{
  "best_metric": 0.007954709231853485,
  "best_model_checkpoint": "autotrain-tlvon-zmjgo/checkpoint-3960",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3960,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047979797979797977,
      "grad_norm": 69.1661148071289,
      "learning_rate": 7.575757575757576e-07,
      "loss": 9.6544,
      "step": 19
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 59.700984954833984,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 8.2669,
      "step": 38
    },
    {
      "epoch": 0.14393939393939395,
      "grad_norm": 22.565589904785156,
      "learning_rate": 2.6262626262626263e-06,
      "loss": 6.1057,
      "step": 57
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 12.696467399597168,
      "learning_rate": 3.5858585858585863e-06,
      "loss": 4.9529,
      "step": 76
    },
    {
      "epoch": 0.2398989898989899,
      "grad_norm": 11.562800407409668,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 4.3771,
      "step": 95
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 7.8888840675354,
      "learning_rate": 5.5050505050505056e-06,
      "loss": 4.027,
      "step": 114
    },
    {
      "epoch": 0.33585858585858586,
      "grad_norm": 11.868915557861328,
      "learning_rate": 6.464646464646465e-06,
      "loss": 3.3608,
      "step": 133
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 6.647916793823242,
      "learning_rate": 7.424242424242425e-06,
      "loss": 3.3761,
      "step": 152
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 5.503500938415527,
      "learning_rate": 8.383838383838384e-06,
      "loss": 3.3234,
      "step": 171
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 7.909439563751221,
      "learning_rate": 9.343434343434344e-06,
      "loss": 2.9671,
      "step": 190
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 6.679018020629883,
      "learning_rate": 1.0303030303030304e-05,
      "loss": 2.9742,
      "step": 209
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 7.1399664878845215,
      "learning_rate": 1.1262626262626264e-05,
      "loss": 2.8917,
      "step": 228
    },
    {
      "epoch": 0.6237373737373737,
      "grad_norm": 6.230110168457031,
      "learning_rate": 1.2222222222222222e-05,
      "loss": 2.9786,
      "step": 247
    },
    {
      "epoch": 0.6717171717171717,
      "grad_norm": 5.975085735321045,
      "learning_rate": 1.318181818181818e-05,
      "loss": 2.5503,
      "step": 266
    },
    {
      "epoch": 0.7196969696969697,
      "grad_norm": 6.412594318389893,
      "learning_rate": 1.4141414141414141e-05,
      "loss": 2.6222,
      "step": 285
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 5.266932487487793,
      "learning_rate": 1.5101010101010103e-05,
      "loss": 2.4747,
      "step": 304
    },
    {
      "epoch": 0.8156565656565656,
      "grad_norm": 6.42549991607666,
      "learning_rate": 1.606060606060606e-05,
      "loss": 2.4522,
      "step": 323
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 5.953466892242432,
      "learning_rate": 1.7020202020202023e-05,
      "loss": 2.4671,
      "step": 342
    },
    {
      "epoch": 0.9116161616161617,
      "grad_norm": 5.912783145904541,
      "learning_rate": 1.797979797979798e-05,
      "loss": 2.1904,
      "step": 361
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 6.379250526428223,
      "learning_rate": 1.893939393939394e-05,
      "loss": 2.2119,
      "step": 380
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 433.9545,
      "eval_loss": 1.9540973901748657,
      "eval_rouge1": 61.8945,
      "eval_rouge2": 45.0914,
      "eval_rougeL": 55.0215,
      "eval_rougeLsum": 60.5887,
      "eval_runtime": 309.9067,
      "eval_samples_per_second": 0.639,
      "eval_steps_per_second": 0.161,
      "step": 396
    },
    {
      "epoch": 1.0075757575757576,
      "grad_norm": 5.456070899963379,
      "learning_rate": 1.98989898989899e-05,
      "loss": 2.1641,
      "step": 399
    },
    {
      "epoch": 1.0555555555555556,
      "grad_norm": 6.323323726654053,
      "learning_rate": 2.085858585858586e-05,
      "loss": 1.8417,
      "step": 418
    },
    {
      "epoch": 1.1035353535353536,
      "grad_norm": 5.177259922027588,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 2.1193,
      "step": 437
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 4.9402689933776855,
      "learning_rate": 2.277777777777778e-05,
      "loss": 2.0342,
      "step": 456
    },
    {
      "epoch": 1.1994949494949494,
      "grad_norm": 5.041110515594482,
      "learning_rate": 2.3737373737373738e-05,
      "loss": 1.9017,
      "step": 475
    },
    {
      "epoch": 1.2474747474747474,
      "grad_norm": 5.8411946296691895,
      "learning_rate": 2.46969696969697e-05,
      "loss": 1.9286,
      "step": 494
    },
    {
      "epoch": 1.2954545454545454,
      "grad_norm": 4.762038707733154,
