799916144,
      "loss": 2.0376,
      "step": 915
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0006255950319424097,
      "loss": 2.0141,
      "step": 920
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0006221205225602169,
      "loss": 1.982,
      "step": 925
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0006186397305938427,
      "loss": 1.9456,
      "step": 930
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0006151528351153061,
      "loss": 1.8855,
      "step": 935
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0006116600155106263,
      "loss": 1.9335,
      "step": 940
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0006081614514705933,
      "loss": 1.9459,
      "step": 945
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0006046573229815243,
      "loss": 1.9753,
      "step": 950
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0006011478103160037,
      "loss": 1.969,
      "step": 955
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0005976330940236089,
      "loss": 1.9184,
      "step": 960
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0005941133549216221,
      "loss": 1.9287,
      "step": 965
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0005905887740857279,
      "loss": 1.9373,
      "step": 970
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0005870595328406971,
      "loss": 1.9323,
      "step": 975
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0005835258127510597,
      "loss": 1.9249,
      "step": 980
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0005799877956117621,
      "loss": 2.0135,
      "step": 985
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0005764456634388171,
      "loss": 1.9741,
      "step": 990
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0005728995984599373,
      "loss": 1.9028,
      "step": 995
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0005693497831051624,
      "loss": 1.9647,
      "step": 1000
    },
    {
      "epoch": 1.37,
      "eval_loss": 2.0705747604370117,
      "eval_runtime": 8.8388,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 1000
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0005657963999974728,
      "loss": 1.9312,
      "step": 1005
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0005622396319433947,
      "loss": 1.9319,
      "step": 1010
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0005586796619235951,
      "loss": 2.0215,
      "step": 1015
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0005551166730834692,
      "loss": 1.9109,
      "step": 1020
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0005515508487237174,
      "loss": 1.9534,
      "step": 1025
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0005479823722909158,
      "loss": 1.9559,
      "step": 1030
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0005444114273680778,
      "loss": 1.9402,
      "step": 1035
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0005408381976652113,
      "loss": 1.8844,
      "step": 1040
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0005372628670098654,
      "loss": 1.8787,
      "step": 1045
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0005336856193376748,
      "loss": 2.0642,
      "step": 1050
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0005301066386828965,
      "loss": 2.0661,
      "step": 1055
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0005265261091689423,
      "loss": 1.8911,
      "step": 1060
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0005229442149989058,
      "loss": 1.9742,
      "step": 1065
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0005193611404460872,
      "loss": 1.8662,
      "step": 1070
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0005157770698445116,
      "loss": 1.9766,
      "step": 1075
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0005121921875794468,
      "loss": 1.8823,
      "step": 1080
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0005086066780779174,
      "loss": 2.0215,
      "step": 1085
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0005050207257992166,
      "loss": 2.002,
      "step": 1090
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0005014345152254166,
      "loss": 2.0568,
      "step": 1095
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0004978482308518779,
      "loss": 2.0477,
      "step": 1100
    },
    {
      "epoch": 1.51,
      "eval_loss": 2.0488994121551514,
      "eval_runtime": 8.8391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 1100
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0004942620571777576,
      "loss": 1.9615,
      "step": 1105
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0004906761786965175,
      "loss": 1.9747,
      "step": 1110
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00048709077988643367,
      "loss": 2.0174,
      "step": 1115
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0004835060452011041,
      "loss": 1.927,
      "step": 1120
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00047992215905996163,
      "loss": 1.8728,
      "step": 1125
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0004763393058387841,
      "loss": 2.0364,
      "step": 1130
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00047275766986021046,
      "loss": 1.9834,
      "step": 1135
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0004691774353842571,
      "loss": 1.838,
      "step": 1140
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0004655987865988401,
      "loss": 1.8644,
      "step": 1145
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0004620219076102975,
      "loss": 1.9723,
      "step": 1150
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0004584469824339192,
      "loss": 1.7848,
      "step": 1155
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0004548741949844795,
      "loss": 1.9848,
      "step": 1160
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0004513037290667761,
      "loss": 1.9545,
      "step": 1165
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00044773576836617336,
      "loss": 2.0322,
      "step": 1170
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0004441704964391529,
      "loss": 1.933,
      "step": 1175
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0004406080967038701,
      "loss": 1.8019,
      "step": 1180
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0004370487524307189,
      "loss": 1.9489,
      "step": 1185
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00043349264673290204,
      "loss": 1.9982,
      "step": 1190
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0004299399625570114,
      "loss": 1.9536,
      "step": 1195
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00042639088267361596,
      "loss": 1.849,
      "step": 1200
    },
    {
      "epoch": 1.64,
      "eval_loss": 2.030912160873413,
      "eval_runtime": 8.838,
      "eval_samples_per_second": 13.351,
      "eval_steps_per_second": 1.697,
      "step": 1200
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00042284558966785944,
      "loss": 1.9273,
      "step": 1205
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00041930426593006633,
      "loss": 1.9215,
      "step": 1210
