{
  "best_metric": 1.0316544771194458,
  "best_model_checkpoint": "checkpoints/instrucode/text_models/llama-13b/checkpoint-3000",
  "epoch": 0.9599232061435086,
  "eval_steps": 200,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 1.9718,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.399999999999999e-05,
      "loss": 1.9714,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.4e-05,
      "loss": 1.6976,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.4059,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014399999999999998,
      "loss": 1.1741,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017399999999999997,
      "loss": 1.1727,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000204,
      "loss": 1.1187,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000234,
      "loss": 1.1282,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00026399999999999997,
      "loss": 1.1329,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000294,
      "loss": 1.0721,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002998454106280193,
      "loss": 1.118,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00029965217391304344,
      "loss": 1.1217,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002994589371980676,
      "loss": 1.1033,
      "step": 130
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002992657004830917,
      "loss": 1.1104,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002990724637681159,
      "loss": 1.078,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00029887922705314007,
      "loss": 1.0807,
      "step": 160
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002986859903381642,
      "loss": 1.0875,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00029849275362318835,
      "loss": 1.0463,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00029829951690821255,
      "loss": 1.1217,
      "step": 190
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002981062801932367,
      "loss": 1.0452,
      "step": 200
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.0776479244232178,
      "eval_runtime": 197.5388,
      "eval_samples_per_second": 10.125,
      "eval_steps_per_second": 1.266,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029791304347826083,
      "loss": 1.0228,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000297719806763285,
      "loss": 1.092,
      "step": 220
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002975265700483091,
      "loss": 1.104,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002973333333333333,
      "loss": 1.0577,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00029714009661835746,
      "loss": 1.0892,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002969468599033816,
      "loss": 1.0915,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00029675362318840574,
      "loss": 1.0616,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002965603864734299,
      "loss": 1.071,
      "step": 280
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002963671497584541,
      "loss": 1.08,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002961739130434782,
      "loss": 1.0947,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00029598067632850237,
      "loss": 1.0547,
      "step": 310
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002957874396135265,
      "loss": 1.0723,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002955942028985507,
      "loss": 1.0367,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00029540096618357485,
      "loss": 1.0349,
      "step": 340
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000295207729468599,
      "loss": 1.0507,
      "step": 350
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00029501449275362313,
      "loss": 1.0568,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002948212560386473,
      "loss": 1.0861,
      "step": 370
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002946280193236715,
      "loss": 1.0287,
      "step": 380
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002944347826086956,
      "loss": 1.1086,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00029424154589371976,
      "loss": 1.0916,
      "step": 400
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0622169971466064,
      "eval_runtime": 197.2041,
      "eval_samples_per_second": 10.142,
      "eval_steps_per_second": 1.268,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002940483091787439,
      "loss": 1.075,
      "step": 410
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002938550724637681,
      "loss": 1.0899,
      "step": 420
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00029366183574879224,
      "loss": 1.0565,
      "step": 430
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002934685990338164,
      "loss": 1.0414,
      "step": 440
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002932753623188405,
      "loss": 1.1033,
      "step": 450
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00029308212560386467,
      "loss": 1.0518,
      "step": 460
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00029288888888888886,
      "loss": 1.1324,
      "step": 470
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000292695652173913,
      "loss": 1.0275,
      "step": 480
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00029250241545893715,
      "loss": 1.029,
      "step": 490
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002923091787439613,
      "loss": 1.0648,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002921159420289855,
      "loss": 1.0746,
      "step": 510
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00029192270531400963,
      "loss": 1.0845,
      "step": 520
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002917294685990338,
      "loss": 1.0186,
      "step": 530
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002915362318840579,
      "loss": 1.0984,
      "step": 540
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002913429951690821,
      "loss": 1.0706,
      "step": 550