      "learning_rate": 2.5656565656565658e-05,
      "loss": 1.9661,
      "step": 513
    },
    {
      "epoch": 1.3434343434343434,
      "grad_norm": 5.631948947906494,
      "learning_rate": 2.6616161616161616e-05,
      "loss": 1.6384,
      "step": 532
    },
    {
      "epoch": 1.3914141414141414,
      "grad_norm": 8.481356620788574,
      "learning_rate": 2.7575757575757578e-05,
      "loss": 1.628,
      "step": 551
    },
    {
      "epoch": 1.4393939393939394,
      "grad_norm": 5.706149101257324,
      "learning_rate": 2.8535353535353536e-05,
      "loss": 1.7007,
      "step": 570
    },
    {
      "epoch": 1.4873737373737375,
      "grad_norm": 5.414116382598877,
      "learning_rate": 2.9494949494949498e-05,
      "loss": 1.5938,
      "step": 589
    },
    {
      "epoch": 1.5353535353535355,
      "grad_norm": 4.6547441482543945,
      "learning_rate": 3.0454545454545456e-05,
      "loss": 1.6564,
      "step": 608
    },
    {
      "epoch": 1.5833333333333335,
      "grad_norm": 5.299274444580078,
      "learning_rate": 3.141414141414142e-05,
      "loss": 1.5271,
      "step": 627
    },
    {
      "epoch": 1.6313131313131313,
      "grad_norm": 5.234986305236816,
      "learning_rate": 3.237373737373737e-05,
      "loss": 1.4951,
      "step": 646
    },
    {
      "epoch": 1.6792929292929293,
      "grad_norm": 4.347626209259033,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.2796,
      "step": 665
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 4.5906596183776855,
      "learning_rate": 3.429292929292929e-05,
      "loss": 1.3838,
      "step": 684
    },
    {
      "epoch": 1.7752525252525253,
      "grad_norm": 5.531446933746338,
      "learning_rate": 3.525252525252525e-05,
      "loss": 1.5017,
      "step": 703
    },
    {
      "epoch": 1.823232323232323,
      "grad_norm": 2.8456931114196777,
      "learning_rate": 3.621212121212122e-05,
      "loss": 1.3426,
      "step": 722
    },
    {
      "epoch": 1.871212121212121,
      "grad_norm": 4.428695201873779,
      "learning_rate": 3.7171717171717175e-05,
      "loss": 1.4338,
      "step": 741
    },
    {
      "epoch": 1.9191919191919191,
      "grad_norm": 5.436211585998535,
      "learning_rate": 3.8131313131313133e-05,
      "loss": 1.4004,
      "step": 760
    },
    {
      "epoch": 1.9671717171717171,
      "grad_norm": 5.241793632507324,
      "learning_rate": 3.909090909090909e-05,
      "loss": 1.2884,
      "step": 779
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 452.298,
      "eval_loss": 1.0236088037490845,
      "eval_rouge1": 73.1042,
      "eval_rouge2": 58.8087,
      "eval_rougeL": 67.5013,
      "eval_rougeLsum": 71.9232,
      "eval_runtime": 307.9407,
      "eval_samples_per_second": 0.643,
      "eval_steps_per_second": 0.162,
      "step": 792
    },
    {
      "epoch": 2.015151515151515,
      "grad_norm": 6.048191547393799,
      "learning_rate": 4.005050505050506e-05,
      "loss": 1.1874,
      "step": 798
    },
    {
      "epoch": 2.063131313131313,
      "grad_norm": 4.456089019775391,
      "learning_rate": 4.101010101010101e-05,
      "loss": 1.2008,
      "step": 817
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 4.898771286010742,
      "learning_rate": 4.196969696969697e-05,
      "loss": 1.1192,
      "step": 836
    },
    {
      "epoch": 2.159090909090909,
      "grad_norm": 4.564539909362793,
      "learning_rate": 4.292929292929293e-05,
      "loss": 1.0235,
      "step": 855
    },
    {
      "epoch": 2.207070707070707,
      "grad_norm": 3.8853230476379395,
      "learning_rate": 4.388888888888889e-05,
      "loss": 1.0205,
      "step": 874
    },
    {
      "epoch": 2.255050505050505,
      "grad_norm": 5.523693084716797,
      "learning_rate": 4.484848484848485e-05,
      "loss": 1.1685,
      "step": 893
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 4.635316848754883,
      "learning_rate": 4.5808080808080814e-05,
      "loss": 0.9885,
      "step": 912
    },
    {
      "epoch": 2.351010101010101,
      "grad_norm": 4.56376314163208,
      "learning_rate": 4.676767676767677e-05,
      "loss": 0.9086,
      "step": 931
    },
    {
      "epoch": 2.398989898989899,
      "grad_norm": 4.306213855743408,
      "learning_rate": 4.772727272727273e-05,
      "loss": 0.9958,
      "step": 950
    },
    {
      "epoch": 2.446969696969697,
      "grad_norm": 3.2135376930236816,
      "learning_rate": 4.868686868686869e-05,
      "loss": 0.8709,
      "step": 969
    },
    {
      "epoch": 2.494949494949495,
      "grad_norm": 6.685573101043701,
      "learning_rate": 4.964646464646465e-05,
      "loss": 0.931,
      "step": 988
    },
    {
      "epoch": 2.542929292929293,
      "grad_norm": 3.9406039714813232,
      "learning_rate": 4.993265993265993e-05,
      "loss": 0.8775,
      "step": 1007
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 5.393746852874756,
