{
  "best_metric": 0.6470396518707275,
  "best_model_checkpoint": "checkpoints/instrucode/with_input/1a_52k/checkpoint-3000",
  "epoch": 1.9198464122870171,
  "eval_steps": 200,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 1.8998,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 1.8477,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.4e-05,
      "loss": 1.5682,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.1025,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014399999999999998,
      "loss": 0.9534,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017399999999999997,
      "loss": 0.9024,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000204,
      "loss": 0.7691,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000234,
      "loss": 0.712,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00026399999999999997,
      "loss": 0.7302,
      "step": 90
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000294,
      "loss": 0.6993,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002996887159533074,
      "loss": 0.6977,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002992996108949416,
      "loss": 0.6908,
      "step": 120
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00029891050583657586,
      "loss": 0.6971,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002985214007782101,
      "loss": 0.6838,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00029813229571984433,
      "loss": 0.6588,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002977431906614786,
      "loss": 0.672,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002973540856031128,
      "loss": 0.6933,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00029696498054474705,
      "loss": 0.6926,
      "step": 180
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002965758754863813,
      "loss": 0.6862,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00029618677042801553,
      "loss": 0.672,
      "step": 200
    },
    {
      "epoch": 0.13,
      "eval_loss": 0.6792568564414978,
      "eval_runtime": 292.2523,
      "eval_samples_per_second": 6.843,
      "eval_steps_per_second": 0.855,
      "step": 200
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00029579766536964977,
      "loss": 0.6773,
      "step": 210
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000295408560311284,
      "loss": 0.652,
      "step": 220
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00029501945525291825,
      "loss": 0.662,
      "step": 230
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002946303501945525,
      "loss": 0.6919,
      "step": 240
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00029424124513618673,
      "loss": 0.6828,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00029385214007782097,
      "loss": 0.6734,
      "step": 260
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002934630350194552,
      "loss": 0.6605,
      "step": 270
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00029307392996108945,
      "loss": 0.6779,
      "step": 280
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002926848249027237,
      "loss": 0.6751,
      "step": 290
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00029229571984435793,
      "loss": 0.6514,
      "step": 300
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00029190661478599217,
      "loss": 0.6764,
      "step": 310
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002915175097276264,
      "loss": 0.6946,
      "step": 320
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00029112840466926065,
      "loss": 0.6687,
      "step": 330
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00029073929961089494,
      "loss": 0.6504,
      "step": 340
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002903501945525292,
      "loss": 0.6598,
      "step": 350
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002899610894941634,
      "loss": 0.6719,
      "step": 360
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00028957198443579766,
      "loss": 0.6514,
      "step": 370
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002891828793774319,
      "loss": 0.6696,
      "step": 380
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00028879377431906614,
      "loss": 0.6726,
      "step": 390
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002884046692607004,
      "loss": 0.6505,
      "step": 400
    },
    {
      "epoch": 0.26,
      "eval_loss": 0.6674855351448059,
      "eval_runtime": 303.0692,
      "eval_samples_per_second": 6.599,
      "eval_steps_per_second": 0.825,
      "step": 400
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002880155642023346,
      "loss": 0.6722,
      "step": 410
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00028762645914396886,
      "loss": 0.6618,
      "step": 420
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002872373540856031,
      "loss": 0.6679,
      "step": 430
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00028684824902723734,
      "loss": 0.6371,
      "step": 440
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002864591439688716,
      "loss": 0.6574,
      "step": 450
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002860700389105058,
      "loss": 0.6779,
      "step": 460
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00028568093385214006,
      "loss": 0.674,
      "step": 470
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002852918287937743,
      "loss": 0.6661,
      "step": 480
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00028490272373540853,
      "loss": 0.6515,
      "step": 490
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002845136186770428,
      "loss": 0.6719,
      "step": 500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000284124513618677,
      "loss": 0.6875,
      "step": 510
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00028373540856031125,
      "loss": 0.6976,
      "step": 520
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002833463035019455,
      "loss": 0.6636,
      "step": 530
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028295719844357973,
      "loss": 0.6481,