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00029114975845410626,
      "loss": 1.0184,
      "step": 560
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002909565217391304,
      "loss": 1.0686,
      "step": 570
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00029076328502415454,
      "loss": 1.0391,
      "step": 580
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002905700483091787,
      "loss": 1.0616,
      "step": 590
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002903768115942029,
      "loss": 1.0565,
      "step": 600
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.0566095113754272,
      "eval_runtime": 196.6646,
      "eval_samples_per_second": 10.17,
      "eval_steps_per_second": 1.271,
      "step": 600
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000290183574879227,
      "loss": 1.0609,
      "step": 610
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00028999033816425117,
      "loss": 1.0633,
      "step": 620
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002897971014492753,
      "loss": 1.0049,
      "step": 630
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002896038647342995,
      "loss": 0.9926,
      "step": 640
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00028941062801932365,
      "loss": 1.0949,
      "step": 650
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002892173913043478,
      "loss": 1.0686,
      "step": 660
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00028902415458937193,
      "loss": 1.0152,
      "step": 670
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002888309178743961,
      "loss": 1.0462,
      "step": 680
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00028863768115942027,
      "loss": 1.0438,
      "step": 690
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002884444444444444,
      "loss": 1.0124,
      "step": 700
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00028825120772946856,
      "loss": 0.9959,
      "step": 710
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002880579710144927,
      "loss": 1.0467,
      "step": 720
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002878647342995169,
      "loss": 1.0502,
      "step": 730
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00028767149758454104,
      "loss": 1.0763,
      "step": 740
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002874782608695652,
      "loss": 1.0821,
      "step": 750
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002872850241545893,
      "loss": 1.0667,
      "step": 760
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00028709178743961347,
      "loss": 1.0604,
      "step": 770
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00028689855072463766,
      "loss": 1.0555,
      "step": 780
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002867053140096618,
      "loss": 1.0861,
      "step": 790
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00028651207729468595,
      "loss": 1.0458,
      "step": 800
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.0510022640228271,
      "eval_runtime": 196.1318,
      "eval_samples_per_second": 10.197,
      "eval_steps_per_second": 1.275,
      "step": 800
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002863188405797101,
      "loss": 1.0542,
      "step": 810
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002861256038647343,
      "loss": 1.0783,
      "step": 820
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00028593236714975843,
      "loss": 1.0668,
      "step": 830
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00028573913043478257,
      "loss": 1.0369,
      "step": 840
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002855458937198067,
      "loss": 1.0321,
      "step": 850
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002853526570048309,
      "loss": 1.0515,
      "step": 860
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00028515942028985505,
      "loss": 1.0129,
      "step": 870
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002849661835748792,
      "loss": 1.0042,
      "step": 880
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00028477294685990334,
      "loss": 1.0086,
      "step": 890
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002845797101449275,
      "loss": 1.0555,
      "step": 900
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002843864734299517,
      "loss": 0.9976,
      "step": 910
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002841932367149758,
      "loss": 1.0679,
      "step": 920
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00028399999999999996,
      "loss": 1.0039,
      "step": 930
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002838067632850241,
      "loss": 1.0254,
      "step": 940
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002836135265700483,
      "loss": 1.0109,
      "step": 950
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00028342028985507245,
      "loss": 1.0158,
      "step": 960
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002832270531400966,
      "loss": 1.0165,
      "step": 970
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00028303381642512073,
      "loss": 1.031,
      "step": 980
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002828405797101449,
      "loss": 1.0534,
      "step": 990
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028264734299516907,
      "loss": 1.066,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "eval_loss": 1.047478199005127,
      "eval_runtime": 196.1193,
      "eval_samples_per_second": 10.198,
      "eval_steps_per_second": 1.275,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002824541062801932,
      "loss": 1.0527,
      "step": 1010
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00028226086956521736,
      "loss": 1.0677,
      "step": 1020
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002820676328502415,
      "loss": 1.0409,
      "step": 1030
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002818743961352657,
      "loss": 1.0414,
      "step": 1040