      "learning_rate": 4.9826038159371496e-05,
      "loss": 0.8857,
      "step": 1026
    },
    {
      "epoch": 2.638888888888889,
      "grad_norm": 5.132722854614258,
      "learning_rate": 4.971941638608306e-05,
      "loss": 0.8471,
      "step": 1045
    },
    {
      "epoch": 2.686868686868687,
      "grad_norm": 4.663482189178467,
      "learning_rate": 4.9612794612794616e-05,
      "loss": 0.7213,
      "step": 1064
    },
    {
      "epoch": 2.734848484848485,
      "grad_norm": 4.11750602722168,
      "learning_rate": 4.950617283950618e-05,
      "loss": 0.8061,
      "step": 1083
    },
    {
      "epoch": 2.782828282828283,
      "grad_norm": 4.041347026824951,
      "learning_rate": 4.9399551066217736e-05,
      "loss": 0.7509,
      "step": 1102
    },
    {
      "epoch": 2.830808080808081,
      "grad_norm": 4.211297988891602,
      "learning_rate": 4.92929292929293e-05,
      "loss": 0.6744,
      "step": 1121
    },
    {
      "epoch": 2.878787878787879,
      "grad_norm": 3.244640827178955,
      "learning_rate": 4.9186307519640855e-05,
      "loss": 0.7003,
      "step": 1140
    },
    {
      "epoch": 2.926767676767677,
      "grad_norm": 5.315489768981934,
      "learning_rate": 4.907968574635242e-05,
      "loss": 0.7851,
      "step": 1159
    },
    {
      "epoch": 2.974747474747475,
      "grad_norm": 4.3310651779174805,
      "learning_rate": 4.8973063973063975e-05,
      "loss": 0.6508,
      "step": 1178
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 446.7525,
      "eval_loss": 0.4764357805252075,
      "eval_rouge1": 81.6804,
      "eval_rouge2": 72.1296,
      "eval_rougeL": 77.6939,
      "eval_rougeLsum": 80.7121,
      "eval_runtime": 314.0103,
      "eval_samples_per_second": 0.631,
      "eval_steps_per_second": 0.159,
      "step": 1188
    },
    {
      "epoch": 3.022727272727273,
      "grad_norm": 4.33705997467041,
      "learning_rate": 4.886644219977554e-05,
      "loss": 0.6099,
      "step": 1197
    },
    {
      "epoch": 3.0707070707070705,
      "grad_norm": 3.1699767112731934,
      "learning_rate": 4.8759820426487094e-05,
      "loss": 0.5929,
      "step": 1216
    },
    {
      "epoch": 3.1186868686868685,
      "grad_norm": 4.443921089172363,
      "learning_rate": 4.865319865319866e-05,
      "loss": 0.5826,
      "step": 1235
    },
    {
      "epoch": 3.1666666666666665,
      "grad_norm": 2.6721291542053223,
      "learning_rate": 4.8546576879910214e-05,
      "loss": 0.5011,
      "step": 1254
    },
    {
      "epoch": 3.2146464646464645,
      "grad_norm": 3.757880687713623,
      "learning_rate": 4.843995510662178e-05,
      "loss": 0.5661,
      "step": 1273
    },
    {
      "epoch": 3.2626262626262625,
      "grad_norm": 3.813979387283325,
      "learning_rate": 4.8333333333333334e-05,
      "loss": 0.5751,
      "step": 1292
    },
    {
      "epoch": 3.3106060606060606,
      "grad_norm": 3.1598410606384277,
      "learning_rate": 4.82267115600449e-05,
      "loss": 0.4737,
      "step": 1311
    },
    {
      "epoch": 3.3585858585858586,
      "grad_norm": 3.785410165786743,
      "learning_rate": 4.812008978675645e-05,
      "loss": 0.517,
      "step": 1330
    },
    {
      "epoch": 3.4065656565656566,
      "grad_norm": 3.080495834350586,
      "learning_rate": 4.8013468013468016e-05,
      "loss": 0.5221,
      "step": 1349
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 3.909271001815796,
      "learning_rate": 4.790684624017957e-05,
      "loss": 0.4863,
      "step": 1368
    },
    {
      "epoch": 3.5025252525252526,
      "grad_norm": 4.788086891174316,
      "learning_rate": 4.7800224466891136e-05,
      "loss": 0.4692,
      "step": 1387
    },
    {
      "epoch": 3.5505050505050506,
      "grad_norm": 3.4247238636016846,
      "learning_rate": 4.769360269360269e-05,
      "loss": 0.4108,
      "step": 1406
    },
    {
      "epoch": 3.5984848484848486,
      "grad_norm": 4.0106587409973145,
      "learning_rate": 4.7586980920314256e-05,
      "loss": 0.4493,
      "step": 1425
    },
    {
      "epoch": 3.6464646464646466,
      "grad_norm": 3.134174108505249,
      "learning_rate": 4.748035914702582e-05,
      "loss": 0.4723,
      "step": 1444
    },
    {
      "epoch": 3.6944444444444446,
      "grad_norm": 3.621345043182373,
      "learning_rate": 4.7373737373737375e-05,
      "loss": 0.4259,
      "step": 1463
    },
    {
      "epoch": 3.742424242424242,
      "grad_norm": 3.506635904312134,
      "learning_rate": 4.726711560044894e-05,
      "loss": 0.4028,
      "step": 1482
    },
    {
      "epoch": 3.7904040404040407,
      "grad_norm": 3.2687313556671143,
      "learning_rate": 4.7160493827160495e-05,
      "loss": 0.3411,
      "step": 1501
    },
    {
      "epoch": 3.8383838383838382,
      "grad_norm": 2.7574453353881836,
      "learning_rate": 4.705387205387206e-05,
      "loss": 0.3987,
      "step": 1520
    },
    {
