{
  "best_metric": 31.7626,
  "best_model_checkpoint": "/content/drive/Shareddrives/UCM_SHARED/TFM_ESG/Ejemplo Oficial de T5-Summarization de HF/t5-small_adafactor/checkpoint-8100",
  "epoch": 0.9880028228652082,
  "global_step": 8400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0009823570924488356,
      "loss": 2.9361,
      "step": 150
    },
    {
      "epoch": 0.02,
      "eval_gen_len": 18.8845,
      "eval_loss": 2.6215693950653076,
      "eval_rouge1": 26.8542,
      "eval_rouge2": 6.8667,
      "eval_rougeL": 21.1484,
      "eval_rougeLsum": 21.1563,
      "eval_runtime": 342.0879,
      "eval_samples_per_second": 33.126,
      "eval_steps_per_second": 1.383,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009648318042813455,
      "loss": 2.8543,
      "step": 300
    },
    {
      "epoch": 0.04,
      "eval_gen_len": 18.8097,
      "eval_loss": 2.5835769176483154,
      "eval_rouge1": 27.2234,
      "eval_rouge2": 7.1753,
      "eval_rougeL": 21.5276,
      "eval_rougeLsum": 21.5308,
      "eval_runtime": 342.5643,
      "eval_samples_per_second": 33.08,
      "eval_steps_per_second": 1.381,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009471888967301812,
      "loss": 2.814,
      "step": 450
    },
    {
      "epoch": 0.05,
      "eval_gen_len": 18.8294,
      "eval_loss": 2.564615488052368,
      "eval_rouge1": 28.1695,
      "eval_rouge2": 7.7873,
      "eval_rougeL": 22.2229,
      "eval_rougeLsum": 22.2251,
      "eval_runtime": 341.6846,
      "eval_samples_per_second": 33.165,
      "eval_steps_per_second": 1.384,
      "step": 450
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009295459891790166,
      "loss": 2.7861,
      "step": 600
    },
    {
      "epoch": 0.07,
      "eval_gen_len": 18.7867,
      "eval_loss": 2.5409207344055176,
      "eval_rouge1": 28.5349,
      "eval_rouge2": 7.9732,
      "eval_rougeL": 22.6959,
      "eval_rougeLsum": 22.7078,
      "eval_runtime": 341.6917,
      "eval_samples_per_second": 33.164,
      "eval_steps_per_second": 1.384,
      "step": 600
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009119030816278523,
      "loss": 2.76,
      "step": 750
    },
    {
      "epoch": 0.09,
      "eval_gen_len": 18.7526,
      "eval_loss": 2.5160539150238037,
      "eval_rouge1": 28.5629,
      "eval_rouge2": 7.9485,
      "eval_rougeL": 22.6545,
      "eval_rougeLsum": 22.6617,
      "eval_runtime": 341.8755,
      "eval_samples_per_second": 33.147,
      "eval_steps_per_second": 1.384,
      "step": 750
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0008942601740766878,
      "loss": 2.7545,
      "step": 900
    },
    {
      "epoch": 0.11,
      "eval_gen_len": 18.7481,
      "eval_loss": 2.5028903484344482,
      "eval_rouge1": 29.1851,
      "eval_rouge2": 8.3586,
      "eval_rougeL": 23.1781,
      "eval_rougeLsum": 23.1815,
      "eval_runtime": 341.7767,
      "eval_samples_per_second": 33.156,
      "eval_steps_per_second": 1.384,
      "step": 900
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0008767348859091978,
      "loss": 2.7294,
      "step": 1050
    },
    {
      "epoch": 0.12,
      "eval_gen_len": 18.6948,
      "eval_loss": 2.4874510765075684,
      "eval_rouge1": 28.7611,
      "eval_rouge2": 8.0309,
      "eval_rougeL": 22.8289,
      "eval_rougeLsum": 22.8364,
      "eval_runtime": 341.7005,
      "eval_samples_per_second": 33.164,
      "eval_steps_per_second": 1.384,
      "step": 1050