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00028168115942028984,
      "loss": 1.0466,
      "step": 1050
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000281487922705314,
      "loss": 1.0357,
      "step": 1060
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002812946859903381,
      "loss": 1.0418,
      "step": 1070
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028110144927536227,
      "loss": 1.0796,
      "step": 1080
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028090821256038646,
      "loss": 1.0579,
      "step": 1090
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002807149758454106,
      "loss": 1.0631,
      "step": 1100
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00028052173913043475,
      "loss": 1.0221,
      "step": 1110
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002803285024154589,
      "loss": 1.049,
      "step": 1120
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002801352657004831,
      "loss": 1.0192,
      "step": 1130
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00027994202898550723,
      "loss": 0.9978,
      "step": 1140
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00027974879227053137,
      "loss": 1.0044,
      "step": 1150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002795555555555555,
      "loss": 1.0802,
      "step": 1160
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002793623188405797,
      "loss": 1.1231,
      "step": 1170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00027916908212560385,
      "loss": 1.0323,
      "step": 1180
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000278975845410628,
      "loss": 1.0908,
      "step": 1190
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00027878260869565214,
      "loss": 1.0456,
      "step": 1200
    },
    {
      "epoch": 0.38,
      "eval_loss": 1.0448572635650635,
      "eval_runtime": 197.1129,
      "eval_samples_per_second": 10.146,
      "eval_steps_per_second": 1.268,
      "step": 1200
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002785893719806763,
      "loss": 1.0119,
      "step": 1210
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002783961352657005,
      "loss": 1.0101,
      "step": 1220
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002782028985507246,
      "loss": 1.0481,
      "step": 1230
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00027800966183574876,
      "loss": 1.0478,
      "step": 1240
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002778164251207729,
      "loss": 1.0388,
      "step": 1250
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002776231884057971,
      "loss": 1.0566,
      "step": 1260
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00027742995169082124,
      "loss": 1.084,
      "step": 1270
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002772367149758454,
      "loss": 1.0515,
      "step": 1280
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00027704347826086953,
      "loss": 1.053,
      "step": 1290
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00027685024154589367,
      "loss": 1.0276,
      "step": 1300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00027665700483091787,
      "loss": 1.0394,
      "step": 1310
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000276463768115942,
      "loss": 0.9991,
      "step": 1320
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00027627053140096615,
      "loss": 1.0272,
      "step": 1330
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002760772946859903,
      "loss": 1.0684,
      "step": 1340
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002758840579710145,
      "loss": 1.0865,
      "step": 1350
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00027569082125603864,
      "loss": 1.0375,
      "step": 1360
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002754975845410628,
      "loss": 1.0922,
      "step": 1370
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002753043478260869,
      "loss": 1.0611,
      "step": 1380
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00027511111111111106,
      "loss": 0.9878,
      "step": 1390
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00027491787439613526,
      "loss": 1.0658,
      "step": 1400
    },
    {
      "epoch": 0.45,
      "eval_loss": 1.0436240434646606,
      "eval_runtime": 197.0464,
      "eval_samples_per_second": 10.15,
      "eval_steps_per_second": 1.269,
      "step": 1400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002747246376811594,
      "loss": 1.0201,
      "step": 1410
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00027453140096618355,
      "loss": 1.0537,
      "step": 1420
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002743381642512077,
      "loss": 1.051,
      "step": 1430
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002741449275362319,
      "loss": 1.0028,
      "step": 1440
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00027395169082125603,
      "loss": 1.0521,
      "step": 1450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00027375845410628017,
      "loss": 1.0732,
      "step": 1460
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002735652173913043,
      "loss": 1.0427,
      "step": 1470
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002733719806763285,
      "loss": 1.0333,
      "step": 1480
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00027317874396135265,
      "loss": 1.0084,
      "step": 1490
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002729855072463768,
      "loss": 1.0555,
      "step": 1500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00027279227053140094,
      "loss": 1.0419,
      "step": 1510
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002725990338164251,
      "loss": 1.0846,
      "step": 1520
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002724057971014493,
      "loss": 1.0375,
      "step": 1530
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002722125603864734,
      "loss": 1.0593,
      "step": 1540
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00027201932367149756,