      "epoch": 3.8863636363636362,
      "grad_norm": 3.152305841445923,
      "learning_rate": 4.6947250280583614e-05,
      "loss": 0.3134,
      "step": 1539
    },
    {
      "epoch": 3.9343434343434343,
      "grad_norm": 3.0011281967163086,
      "learning_rate": 4.684062850729518e-05,
      "loss": 0.4049,
      "step": 1558
    },
    {
      "epoch": 3.9823232323232323,
      "grad_norm": 3.843477487564087,
      "learning_rate": 4.6734006734006734e-05,
      "loss": 0.3601,
      "step": 1577
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 450.1111,
      "eval_loss": 0.200236514210701,
      "eval_rouge1": 88.8764,
      "eval_rouge2": 82.5347,
      "eval_rougeL": 86.0051,
      "eval_rougeLsum": 88.1546,
      "eval_runtime": 311.9983,
      "eval_samples_per_second": 0.635,
      "eval_steps_per_second": 0.16,
      "step": 1584
    },
    {
      "epoch": 4.03030303030303,
      "grad_norm": 3.5295767784118652,
      "learning_rate": 4.66273849607183e-05,
      "loss": 0.2928,
      "step": 1596
    },
    {
      "epoch": 4.078282828282829,
      "grad_norm": 2.5708324909210205,
      "learning_rate": 4.6520763187429854e-05,
      "loss": 0.3198,
      "step": 1615
    },
    {
      "epoch": 4.126262626262626,
      "grad_norm": 3.164304256439209,
      "learning_rate": 4.641414141414142e-05,
      "loss": 0.2895,
      "step": 1634
    },
    {
      "epoch": 4.174242424242424,
      "grad_norm": 2.5397143363952637,
      "learning_rate": 4.630751964085297e-05,
      "loss": 0.277,
      "step": 1653
    },
    {
      "epoch": 4.222222222222222,
      "grad_norm": 2.639850616455078,
      "learning_rate": 4.6200897867564537e-05,
      "loss": 0.2605,
      "step": 1672
    },
    {
      "epoch": 4.27020202020202,
      "grad_norm": 2.7750766277313232,
      "learning_rate": 4.609427609427609e-05,
      "loss": 0.2702,
      "step": 1691
    },
    {
      "epoch": 4.318181818181818,
      "grad_norm": 3.7487545013427734,
      "learning_rate": 4.5987654320987656e-05,
      "loss": 0.2904,
      "step": 1710
    },
    {
      "epoch": 4.366161616161616,
      "grad_norm": 2.997239351272583,
      "learning_rate": 4.588103254769921e-05,
      "loss": 0.2802,
      "step": 1729
    },
    {
      "epoch": 4.414141414141414,
      "grad_norm": 3.394998788833618,
      "learning_rate": 4.5774410774410776e-05,
      "loss": 0.2538,
      "step": 1748
    },
    {
      "epoch": 4.462121212121212,
      "grad_norm": 2.767073392868042,
      "learning_rate": 4.566778900112233e-05,
      "loss": 0.2537,
      "step": 1767
    },
    {
      "epoch": 4.51010101010101,
      "grad_norm": 2.4357552528381348,
      "learning_rate": 4.5561167227833895e-05,
      "loss": 0.2404,
      "step": 1786
    },
    {
      "epoch": 4.558080808080808,
      "grad_norm": 3.32743763923645,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.2273,
      "step": 1805
    },
    {
      "epoch": 4.606060606060606,
      "grad_norm": 4.112804889678955,
      "learning_rate": 4.5347923681257015e-05,
      "loss": 0.2373,
      "step": 1824
    },
    {
      "epoch": 4.654040404040404,
      "grad_norm": 2.256756067276001,
      "learning_rate": 4.524130190796858e-05,
      "loss": 0.2387,
      "step": 1843
    },
    {
      "epoch": 4.702020202020202,
      "grad_norm": 2.8960530757904053,
      "learning_rate": 4.5134680134680135e-05,
      "loss": 0.2507,
      "step": 1862
    },
    {
      "epoch": 4.75,
      "grad_norm": 2.621000289916992,
      "learning_rate": 4.50280583613917e-05,
      "loss": 0.1899,
      "step": 1881
    },
    {
      "epoch": 4.797979797979798,
      "grad_norm": 2.6264095306396484,
      "learning_rate": 4.4921436588103254e-05,
      "loss": 0.1921,
      "step": 1900
    },
    {
      "epoch": 4.845959595959596,
      "grad_norm": 2.770009994506836,
      "learning_rate": 4.481481481481482e-05,
      "loss": 0.1819,
      "step": 1919
    },
    {
      "epoch": 4.893939393939394,
      "grad_norm": 2.9698147773742676,
      "learning_rate": 4.4708193041526374e-05,
      "loss": 0.1877,
      "step": 1938
    },
    {
      "epoch": 4.941919191919192,
      "grad_norm": 2.6372764110565186,
      "learning_rate": 4.460157126823794e-05,
      "loss": 0.1848,
      "step": 1957
    },
    {
      "epoch": 4.98989898989899,
      "grad_norm": 3.164541006088257,
      "learning_rate": 4.4494949494949493e-05,
      "loss": 0.1663,
      "step": 1976
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 456.2828,
      "eval_loss": 0.07814756035804749,
      "eval_rouge1": 94.3866,
      "eval_rouge2": 91.5001,
      "eval_rougeL": 93.1131,
      "eval_rougeLsum": 94.0657,
      "eval_runtime": 313.1525,
      "eval_samples_per_second": 0.632,
      "eval_steps_per_second": 0.16,
      "step": 1980
    },
    {
      "epoch": 5.037878787878788,
      "grad_norm": 1.722895622253418,
      "learning_rate": 4.438832772166106e-05,