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0004157670936463592,
      "loss": 2.0457,
      "step": 1215
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00041223425478928595,
      "loss": 1.9452,
      "step": 1220
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0004087059311084581,
      "loss": 2.033,
      "step": 1225
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0004051823041212002,
      "loss": 1.9818,
      "step": 1230
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00040166355510321195,
      "loss": 2.0649,
      "step": 1235
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00039814986507924195,
      "loss": 1.8362,
      "step": 1240
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0003946414148137756,
      "loss": 2.017,
      "step": 1245
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0003911383848017341,
      "loss": 1.871,
      "step": 1250
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0003876409552591901,
      "loss": 1.9843,
      "step": 1255
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00038414930611409525,
      "loss": 1.7489,
      "step": 1260
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.000380663616997025,
      "loss": 2.071,
      "step": 1265
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00037718406723193576,
      "loss": 2.0351,
      "step": 1270
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0003737108358269408,
      "loss": 1.9891,
      "step": 1275
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00037024410146510014,
      "loss": 2.0055,
      "step": 1280
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0003667840424952288,
      "loss": 1.9104,
      "step": 1285
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00036333083692272083,
      "loss": 1.9239,
      "step": 1290
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00035988466240039206,
      "loss": 1.8592,
      "step": 1295
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0003564456962193403,
      "loss": 2.0883,
      "step": 1300
    },
    {
      "epoch": 1.78,
      "eval_loss": 2.012606382369995,
      "eval_runtime": 8.8391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 1300
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0003530141152998255,
      "loss": 1.8061,
      "step": 1305
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0003495900961821662,
      "loss": 1.8564,
      "step": 1310
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0003461738150176588,
      "loss": 2.0208,
      "step": 1315
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00034276544755951444,
      "loss": 2.0325,
      "step": 1320
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00033936516915381774,
      "loss": 1.9853,
      "step": 1325
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00033597315473050596,
      "loss": 1.8627,
      "step": 1330
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00033258957879436893,
      "loss": 1.7516,
      "step": 1335
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00032921461541607225,
      "loss": 1.8258,
      "step": 1340
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0003258484382232023,
      "loss": 1.9302,
      "step": 1345
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00032249122039133273,
      "loss": 1.8517,
      "step": 1350
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00031914313463511635,
      "loss": 1.9234,
      "step": 1355
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000315804353199399,
      "loss": 1.7208,
      "step": 1360
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0003124750478503593,
      "loss": 1.9718,
      "step": 1365
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0003091553898666705,
      "loss": 1.9739,
      "step": 1370
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00030584555003069017,
      "loss": 1.9678,
      "step": 1375
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0003025456986196734,
      "loss": 1.859,
      "step": 1380
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002992560053970135,
      "loss": 1.866,
      "step": 1385
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002959766396035077,
      "loss": 1.8789,
      "step": 1390
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002927077699486507,
      "loss": 1.9049,
      "step": 1395
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00028944956460195514,
      "loss": 1.9501,
      "step": 1400
    },
    {
      "epoch": 1.92,
      "eval_loss": 2.006899833679199,
      "eval_runtime": 8.8391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 1400
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002862021911843008,
      "loss": 1.9477,
      "step": 1405
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00028296581675930964,
      "loss": 1.8011,
      "step": 1410
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00027974060782475255,
      "loss": 1.9646,
      "step": 1415
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.000276526730303983,
      "loss": 1.7943,
      "step": 1420
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002733243495374013,
      "loss": 1.8871,
      "step": 1425
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.000270133630273948,
      "loss": 1.9161,
      "step": 1430
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00026695473666262925,
      "loss": 1.7969,
      "step": 1435
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002637878322440708,
      "loss": 1.9717,
      "step": 1440
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00026063307994210586,
      "loss": 1.8904,
      "step": 1445
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00025749064205539206,
      "loss": 1.8843,
      "step": 1450
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002543606802490628,
      "loss": 1.9602,
      "step": 1455
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00025124335554640965,
      "loss": 1.8936,
      "step": 1460
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00024813882832059914,
      "loss": 1.6483,
      "step": 1465
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00024504725828642125,
      "loss": 1.7576,
      "step": 1470
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00024196880449207364,
      "loss": 1.7134,
      "step": 1475
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002389036253109787,
      "loss": 1.7071,
      "step": 1480
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00023585187843363614,
      "loss": 1.7951,
      "step": 1485
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00023281372085951068,
      "loss": 1.6741,
      "step": 1490
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00022978930888895466,
      "loss": 1.6294,
      "step": 1495
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00022677879811516715,
      "loss": 1.7268,
      "step": 1500
    },
    {
      "epoch": 2.05,
      "eval_loss": 2.005824327468872,
      "eval_runtime": 8.8391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 1.697,
      "step": 1500
    }
  ],
  "logging_steps": 5,
  "max_steps": 2190,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 4.432472626272338e+17,
  "trial_name": null,
  "trial_params": null
}