      "step": 540
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028256809338521397,
      "loss": 0.6504,
      "step": 550
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002821789883268482,
      "loss": 0.6776,
      "step": 560
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00028178988326848245,
      "loss": 0.6906,
      "step": 570
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002814007782101167,
      "loss": 0.6714,
      "step": 580
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00028101167315175093,
      "loss": 0.6495,
      "step": 590
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00028062256809338517,
      "loss": 0.6508,
      "step": 600
    },
    {
      "epoch": 0.38,
      "eval_loss": 0.6634581089019775,
      "eval_runtime": 294.3504,
      "eval_samples_per_second": 6.795,
      "eval_steps_per_second": 0.849,
      "step": 600
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002802334630350194,
      "loss": 0.6613,
      "step": 610
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002798443579766537,
      "loss": 0.6702,
      "step": 620
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00027945525291828794,
      "loss": 0.649,
      "step": 630
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002790661478599222,
      "loss": 0.6718,
      "step": 640
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002786770428015564,
      "loss": 0.6647,
      "step": 650
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00027828793774319066,
      "loss": 0.6441,
      "step": 660
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002778988326848249,
      "loss": 0.6628,
      "step": 670
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00027750972762645914,
      "loss": 0.6358,
      "step": 680
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002771206225680934,
      "loss": 0.6568,
      "step": 690
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002767315175097276,
      "loss": 0.6428,
      "step": 700
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002763424124513618,
      "loss": 0.6644,
      "step": 710
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00027595330739299605,
      "loss": 0.6401,
      "step": 720
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00027556420233463034,
      "loss": 0.6733,
      "step": 730
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002751750972762646,
      "loss": 0.6773,
      "step": 740
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002747859922178988,
      "loss": 0.667,
      "step": 750
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00027439688715953306,
      "loss": 0.6729,
      "step": 760
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002740077821011673,
      "loss": 0.6609,
      "step": 770
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00027361867704280154,
      "loss": 0.6349,
      "step": 780
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002732295719844358,
      "loss": 0.6647,
      "step": 790
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00027284046692607,
      "loss": 0.6557,
      "step": 800
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.6586535573005676,
      "eval_runtime": 307.0004,
      "eval_samples_per_second": 6.515,
      "eval_steps_per_second": 0.814,
      "step": 800
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00027245136186770426,
      "loss": 0.6461,
      "step": 810
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002720622568093385,
      "loss": 0.6451,
      "step": 820
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00027167315175097274,
      "loss": 0.6556,
      "step": 830
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000271284046692607,
      "loss": 0.6176,
      "step": 840
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002708949416342412,
      "loss": 0.6425,
      "step": 850
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00027050583657587545,
      "loss": 0.658,
      "step": 860
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002701167315175097,
      "loss": 0.6498,
      "step": 870
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00026972762645914393,
      "loss": 0.6337,
      "step": 880
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00026933852140077817,
      "loss": 0.6435,
      "step": 890
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002689494163424124,
      "loss": 0.6735,
      "step": 900
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002685603112840467,
      "loss": 0.6674,
      "step": 910
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00026817120622568095,
      "loss": 0.6515,
      "step": 920
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002677821011673152,
      "loss": 0.6725,
      "step": 930
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002673929961089494,
      "loss": 0.6484,
      "step": 940
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002670038910505836,
      "loss": 0.6595,
      "step": 950
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00026661478599221785,
      "loss": 0.6581,
      "step": 960
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002662256809338521,
      "loss": 0.7032,
      "step": 970
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00026583657587548633,
      "loss": 0.6614,
      "step": 980
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00026544747081712057,
      "loss": 0.6715,
      "step": 990
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002650583657587548,
      "loss": 0.6224,
      "step": 1000
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.6567265391349792,
      "eval_runtime": 296.8164,
      "eval_samples_per_second": 6.738,
      "eval_steps_per_second": 0.842,
      "step": 1000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00026466926070038905,
      "loss": 0.6769,
      "step": 1010
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00026428015564202334,
      "loss": 0.6349,
      "step": 1020
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002638910505836576,
      "loss": 0.6293,
      "step": 1030