      "loss": 0.1759,
      "step": 1995
    },
    {
      "epoch": 5.085858585858586,
      "grad_norm": 5.62981653213501,
      "learning_rate": 4.428170594837261e-05,
      "loss": 0.1636,
      "step": 2014
    },
    {
      "epoch": 5.133838383838384,
      "grad_norm": 2.8217477798461914,
      "learning_rate": 4.4175084175084176e-05,
      "loss": 0.1606,
      "step": 2033
    },
    {
      "epoch": 5.181818181818182,
      "grad_norm": 2.2173731327056885,
      "learning_rate": 4.406846240179573e-05,
      "loss": 0.1439,
      "step": 2052
    },
    {
      "epoch": 5.22979797979798,
      "grad_norm": 2.4998719692230225,
      "learning_rate": 4.3961840628507296e-05,
      "loss": 0.1621,
      "step": 2071
    },
    {
      "epoch": 5.277777777777778,
      "grad_norm": 2.240722894668579,
      "learning_rate": 4.385521885521885e-05,
      "loss": 0.1453,
      "step": 2090
    },
    {
      "epoch": 5.325757575757576,
      "grad_norm": 2.2540104389190674,
      "learning_rate": 4.3748597081930415e-05,
      "loss": 0.1277,
      "step": 2109
    },
    {
      "epoch": 5.373737373737374,
      "grad_norm": 2.4170944690704346,
      "learning_rate": 4.364197530864197e-05,
      "loss": 0.1447,
      "step": 2128
    },
    {
      "epoch": 5.421717171717171,
      "grad_norm": 2.999178409576416,
      "learning_rate": 4.3535353535353535e-05,
      "loss": 0.1436,
      "step": 2147
    },
    {
      "epoch": 5.46969696969697,
      "grad_norm": 1.2877140045166016,
      "learning_rate": 4.34287317620651e-05,
      "loss": 0.1567,
      "step": 2166
    },
    {
      "epoch": 5.517676767676767,
      "grad_norm": 2.6238033771514893,
      "learning_rate": 4.332210998877666e-05,
      "loss": 0.1196,
      "step": 2185
    },
    {
      "epoch": 5.565656565656566,
      "grad_norm": 3.2489261627197266,
      "learning_rate": 4.321548821548822e-05,
      "loss": 0.1403,
      "step": 2204
    },
    {
      "epoch": 5.613636363636363,
      "grad_norm": 2.750288963317871,
      "learning_rate": 4.310886644219978e-05,
      "loss": 0.1422,
      "step": 2223
    },
    {
      "epoch": 5.661616161616162,
      "grad_norm": 2.125354290008545,
      "learning_rate": 4.300224466891134e-05,
      "loss": 0.1209,
      "step": 2242
    },
    {
      "epoch": 5.709595959595959,
      "grad_norm": 2.956669330596924,
      "learning_rate": 4.28956228956229e-05,
      "loss": 0.1261,
      "step": 2261
    },
    {
      "epoch": 5.757575757575758,
      "grad_norm": 2.4984519481658936,
      "learning_rate": 4.278900112233446e-05,
      "loss": 0.1688,
      "step": 2280
    },
    {
      "epoch": 5.805555555555555,
      "grad_norm": 1.8321527242660522,
      "learning_rate": 4.268237934904602e-05,
      "loss": 0.1242,
      "step": 2299
    },
    {
      "epoch": 5.853535353535354,
      "grad_norm": 2.03973650932312,
      "learning_rate": 4.257575757575758e-05,
      "loss": 0.1083,
      "step": 2318
    },
    {
      "epoch": 5.901515151515151,
      "grad_norm": 3.7561116218566895,
      "learning_rate": 4.246913580246914e-05,
      "loss": 0.1553,
      "step": 2337
    },
    {
      "epoch": 5.94949494949495,
      "grad_norm": 4.251192092895508,
      "learning_rate": 4.23625140291807e-05,
      "loss": 0.1083,
      "step": 2356
    },
    {
      "epoch": 5.997474747474747,
      "grad_norm": 1.9990973472595215,
      "learning_rate": 4.225589225589226e-05,
      "loss": 0.1058,
      "step": 2375
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 457.202,
      "eval_loss": 0.04152845963835716,
      "eval_rouge1": 96.8862,
      "eval_rouge2": 95.3951,
      "eval_rougeL": 96.2693,
      "eval_rougeLsum": 96.7116,
      "eval_runtime": 311.7737,
      "eval_samples_per_second": 0.635,
      "eval_steps_per_second": 0.16,
      "step": 2376
    },
    {
      "epoch": 6.045454545454546,
      "grad_norm": 0.8384280204772949,
      "learning_rate": 4.214927048260382e-05,
      "loss": 0.108,
      "step": 2394
    },
    {
      "epoch": 6.093434343434343,
      "grad_norm": 2.411668539047241,
      "learning_rate": 4.204264870931538e-05,
      "loss": 0.1004,
      "step": 2413
    },
    {
      "epoch": 6.141414141414141,
      "grad_norm": 1.1796258687973022,
      "learning_rate": 4.193602693602694e-05,
      "loss": 0.1045,
      "step": 2432
    },
    {
      "epoch": 6.1893939393939394,
      "grad_norm": 1.7287437915802002,
      "learning_rate": 4.18294051627385e-05,
      "loss": 0.0994,
      "step": 2451
    },
    {
      "epoch": 6.237373737373737,
      "grad_norm": 1.7795087099075317,
      "learning_rate": 4.172278338945006e-05,
      "loss": 0.0972,
      "step": 2470
    },
    {
      "epoch": 6.2853535353535355,
      "grad_norm": 1.167188048362732,
      "learning_rate": 4.161616161616162e-05,
      "loss": 0.0983,
      "step": 2489
    },
    {
      "epoch": 6.333333333333333,