      "loss": 1.017,
      "step": 1550
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002718260869565217,
      "loss": 1.0887,
      "step": 1560
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002716328502415459,
      "loss": 1.0333,
      "step": 1570
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00027143961352657004,
      "loss": 1.0439,
      "step": 1580
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002712463768115942,
      "loss": 1.0221,
      "step": 1590
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00027105314009661833,
      "loss": 1.063,
      "step": 1600
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.042041301727295,
      "eval_runtime": 196.9233,
      "eval_samples_per_second": 10.156,
      "eval_steps_per_second": 1.27,
      "step": 1600
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00027085990338164247,
      "loss": 1.0347,
      "step": 1610
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00027066666666666667,
      "loss": 1.027,
      "step": 1620
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002704734299516908,
      "loss": 0.9961,
      "step": 1630
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00027028019323671495,
      "loss": 0.9966,
      "step": 1640
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002700869565217391,
      "loss": 1.0474,
      "step": 1650
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002698937198067633,
      "loss": 1.017,
      "step": 1660
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00026970048309178744,
      "loss": 1.0663,
      "step": 1670
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002695072463768116,
      "loss": 1.0505,
      "step": 1680
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002693140096618357,
      "loss": 1.0954,
      "step": 1690
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00026912077294685986,
      "loss": 1.0136,
      "step": 1700
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00026892753623188406,
      "loss": 1.0749,
      "step": 1710
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002687342995169082,
      "loss": 0.9969,
      "step": 1720
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00026854106280193234,
      "loss": 1.0681,
      "step": 1730
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002683478260869565,
      "loss": 1.0237,
      "step": 1740
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002681545893719807,
      "loss": 1.0473,
      "step": 1750
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002679613526570048,
      "loss": 1.0249,
      "step": 1760
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00026776811594202897,
      "loss": 0.999,
      "step": 1770
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002675748792270531,
      "loss": 1.0299,
      "step": 1780
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002673816425120773,
      "loss": 1.0885,
      "step": 1790
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00026718840579710145,
      "loss": 1.0552,
      "step": 1800
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.0400397777557373,
      "eval_runtime": 196.3928,
      "eval_samples_per_second": 10.184,
      "eval_steps_per_second": 1.273,
      "step": 1800
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002669951690821256,
      "loss": 1.0717,
      "step": 1810
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00026680193236714974,
      "loss": 1.0412,
      "step": 1820
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002666086956521739,
      "loss": 1.0221,
      "step": 1830
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002664154589371981,
      "loss": 1.0729,
      "step": 1840
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002662222222222222,
      "loss": 1.0284,
      "step": 1850
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00026602898550724636,
      "loss": 1.0319,
      "step": 1860
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002658357487922705,
      "loss": 1.0305,
      "step": 1870
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002656425120772947,
      "loss": 1.0398,
      "step": 1880
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00026544927536231884,
      "loss": 1.0427,
      "step": 1890
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000265256038647343,
      "loss": 0.9895,
      "step": 1900
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00026506280193236713,
      "loss": 1.0631,
      "step": 1910
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00026486956521739127,
      "loss": 1.0165,
      "step": 1920
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00026467632850241547,
      "loss": 1.0257,
      "step": 1930
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002644830917874396,
      "loss": 1.0475,
      "step": 1940
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00026428985507246375,
      "loss": 1.0641,
      "step": 1950
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002640966183574879,
      "loss": 1.014,
      "step": 1960
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002639033816425121,
      "loss": 1.021,
      "step": 1970
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00026371014492753623,
      "loss": 1.0223,
      "step": 1980
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002635169082125604,
      "loss": 1.0313,
      "step": 1990
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002633236714975845,
      "loss": 1.069,
      "step": 2000
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.037448525428772,
      "eval_runtime": 196.1715,
      "eval_samples_per_second": 10.195,
      "eval_steps_per_second": 1.274,
      "step": 2000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00026313043478260866,
      "loss": 1.0353,
      "step": 2010
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00026293719806763286,
      "loss": 1.0634,
      "step": 2020
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000262743961352657,
      "loss": 1.0551,