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002635019455252918,
      "loss": 0.6704,
      "step": 1040
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00026311284046692606,
      "loss": 0.6562,
      "step": 1050
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002627237354085603,
      "loss": 0.6572,
      "step": 1060
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00026233463035019454,
      "loss": 0.6496,
      "step": 1070
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002619455252918288,
      "loss": 0.6933,
      "step": 1080
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000261556420233463,
      "loss": 0.6777,
      "step": 1090
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00026116731517509726,
      "loss": 0.6612,
      "step": 1100
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002607782101167315,
      "loss": 0.6434,
      "step": 1110
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00026038910505836574,
      "loss": 0.6605,
      "step": 1120
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00026,
      "loss": 0.6629,
      "step": 1130
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002596108949416342,
      "loss": 0.6511,
      "step": 1140
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00025922178988326846,
      "loss": 0.6427,
      "step": 1150
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002588326848249027,
      "loss": 0.6788,
      "step": 1160
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00025844357976653694,
      "loss": 0.6766,
      "step": 1170
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002580544747081712,
      "loss": 0.644,
      "step": 1180
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002576653696498054,
      "loss": 0.6465,
      "step": 1190
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025727626459143965,
      "loss": 0.6685,
      "step": 1200
    },
    {
      "epoch": 0.77,
      "eval_loss": 0.6553727984428406,
      "eval_runtime": 303.8445,
      "eval_samples_per_second": 6.582,
      "eval_steps_per_second": 0.823,
      "step": 1200
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002568871595330739,
      "loss": 0.6359,
      "step": 1210
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00025649805447470813,
      "loss": 0.639,
      "step": 1220
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002561089494163424,
      "loss": 0.6284,
      "step": 1230
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002557198443579766,
      "loss": 0.6625,
      "step": 1240
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00025533073929961085,
      "loss": 0.6389,
      "step": 1250
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002549416342412451,
      "loss": 0.6784,
      "step": 1260
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00025455252918287933,
      "loss": 0.6379,
      "step": 1270
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00025416342412451357,
      "loss": 0.6553,
      "step": 1280
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002537743190661478,
      "loss": 0.6721,
      "step": 1290
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002533852140077821,
      "loss": 0.6442,
      "step": 1300
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00025299610894941634,
      "loss": 0.642,
      "step": 1310
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002526070038910506,
      "loss": 0.6109,
      "step": 1320
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002522178988326848,
      "loss": 0.6829,
      "step": 1330
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00025182879377431906,
      "loss": 0.634,
      "step": 1340
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002514396887159533,
      "loss": 0.6483,
      "step": 1350
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00025105058365758754,
      "loss": 0.6571,
      "step": 1360
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002506614785992218,
      "loss": 0.6739,
      "step": 1370
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000250272373540856,
      "loss": 0.6575,
      "step": 1380
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00024988326848249026,
      "loss": 0.6446,
      "step": 1390
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002494941634241245,
      "loss": 0.6264,
      "step": 1400
    },
    {
      "epoch": 0.9,
      "eval_loss": 0.6528891921043396,
      "eval_runtime": 304.6435,
      "eval_samples_per_second": 6.565,
      "eval_steps_per_second": 0.821,
      "step": 1400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00024910505836575874,
      "loss": 0.6295,
      "step": 1410
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000248715953307393,
      "loss": 0.6534,
      "step": 1420
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002483268482490272,
      "loss": 0.6448,
      "step": 1430
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00024793774319066146,
      "loss": 0.6337,
      "step": 1440
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002475486381322957,
      "loss": 0.6344,
      "step": 1450
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00024715953307392994,
      "loss": 0.6451,
      "step": 1460
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002467704280155642,
      "loss": 0.6562,
      "step": 1470
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002463813229571984,
      "loss": 0.6478,
      "step": 1480
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00024599221789883266,
      "loss": 0.6532,
      "step": 1490
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002456031128404669,
      "loss": 0.6384,
      "step": 1500
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00024521400778210114,
      "loss": 0.6422,
      "step": 1510
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002448249027237354,
      "loss": 0.6557,
      "step": 1520
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002444357976653696,
      "loss": 0.6405,
      "step": 1530
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00024404669260700388,
      "loss": 0.6654,