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0008590919783580335,
      "loss": 2.7005,
      "step": 1200
    },
    {
      "epoch": 0.14,
      "eval_gen_len": 18.7843,
      "eval_loss": 2.4769885540008545,
      "eval_rouge1": 29.1072,
      "eval_rouge2": 8.2713,
      "eval_rougeL": 23.0568,
      "eval_rougeLsum": 23.0602,
      "eval_runtime": 341.9693,
      "eval_samples_per_second": 33.137,
      "eval_steps_per_second": 1.383,
      "step": 1200
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0008414490708068689,
      "loss": 2.7057,
      "step": 1350
    },
    {
      "epoch": 0.16,
      "eval_gen_len": 18.6973,
      "eval_loss": 2.46754789352417,
      "eval_rouge1": 29.0607,
      "eval_rouge2": 8.4308,
      "eval_rougeL": 23.1094,
      "eval_rougeLsum": 23.1125,
      "eval_runtime": 341.5228,
      "eval_samples_per_second": 33.181,
      "eval_steps_per_second": 1.385,
      "step": 1350
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0008238061632557046,
      "loss": 2.6779,
      "step": 1500
    },
    {
      "epoch": 0.18,
      "eval_gen_len": 18.7927,
      "eval_loss": 2.4461910724639893,
      "eval_rouge1": 29.4815,
      "eval_rouge2": 8.6203,
      "eval_rougeL": 23.3742,
      "eval_rougeLsum": 23.3745,
      "eval_runtime": 341.6546,
      "eval_samples_per_second": 33.168,
      "eval_steps_per_second": 1.384,
      "step": 1500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00080616325570454,
      "loss": 2.6944,
      "step": 1650
    },
    {
      "epoch": 0.19,
      "eval_gen_len": 18.8219,
      "eval_loss": 2.4397881031036377,
      "eval_rouge1": 29.3817,
      "eval_rouge2": 8.5247,
      "eval_rougeL": 23.3088,
      "eval_rougeLsum": 23.3137,
      "eval_runtime": 341.8781,
      "eval_samples_per_second": 33.146,
      "eval_steps_per_second": 1.384,
      "step": 1650
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0007885203481533757,
      "loss": 2.6589,
      "step": 1800
    },
    {
      "epoch": 0.21,
      "eval_gen_len": 18.7917,
      "eval_loss": 2.429356813430786,
      "eval_rouge1": 29.1914,
      "eval_rouge2": 8.5565,
      "eval_rougeL": 23.2017,
      "eval_rougeLsum": 23.2039,
      "eval_runtime": 341.5952,
      "eval_samples_per_second": 33.174,
      "eval_steps_per_second": 1.385,
      "step": 1800
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0007708774406022112,
      "loss": 2.6473,
      "step": 1950
    },
    {
      "epoch": 0.23,
      "eval_gen_len": 18.7605,
      "eval_loss": 2.417249917984009,
      "eval_rouge1": 29.9482,
      "eval_rouge2": 8.8321,
      "eval_rougeL": 23.7848,
      "eval_rougeLsum": 23.7954,
      "eval_runtime": 341.816,
      "eval_samples_per_second": 33.152,
      "eval_steps_per_second": 1.384,
      "step": 1950
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0007532345330510469,
      "loss": 2.6498,
      "step": 2100
    },
    {
      "epoch": 0.25,
      "eval_gen_len": 18.8079,
      "eval_loss": 2.4158124923706055,
      "eval_rouge1": 29.5843,
      "eval_rouge2": 8.9229,
      "eval_rougeL": 23.6193,
      "eval_rougeLsum": 23.6255,
      "eval_runtime": 341.8291,
      "eval_samples_per_second": 33.151,
      "eval_steps_per_second": 1.384,
      "step": 2100
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0007355916254998823,
      "loss": 2.6321,
      "step": 2250
    },
    {
      "epoch": 0.26,
      "eval_gen_len": 18.7639,
      "eval_loss": 2.4022669792175293,
      "eval_rouge1": 29.9147,