      "step": 2030
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00026255072463768114,
      "loss": 1.0555,
      "step": 2040
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002623574879227053,
      "loss": 1.019,
      "step": 2050
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002621642512077295,
      "loss": 1.0524,
      "step": 2060
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002619710144927536,
      "loss": 1.0285,
      "step": 2070
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00026177777777777777,
      "loss": 1.0271,
      "step": 2080
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002615845410628019,
      "loss": 1.0253,
      "step": 2090
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002613913043478261,
      "loss": 1.0134,
      "step": 2100
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00026119806763285025,
      "loss": 1.0424,
      "step": 2110
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002610048309178744,
      "loss": 1.0769,
      "step": 2120
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00026081159420289854,
      "loss": 1.0464,
      "step": 2130
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002606183574879227,
      "loss": 1.0213,
      "step": 2140
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002604251207729469,
      "loss": 1.0178,
      "step": 2150
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000260231884057971,
      "loss": 1.0113,
      "step": 2160
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00026003864734299516,
      "loss": 1.0261,
      "step": 2170
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002598454106280193,
      "loss": 1.0522,
      "step": 2180
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00025965217391304344,
      "loss": 1.0553,
      "step": 2190
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00025945893719806764,
      "loss": 1.036,
      "step": 2200
    },
    {
      "epoch": 0.7,
      "eval_loss": 1.0350252389907837,
      "eval_runtime": 195.1168,
      "eval_samples_per_second": 10.25,
      "eval_steps_per_second": 1.281,
      "step": 2200
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002592657004830918,
      "loss": 1.0341,
      "step": 2210
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002590724637681159,
      "loss": 1.0552,
      "step": 2220
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00025887922705314007,
      "loss": 0.9925,
      "step": 2230
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00025868599033816427,
      "loss": 1.0427,
      "step": 2240
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002584927536231884,
      "loss": 1.0169,
      "step": 2250
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00025829951690821255,
      "loss": 1.028,
      "step": 2260
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002581062801932367,
      "loss": 1.0556,
      "step": 2270
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00025791304347826084,
      "loss": 1.0242,
      "step": 2280
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00025771980676328503,
      "loss": 1.0307,
      "step": 2290
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002575265700483092,
      "loss": 1.0083,
      "step": 2300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002573333333333333,
      "loss": 1.0146,
      "step": 2310
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00025714009661835746,
      "loss": 0.993,
      "step": 2320
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002569468599033816,
      "loss": 1.0726,
      "step": 2330
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002567536231884058,
      "loss": 1.028,
      "step": 2340
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00025656038647342994,
      "loss": 1.031,
      "step": 2350
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002563671497584541,
      "loss": 1.0175,
      "step": 2360
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00025617391304347823,
      "loss": 1.0618,
      "step": 2370
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002559806763285024,
      "loss": 1.0442,
      "step": 2380
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00025578743961352657,
      "loss": 1.0507,
      "step": 2390
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002555942028985507,
      "loss": 1.0347,
      "step": 2400
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.0352022647857666,
      "eval_runtime": 194.821,
      "eval_samples_per_second": 10.266,
      "eval_steps_per_second": 1.283,
      "step": 2400
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025540096618357485,
      "loss": 1.0786,
      "step": 2410
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000255207729468599,
      "loss": 1.0542,
      "step": 2420
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002550144927536232,
      "loss": 1.0799,
      "step": 2430
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00025482125603864733,
      "loss": 1.0518,
      "step": 2440
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002546280193236715,
      "loss": 1.005,
      "step": 2450
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002544347826086956,
      "loss": 1.0239,
      "step": 2460
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002542415458937198,
      "loss": 1.0243,
      "step": 2470
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00025404830917874396,
      "loss": 1.0144,
      "step": 2480
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002538550724637681,
      "loss": 0.9995,
      "step": 2490
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00025366183574879224,
      "loss": 1.0222,
      "step": 2500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002534685990338164,
      "loss": 1.0381,
      "step": 2510
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002532753623188406,
      "loss": 1.0309,
      "step": 2520
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002530821256038647,
      "loss": 1.0176,
      "step": 2530