      "grad_norm": 2.2238261699676514,
      "learning_rate": 4.150953984287318e-05,
      "loss": 0.0924,
      "step": 2508
    },
    {
      "epoch": 6.3813131313131315,
      "grad_norm": 2.0129451751708984,
      "learning_rate": 4.140291806958474e-05,
      "loss": 0.1008,
      "step": 2527
    },
    {
      "epoch": 6.429292929292929,
      "grad_norm": 2.159029006958008,
      "learning_rate": 4.12962962962963e-05,
      "loss": 0.0844,
      "step": 2546
    },
    {
      "epoch": 6.4772727272727275,
      "grad_norm": 1.6442041397094727,
      "learning_rate": 4.118967452300786e-05,
      "loss": 0.089,
      "step": 2565
    },
    {
      "epoch": 6.525252525252525,
      "grad_norm": 1.7517181634902954,
      "learning_rate": 4.108305274971942e-05,
      "loss": 0.0901,
      "step": 2584
    },
    {
      "epoch": 6.5732323232323235,
      "grad_norm": 1.2451421022415161,
      "learning_rate": 4.097643097643098e-05,
      "loss": 0.0792,
      "step": 2603
    },
    {
      "epoch": 6.621212121212121,
      "grad_norm": 1.7869890928268433,
      "learning_rate": 4.086980920314254e-05,
      "loss": 0.0915,
      "step": 2622
    },
    {
      "epoch": 6.66919191919192,
      "grad_norm": 2.2728748321533203,
      "learning_rate": 4.07631874298541e-05,
      "loss": 0.0844,
      "step": 2641
    },
    {
      "epoch": 6.717171717171717,
      "grad_norm": 1.853063702583313,
      "learning_rate": 4.065656565656566e-05,
      "loss": 0.0857,
      "step": 2660
    },
    {
      "epoch": 6.765151515151516,
      "grad_norm": 1.8357278108596802,
      "learning_rate": 4.0549943883277216e-05,
      "loss": 0.0785,
      "step": 2679
    },
    {
      "epoch": 6.813131313131313,
      "grad_norm": 2.4003820419311523,
      "learning_rate": 4.044332210998878e-05,
      "loss": 0.0928,
      "step": 2698
    },
    {
      "epoch": 6.861111111111111,
      "grad_norm": 3.2185213565826416,
      "learning_rate": 4.0336700336700336e-05,
      "loss": 0.0846,
      "step": 2717
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 2.1494338512420654,
      "learning_rate": 4.02300785634119e-05,
      "loss": 0.0779,
      "step": 2736
    },
    {
      "epoch": 6.957070707070707,
      "grad_norm": 1.4656015634536743,
      "learning_rate": 4.012345679012346e-05,
      "loss": 0.0701,
      "step": 2755
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 457.0758,
      "eval_loss": 0.023281894624233246,
      "eval_rouge1": 98.2551,
      "eval_rouge2": 97.419,
      "eval_rougeL": 97.9827,
      "eval_rougeLsum": 98.1479,
      "eval_runtime": 308.2542,
      "eval_samples_per_second": 0.642,
      "eval_steps_per_second": 0.162,
      "step": 2772
    },
    {
      "epoch": 7.005050505050505,
      "grad_norm": 2.010523796081543,
      "learning_rate": 4.001683501683502e-05,
      "loss": 0.0752,
      "step": 2774
    },
    {
      "epoch": 7.053030303030303,
      "grad_norm": 2.3323521614074707,
      "learning_rate": 3.991021324354658e-05,
      "loss": 0.0637,
      "step": 2793
    },
    {
      "epoch": 7.101010101010101,
      "grad_norm": 1.684549331665039,
      "learning_rate": 3.980359147025814e-05,
      "loss": 0.0711,
      "step": 2812
    },
    {
      "epoch": 7.148989898989899,
      "grad_norm": 1.6758151054382324,
      "learning_rate": 3.96969696969697e-05,
      "loss": 0.0709,
      "step": 2831
    },
    {
      "epoch": 7.196969696969697,
      "grad_norm": 1.9380394220352173,
      "learning_rate": 3.959034792368126e-05,
      "loss": 0.0665,
      "step": 2850
    },
    {
      "epoch": 7.244949494949495,
      "grad_norm": 1.988451361656189,
      "learning_rate": 3.948372615039282e-05,
      "loss": 0.0693,
      "step": 2869
    },
    {
      "epoch": 7.292929292929293,
      "grad_norm": 1.2491166591644287,
      "learning_rate": 3.937710437710438e-05,
      "loss": 0.0721,
      "step": 2888
    },
    {
      "epoch": 7.340909090909091,
      "grad_norm": 1.4535962343215942,
      "learning_rate": 3.927048260381594e-05,
      "loss": 0.0659,
      "step": 2907
    },
    {
      "epoch": 7.388888888888889,
      "grad_norm": 1.9495213031768799,
      "learning_rate": 3.91638608305275e-05,
      "loss": 0.085,
      "step": 2926
    },
    {
      "epoch": 7.436868686868687,
      "grad_norm": 2.000051259994507,
      "learning_rate": 3.905723905723906e-05,
      "loss": 0.0694,
      "step": 2945
    },
    {
      "epoch": 7.484848484848484,
      "grad_norm": 2.803647518157959,
      "learning_rate": 3.895061728395062e-05,
      "loss": 0.0713,
      "step": 2964
    },
    {
      "epoch": 7.532828282828283,
      "grad_norm": 1.7719061374664307,
      "learning_rate": 3.884399551066218e-05,
      "loss": 0.0626,
      "step": 2983
    },
    {
      "epoch": 7.58080808080808,
      "grad_norm": 2.1927216053009033,
      "learning_rate": 3.8737373737373737e-05,
      "loss": 0.0668,
      "step": 3002