      "step": 1540
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00024365758754863812,
      "loss": 0.6676,
      "step": 1550
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00024326848249027236,
      "loss": 0.6544,
      "step": 1560
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002428793774319066,
      "loss": 0.6426,
      "step": 1570
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00024249027237354084,
      "loss": 0.6309,
      "step": 1580
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00024210116731517508,
      "loss": 0.6543,
      "step": 1590
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00024171206225680932,
      "loss": 0.6244,
      "step": 1600
    },
    {
      "epoch": 1.02,
      "eval_loss": 0.652025043964386,
      "eval_runtime": 302.2996,
      "eval_samples_per_second": 6.616,
      "eval_steps_per_second": 0.827,
      "step": 1600
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00024132295719844356,
      "loss": 0.6328,
      "step": 1610
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002409338521400778,
      "loss": 0.6316,
      "step": 1620
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00024054474708171207,
      "loss": 0.6558,
      "step": 1630
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002401556420233463,
      "loss": 0.6512,
      "step": 1640
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00023976653696498054,
      "loss": 0.6193,
      "step": 1650
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00023937743190661478,
      "loss": 0.6447,
      "step": 1660
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.000238988326848249,
      "loss": 0.6507,
      "step": 1670
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00023859922178988324,
      "loss": 0.6281,
      "step": 1680
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00023821011673151748,
      "loss": 0.6331,
      "step": 1690
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00023782101167315172,
      "loss": 0.6306,
      "step": 1700
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00023743190661478595,
      "loss": 0.6233,
      "step": 1710
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002370428015564202,
      "loss": 0.627,
      "step": 1720
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00023665369649805443,
      "loss": 0.6494,
      "step": 1730
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002362645914396887,
      "loss": 0.6319,
      "step": 1740
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00023587548638132294,
      "loss": 0.6666,
      "step": 1750
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00023548638132295718,
      "loss": 0.6097,
      "step": 1760
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00023509727626459142,
      "loss": 0.6222,
      "step": 1770
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00023470817120622566,
      "loss": 0.6345,
      "step": 1780
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002343190661478599,
      "loss": 0.6506,
      "step": 1790
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00023392996108949414,
      "loss": 0.6451,
      "step": 1800
    },
    {
      "epoch": 1.15,
      "eval_loss": 0.6515942215919495,
      "eval_runtime": 301.7791,
      "eval_samples_per_second": 6.627,
      "eval_steps_per_second": 0.828,
      "step": 1800
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00023354085603112838,
      "loss": 0.664,
      "step": 1810
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00023315175097276262,
      "loss": 0.6299,
      "step": 1820
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00023276264591439688,
      "loss": 0.6286,
      "step": 1830
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00023237354085603112,
      "loss": 0.6216,
      "step": 1840
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00023198443579766536,
      "loss": 0.652,
      "step": 1850
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002315953307392996,
      "loss": 0.6092,
      "step": 1860
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00023120622568093384,
      "loss": 0.6369,
      "step": 1870
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00023081712062256808,
      "loss": 0.6229,
      "step": 1880
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00023042801556420232,
      "loss": 0.6274,
      "step": 1890
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00023003891050583656,
      "loss": 0.6472,
      "step": 1900
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00022964980544747077,
      "loss": 0.6351,
      "step": 1910
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.000229260700389105,
      "loss": 0.6154,
      "step": 1920
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00022887159533073925,
      "loss": 0.6322,
      "step": 1930
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00022848249027237352,
      "loss": 0.6323,
      "step": 1940
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00022809338521400776,
      "loss": 0.6222,
      "step": 1950
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000227704280155642,
      "loss": 0.6119,
      "step": 1960
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00022731517509727624,
      "loss": 0.621,
      "step": 1970
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00022692607003891048,
      "loss": 0.6653,
      "step": 1980
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00022653696498054472,
      "loss": 0.6739,
      "step": 1990
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00022614785992217896,
      "loss": 0.6398,
      "step": 2000
    },
    {
      "epoch": 1.28,
      "eval_loss": 0.6505751013755798,
      "eval_runtime": 333.7471,
      "eval_samples_per_second": 5.993,
      "eval_steps_per_second": 0.749,
      "step": 2000
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002257587548638132,
      "loss": 0.6455,
      "step": 2010
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00022536964980544744,
      "loss": 0.64,
      "step": 2020
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002249805447470817,