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00025288888888888887,
      "loss": 1.0085,
      "step": 2540
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000252695652173913,
      "loss": 1.049,
      "step": 2550
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00025250241545893715,
      "loss": 1.0146,
      "step": 2560
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00025230917874396135,
      "loss": 1.0584,
      "step": 2570
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002521159420289855,
      "loss": 1.0562,
      "step": 2580
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00025192270531400963,
      "loss": 1.0391,
      "step": 2590
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002517294685990338,
      "loss": 1.0388,
      "step": 2600
    },
    {
      "epoch": 0.83,
      "eval_loss": 1.0332427024841309,
      "eval_runtime": 194.4995,
      "eval_samples_per_second": 10.283,
      "eval_steps_per_second": 1.285,
      "step": 2600
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000251536231884058,
      "loss": 1.0589,
      "step": 2610
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002513429951690821,
      "loss": 1.0123,
      "step": 2620
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00025114975845410626,
      "loss": 0.9994,
      "step": 2630
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002509565217391304,
      "loss": 1.0468,
      "step": 2640
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00025076328502415454,
      "loss": 1.0455,
      "step": 2650
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00025057004830917874,
      "loss": 1.0127,
      "step": 2660
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002503768115942029,
      "loss": 1.0031,
      "step": 2670
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000250183574879227,
      "loss": 1.0568,
      "step": 2680
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024999033816425117,
      "loss": 1.0687,
      "step": 2690
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024979710144927537,
      "loss": 1.0378,
      "step": 2700
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002496038647342995,
      "loss": 1.0761,
      "step": 2710
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00024941062801932365,
      "loss": 0.9987,
      "step": 2720
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002492173913043478,
      "loss": 1.0179,
      "step": 2730
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00024902415458937194,
      "loss": 1.0491,
      "step": 2740
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00024883091787439613,
      "loss": 1.0199,
      "step": 2750
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002486376811594203,
      "loss": 1.062,
      "step": 2760
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002484444444444444,
      "loss": 1.0389,
      "step": 2770
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00024825120772946856,
      "loss": 1.027,
      "step": 2780
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002480579710144927,
      "loss": 1.0093,
      "step": 2790
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002478647342995169,
      "loss": 1.0448,
      "step": 2800
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.032317876815796,
      "eval_runtime": 196.407,
      "eval_samples_per_second": 10.183,
      "eval_steps_per_second": 1.273,
      "step": 2800
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00024767149758454104,
      "loss": 1.0627,
      "step": 2810
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002474782608695652,
      "loss": 1.0202,
      "step": 2820
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00024728502415458933,
      "loss": 1.0905,
      "step": 2830
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002470917874396135,
      "loss": 1.0552,
      "step": 2840
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00024689855072463767,
      "loss": 1.0605,
      "step": 2850
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002467053140096618,
      "loss": 1.0194,
      "step": 2860
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00024651207729468595,
      "loss": 1.077,
      "step": 2870
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002463188405797101,
      "loss": 1.0845,
      "step": 2880
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002461256038647343,
      "loss": 1.0225,
      "step": 2890
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00024593236714975843,
      "loss": 1.0217,
      "step": 2900
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002457391304347826,
      "loss": 1.0415,
      "step": 2910
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002455458937198067,
      "loss": 1.0581,
      "step": 2920
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00024535265700483086,
      "loss": 1.0459,
      "step": 2930
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00024515942028985506,
      "loss": 1.0505,
      "step": 2940
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002449661835748792,
      "loss": 1.0562,
      "step": 2950
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00024477294685990334,
      "loss": 0.9631,
      "step": 2960
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002445797101449275,
      "loss": 1.0287,
      "step": 2970
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002443864734299517,
      "loss": 1.0227,
      "step": 2980
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002441932367149758,
      "loss": 1.03,
      "step": 2990
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000244,
      "loss": 1.0795,
      "step": 3000
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.0316544771194458,
      "eval_runtime": 197.1671,
      "eval_samples_per_second": 10.144,
      "eval_steps_per_second": 1.268,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 15625,
  "num_train_epochs": 5,
  "save_steps": 200,
  "total_flos": 6.448770827226317e+17,
  "trial_name": null,
  "trial_params": null
}