    },
    {
      "epoch": 7.628787878787879,
      "grad_norm": 1.1310573816299438,
      "learning_rate": 3.86307519640853e-05,
      "loss": 0.0521,
      "step": 3021
    },
    {
      "epoch": 7.6767676767676765,
      "grad_norm": 1.4547724723815918,
      "learning_rate": 3.8524130190796856e-05,
      "loss": 0.0556,
      "step": 3040
    },
    {
      "epoch": 7.724747474747475,
      "grad_norm": 2.3777520656585693,
      "learning_rate": 3.841750841750842e-05,
      "loss": 0.053,
      "step": 3059
    },
    {
      "epoch": 7.7727272727272725,
      "grad_norm": 2.8660731315612793,
      "learning_rate": 3.8310886644219976e-05,
      "loss": 0.0662,
      "step": 3078
    },
    {
      "epoch": 7.820707070707071,
      "grad_norm": 1.2403335571289062,
      "learning_rate": 3.820426487093154e-05,
      "loss": 0.0513,
      "step": 3097
    },
    {
      "epoch": 7.8686868686868685,
      "grad_norm": 1.2479897737503052,
      "learning_rate": 3.8097643097643095e-05,
      "loss": 0.0529,
      "step": 3116
    },
    {
      "epoch": 7.916666666666667,
      "grad_norm": 0.8943136930465698,
      "learning_rate": 3.799102132435466e-05,
      "loss": 0.0493,
      "step": 3135
    },
    {
      "epoch": 7.9646464646464645,
      "grad_norm": 2.092480421066284,
      "learning_rate": 3.788439955106622e-05,
      "loss": 0.0613,
      "step": 3154
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 456.2626,
      "eval_loss": 0.014666617847979069,
      "eval_rouge1": 98.8857,
      "eval_rouge2": 98.3456,
      "eval_rougeL": 98.7777,
      "eval_rougeLsum": 98.8775,
      "eval_runtime": 309.5854,
      "eval_samples_per_second": 0.64,
      "eval_steps_per_second": 0.162,
      "step": 3168
    },
    {
      "epoch": 8.012626262626263,
      "grad_norm": 0.7548523545265198,
      "learning_rate": 3.777777777777778e-05,
      "loss": 0.0606,
      "step": 3173
    },
    {
      "epoch": 8.06060606060606,
      "grad_norm": 1.4151593446731567,
      "learning_rate": 3.767115600448934e-05,
      "loss": 0.047,
      "step": 3192
    },
    {
      "epoch": 8.108585858585858,
      "grad_norm": 1.26515531539917,
      "learning_rate": 3.75645342312009e-05,
      "loss": 0.0535,
      "step": 3211
    },
    {
      "epoch": 8.156565656565657,
      "grad_norm": 1.318965196609497,
      "learning_rate": 3.745791245791246e-05,
      "loss": 0.0496,
      "step": 3230
    },
    {
      "epoch": 8.204545454545455,
      "grad_norm": 1.5114891529083252,
      "learning_rate": 3.735129068462402e-05,
      "loss": 0.0434,
      "step": 3249
    },
    {
      "epoch": 8.252525252525253,
      "grad_norm": 1.121440052986145,
      "learning_rate": 3.724466891133558e-05,
      "loss": 0.0447,
      "step": 3268
    },
    {
      "epoch": 8.30050505050505,
      "grad_norm": 0.9955199360847473,
      "learning_rate": 3.713804713804714e-05,
      "loss": 0.0478,
      "step": 3287
    },
    {
      "epoch": 8.348484848484848,
      "grad_norm": 2.078119993209839,
      "learning_rate": 3.70314253647587e-05,
      "loss": 0.0494,
      "step": 3306
    },
    {
      "epoch": 8.396464646464647,
      "grad_norm": 1.3387614488601685,
      "learning_rate": 3.692480359147026e-05,
      "loss": 0.0402,
      "step": 3325
    },
    {
      "epoch": 8.444444444444445,
      "grad_norm": 2.1103882789611816,
      "learning_rate": 3.681818181818182e-05,
      "loss": 0.0457,
      "step": 3344
    },
    {
      "epoch": 8.492424242424242,
      "grad_norm": 1.5628422498703003,
      "learning_rate": 3.6711560044893376e-05,
      "loss": 0.0462,
      "step": 3363
    },
    {
      "epoch": 8.54040404040404,
      "grad_norm": 1.7333801984786987,
      "learning_rate": 3.660493827160494e-05,
      "loss": 0.0466,
      "step": 3382
    },
    {
      "epoch": 8.58838383838384,
      "grad_norm": 1.3456194400787354,
      "learning_rate": 3.6498316498316496e-05,
      "loss": 0.0402,
      "step": 3401
    },
    {
      "epoch": 8.636363636363637,
      "grad_norm": 1.2034332752227783,
      "learning_rate": 3.639169472502806e-05,
      "loss": 0.0459,
      "step": 3420
    },
    {
      "epoch": 8.684343434343434,
      "grad_norm": 0.502601683139801,
      "learning_rate": 3.6285072951739616e-05,
      "loss": 0.0465,
      "step": 3439
    },
    {
      "epoch": 8.732323232323232,
      "grad_norm": 1.651060938835144,
      "learning_rate": 3.617845117845118e-05,
      "loss": 0.0401,
      "step": 3458
    },
    {
      "epoch": 8.780303030303031,
      "grad_norm": 1.1892279386520386,
      "learning_rate": 3.6071829405162735e-05,
      "loss": 0.0357,
      "step": 3477
    },
    {
      "epoch": 8.828282828282829,
      "grad_norm": 1.0248866081237793,
      "learning_rate": 3.59652076318743e-05,
      "loss": 0.0368,
      "step": 3496
    },
    {
      "epoch": 8.876262626262626,
      "grad_norm": 1.235990285873413,