      "loss": 0.6313,
      "step": 2030
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00022459143968871594,
      "loss": 0.64,
      "step": 2040
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00022420233463035018,
      "loss": 0.5932,
      "step": 2050
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00022381322957198442,
      "loss": 0.6273,
      "step": 2060
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00022342412451361866,
      "loss": 0.6347,
      "step": 2070
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002230350194552529,
      "loss": 0.623,
      "step": 2080
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00022264591439688714,
      "loss": 0.6247,
      "step": 2090
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00022225680933852138,
      "loss": 0.6411,
      "step": 2100
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00022186770428015565,
      "loss": 0.6342,
      "step": 2110
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002214785992217899,
      "loss": 0.6416,
      "step": 2120
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00022108949416342413,
      "loss": 0.6068,
      "step": 2130
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00022070038910505837,
      "loss": 0.6255,
      "step": 2140
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00022031128404669258,
      "loss": 0.6522,
      "step": 2150
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00021992217898832682,
      "loss": 0.6289,
      "step": 2160
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00021953307392996106,
      "loss": 0.651,
      "step": 2170
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002191439688715953,
      "loss": 0.6257,
      "step": 2180
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00021875486381322954,
      "loss": 0.6186,
      "step": 2190
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00021836575875486378,
      "loss": 0.6141,
      "step": 2200
    },
    {
      "epoch": 1.41,
      "eval_loss": 0.6505178213119507,
      "eval_runtime": 305.7766,
      "eval_samples_per_second": 6.541,
      "eval_steps_per_second": 0.818,
      "step": 2200
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00021797665369649802,
      "loss": 0.6214,
      "step": 2210
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00021758754863813228,
      "loss": 0.618,
      "step": 2220
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00021719844357976652,
      "loss": 0.612,
      "step": 2230
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00021680933852140076,
      "loss": 0.6406,
      "step": 2240
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.000216420233463035,
      "loss": 0.6184,
      "step": 2250
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00021603112840466924,
      "loss": 0.6354,
      "step": 2260
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00021564202334630348,
      "loss": 0.6315,
      "step": 2270
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00021525291828793772,
      "loss": 0.6254,
      "step": 2280
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00021486381322957196,
      "loss": 0.6283,
      "step": 2290
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002144747081712062,
      "loss": 0.6302,
      "step": 2300
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00021408560311284047,
      "loss": 0.6234,
      "step": 2310
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002136964980544747,
      "loss": 0.6592,
      "step": 2320
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00021330739299610895,
      "loss": 0.6247,
      "step": 2330
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00021291828793774318,
      "loss": 0.6383,
      "step": 2340
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00021252918287937742,
      "loss": 0.6451,
      "step": 2350
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00021214007782101166,
      "loss": 0.6311,
      "step": 2360
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002117509727626459,
      "loss": 0.6441,
      "step": 2370
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021136186770428014,
      "loss": 0.6405,
      "step": 2380
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00021097276264591438,
      "loss": 0.6447,
      "step": 2390
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002105836575875486,
      "loss": 0.6311,
      "step": 2400
    },
    {
      "epoch": 1.54,
      "eval_loss": 0.6494212746620178,
      "eval_runtime": 305.7108,
      "eval_samples_per_second": 6.542,
      "eval_steps_per_second": 0.818,
      "step": 2400
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00021019455252918283,
      "loss": 0.6296,
      "step": 2410
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002098054474708171,
      "loss": 0.6444,
      "step": 2420
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00020941634241245134,
      "loss": 0.6366,
      "step": 2430
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00020902723735408558,
      "loss": 0.6433,
      "step": 2440
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00020863813229571982,
      "loss": 0.6302,
      "step": 2450
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00020824902723735406,
      "loss": 0.6134,
      "step": 2460
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002078599221789883,
      "loss": 0.617,
      "step": 2470
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00020747081712062254,
      "loss": 0.6574,
      "step": 2480
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00020708171206225678,
      "loss": 0.6267,
      "step": 2490
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00020669260700389102,
      "loss": 0.6151,
      "step": 2500
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00020630350194552528,
      "loss": 0.66,
      "step": 2510
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00020591439688715952,
      "loss": 0.6372,
      "step": 2520
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00020552529182879376,
      "loss": 0.6184,