      "learning_rate": 3.5858585858585855e-05,
      "loss": 0.0354,
      "step": 3515
    },
    {
      "epoch": 8.924242424242424,
      "grad_norm": 1.156433343887329,
      "learning_rate": 3.575196408529742e-05,
      "loss": 0.0366,
      "step": 3534
    },
    {
      "epoch": 8.972222222222221,
      "grad_norm": 1.7279999256134033,
      "learning_rate": 3.564534231200898e-05,
      "loss": 0.042,
      "step": 3553
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 458.904,
      "eval_loss": 0.010045090690255165,
      "eval_rouge1": 99.2356,
      "eval_rouge2": 98.9142,
      "eval_rougeL": 99.1626,
      "eval_rougeLsum": 99.2057,
      "eval_runtime": 310.3859,
      "eval_samples_per_second": 0.638,
      "eval_steps_per_second": 0.161,
      "step": 3564
    },
    {
      "epoch": 9.02020202020202,
      "grad_norm": 1.298857569694519,
      "learning_rate": 3.553872053872054e-05,
      "loss": 0.0423,
      "step": 3572
    },
    {
      "epoch": 9.068181818181818,
      "grad_norm": 1.124570608139038,
      "learning_rate": 3.54320987654321e-05,
      "loss": 0.0309,
      "step": 3591
    },
    {
      "epoch": 9.116161616161616,
      "grad_norm": 1.5465493202209473,
      "learning_rate": 3.532547699214366e-05,
      "loss": 0.0365,
      "step": 3610
    },
    {
      "epoch": 9.164141414141413,
      "grad_norm": 1.208004117012024,
      "learning_rate": 3.521885521885522e-05,
      "loss": 0.035,
      "step": 3629
    },
    {
      "epoch": 9.212121212121213,
      "grad_norm": 1.7865431308746338,
      "learning_rate": 3.511223344556678e-05,
      "loss": 0.0376,
      "step": 3648
    },
    {
      "epoch": 9.26010101010101,
      "grad_norm": 0.8254820108413696,
      "learning_rate": 3.500561167227834e-05,
      "loss": 0.0327,
      "step": 3667
    },
    {
      "epoch": 9.308080808080808,
      "grad_norm": 1.0625301599502563,
      "learning_rate": 3.48989898989899e-05,
      "loss": 0.0363,
      "step": 3686
    },
    {
      "epoch": 9.356060606060606,
      "grad_norm": 1.4023059606552124,
      "learning_rate": 3.4792368125701466e-05,
      "loss": 0.0386,
      "step": 3705
    },
    {
      "epoch": 9.404040404040405,
      "grad_norm": 1.9438424110412598,
      "learning_rate": 3.468574635241302e-05,
      "loss": 0.0345,
      "step": 3724
    },
    {
      "epoch": 9.452020202020202,
      "grad_norm": 0.7543076872825623,
      "learning_rate": 3.4579124579124586e-05,
      "loss": 0.0369,
      "step": 3743
    },
    {
      "epoch": 9.5,
      "grad_norm": 1.4393041133880615,
      "learning_rate": 3.447250280583614e-05,
      "loss": 0.0327,
      "step": 3762
    },
    {
      "epoch": 9.547979797979798,
      "grad_norm": 0.8074661493301392,
      "learning_rate": 3.4365881032547706e-05,
      "loss": 0.0317,
      "step": 3781
    },
    {
      "epoch": 9.595959595959595,
      "grad_norm": 1.5561342239379883,
      "learning_rate": 3.425925925925926e-05,
      "loss": 0.037,
      "step": 3800
    },
    {
      "epoch": 9.643939393939394,
      "grad_norm": 2.0807337760925293,
      "learning_rate": 3.4152637485970825e-05,
      "loss": 0.0365,
      "step": 3819
    },
    {
      "epoch": 9.691919191919192,
      "grad_norm": 0.9361720681190491,
      "learning_rate": 3.404601571268238e-05,
      "loss": 0.0289,
      "step": 3838
    },
    {
      "epoch": 9.73989898989899,
      "grad_norm": 0.8103030323982239,
      "learning_rate": 3.3939393939393945e-05,
      "loss": 0.0294,
      "step": 3857
    },
    {
      "epoch": 9.787878787878787,
      "grad_norm": 1.4826786518096924,
      "learning_rate": 3.38327721661055e-05,
      "loss": 0.0274,
      "step": 3876
    },
    {
      "epoch": 9.835858585858587,
      "grad_norm": 1.5168986320495605,
      "learning_rate": 3.3726150392817064e-05,
      "loss": 0.0323,
      "step": 3895
    },
    {
      "epoch": 9.883838383838384,
      "grad_norm": 1.7513259649276733,
      "learning_rate": 3.361952861952862e-05,
      "loss": 0.0312,
      "step": 3914
    },
    {
      "epoch": 9.931818181818182,
      "grad_norm": 1.0549064874649048,
      "learning_rate": 3.3512906846240184e-05,
      "loss": 0.0294,
      "step": 3933
    },
    {
      "epoch": 9.97979797979798,
      "grad_norm": 1.206652045249939,
      "learning_rate": 3.340628507295174e-05,
      "loss": 0.0295,
      "step": 3952
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 458.5909,
      "eval_loss": 0.007954709231853485,
      "eval_rouge1": 99.4349,
      "eval_rouge2": 99.1573,
      "eval_rougeL": 99.4066,
      "eval_rougeLsum": 99.4213,
      "eval_runtime": 308.7546,
      "eval_samples_per_second": 0.641,
      "eval_steps_per_second": 0.162,
      "step": 3960
    }
  ],
  "logging_steps": 19,
  "max_steps": 9900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 500,
  "total_flos": 1017429232582656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}