      "step": 2530
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.000205136186770428,
      "loss": 0.6115,
      "step": 2540
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00020474708171206224,
      "loss": 0.6616,
      "step": 2550
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00020435797665369648,
      "loss": 0.6367,
      "step": 2560
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00020396887159533072,
      "loss": 0.6464,
      "step": 2570
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00020357976653696496,
      "loss": 0.6304,
      "step": 2580
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002031906614785992,
      "loss": 0.6015,
      "step": 2590
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00020280155642023347,
      "loss": 0.6353,
      "step": 2600
    },
    {
      "epoch": 1.66,
      "eval_loss": 0.6482927203178406,
      "eval_runtime": 309.3391,
      "eval_samples_per_second": 6.465,
      "eval_steps_per_second": 0.808,
      "step": 2600
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002024124513618677,
      "loss": 0.6311,
      "step": 2610
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00020202334630350195,
      "loss": 0.6221,
      "step": 2620
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002016342412451362,
      "loss": 0.6439,
      "step": 2630
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002012451361867704,
      "loss": 0.6284,
      "step": 2640
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00020085603112840464,
      "loss": 0.6402,
      "step": 2650
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00020046692607003888,
      "loss": 0.6373,
      "step": 2660
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00020007782101167312,
      "loss": 0.6205,
      "step": 2670
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00019968871595330736,
      "loss": 0.6343,
      "step": 2680
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001992996108949416,
      "loss": 0.6272,
      "step": 2690
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00019891050583657586,
      "loss": 0.6262,
      "step": 2700
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001985214007782101,
      "loss": 0.6295,
      "step": 2710
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00019813229571984434,
      "loss": 0.6256,
      "step": 2720
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00019774319066147858,
      "loss": 0.6485,
      "step": 2730
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00019735408560311282,
      "loss": 0.6518,
      "step": 2740
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00019696498054474706,
      "loss": 0.6627,
      "step": 2750
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001965758754863813,
      "loss": 0.594,
      "step": 2760
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00019618677042801554,
      "loss": 0.6289,
      "step": 2770
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00019579766536964978,
      "loss": 0.6393,
      "step": 2780
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00019540856031128405,
      "loss": 0.6073,
      "step": 2790
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001950194552529183,
      "loss": 0.6331,
      "step": 2800
    },
    {
      "epoch": 1.79,
      "eval_loss": 0.647841215133667,
      "eval_runtime": 307.5546,
      "eval_samples_per_second": 6.503,
      "eval_steps_per_second": 0.813,
      "step": 2800
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00019463035019455253,
      "loss": 0.6353,
      "step": 2810
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00019424124513618677,
      "loss": 0.6444,
      "step": 2820
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.000193852140077821,
      "loss": 0.6227,
      "step": 2830
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00019346303501945525,
      "loss": 0.6505,
      "step": 2840
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00019307392996108949,
      "loss": 0.6545,
      "step": 2850
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00019268482490272372,
      "loss": 0.6354,
      "step": 2860
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00019229571984435796,
      "loss": 0.5997,
      "step": 2870
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00019190661478599218,
      "loss": 0.6465,
      "step": 2880
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00019151750972762642,
      "loss": 0.6198,
      "step": 2890
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00019112840466926068,
      "loss": 0.6407,
      "step": 2900
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00019073929961089492,
      "loss": 0.6413,
      "step": 2910
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00019035019455252916,
      "loss": 0.6468,
      "step": 2920
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001899610894941634,
      "loss": 0.6133,
      "step": 2930
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00018957198443579764,
      "loss": 0.6055,
      "step": 2940
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00018918287937743188,
      "loss": 0.6155,
      "step": 2950
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00018879377431906612,
      "loss": 0.6253,
      "step": 2960
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00018840466926070036,
      "loss": 0.631,
      "step": 2970
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001880155642023346,
      "loss": 0.6332,
      "step": 2980
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00018762645914396887,
      "loss": 0.6229,
      "step": 2990
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001872373540856031,
      "loss": 0.6291,
      "step": 3000
    },
    {
      "epoch": 1.92,
      "eval_loss": 0.6470396518707275,
      "eval_runtime": 303.5236,
      "eval_samples_per_second": 6.589,
      "eval_steps_per_second": 0.824,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 7810,
  "num_train_epochs": 5,
  "save_steps": 200,
  "total_flos": 9.12950959125037e+17,
  "trial_name": null,
  "trial_params": null
}