      "eval_rouge2": 9.0085,
      "eval_rougeL": 23.8569,
      "eval_rougeLsum": 23.8709,
      "eval_runtime": 341.59,
      "eval_samples_per_second": 33.174,
      "eval_steps_per_second": 1.385,
      "step": 2250
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000717948717948718,
      "loss": 2.614,
      "step": 2400
    },
    {
      "epoch": 0.28,
      "eval_gen_len": 18.6922,
      "eval_loss": 2.3971035480499268,
      "eval_rouge1": 29.711,
      "eval_rouge2": 9.0017,
      "eval_rougeL": 23.761,
      "eval_rougeLsum": 23.7742,
      "eval_runtime": 341.4293,
      "eval_samples_per_second": 33.19,
      "eval_steps_per_second": 1.385,
      "step": 2400
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0007003058103975535,
      "loss": 2.6212,
      "step": 2550
    },
    {
      "epoch": 0.3,
      "eval_gen_len": 18.7082,
      "eval_loss": 2.390623092651367,
      "eval_rouge1": 29.498,
      "eval_rouge2": 8.6483,
      "eval_rougeL": 23.5006,
      "eval_rougeLsum": 23.5112,
      "eval_runtime": 341.8905,
      "eval_samples_per_second": 33.145,
      "eval_steps_per_second": 1.383,
      "step": 2550
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0006826629028463891,
      "loss": 2.6151,
      "step": 2700
    },
    {
      "epoch": 0.32,
      "eval_gen_len": 18.8923,
      "eval_loss": 2.3796188831329346,
      "eval_rouge1": 29.8502,
      "eval_rouge2": 8.9427,
      "eval_rougeL": 23.6665,
      "eval_rougeLsum": 23.6781,
      "eval_runtime": 341.6707,
      "eval_samples_per_second": 33.166,
      "eval_steps_per_second": 1.384,
      "step": 2700
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0006650199952952247,
      "loss": 2.6123,
      "step": 2850
    },
    {
      "epoch": 0.34,
      "eval_gen_len": 18.7541,
      "eval_loss": 2.371220588684082,
      "eval_rouge1": 30.0211,
      "eval_rouge2": 9.2412,
      "eval_rougeL": 24.0388,
      "eval_rougeLsum": 24.045,
      "eval_runtime": 341.6315,
      "eval_samples_per_second": 33.17,
      "eval_steps_per_second": 1.385,
      "step": 2850
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0006473770877440603,
      "loss": 2.5928,
      "step": 3000
    },
    {
      "epoch": 0.35,
      "eval_gen_len": 18.7963,
      "eval_loss": 2.359456777572632,
      "eval_rouge1": 30.3185,
      "eval_rouge2": 9.2796,
      "eval_rougeL": 24.2004,
      "eval_rougeLsum": 24.2101,
      "eval_runtime": 341.8833,
      "eval_samples_per_second": 33.146,
      "eval_steps_per_second": 1.384,
      "step": 3000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0006297341801928958,
      "loss": 2.5746,
      "step": 3150
    },
    {
      "epoch": 0.37,
      "eval_gen_len": 18.8229,
      "eval_loss": 2.366935968399048,
      "eval_rouge1": 29.8303,
      "eval_rouge2": 9.1665,
      "eval_rougeL": 23.8553,
      "eval_rougeLsum": 23.8672,
      "eval_runtime": 341.7148,
      "eval_samples_per_second": 33.162,
      "eval_steps_per_second": 1.384,
      "step": 3150
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0006120912726417314,
      "loss": 2.5619,
      "step": 3300
    },
    {
      "epoch": 0.39,
      "eval_gen_len": 18.8087,
      "eval_loss": 2.3527944087982178,
      "eval_rouge1": 30.4684,
      "eval_rouge2": 9.4451,
      "eval_rougeL": 24.2867,
      "eval_rougeLsum": 24.2939,
      "eval_runtime": 341.8038,
      "eval_samples_per_second": 33.154,
      "eval_steps_per_second": 1.384,
      "step": 3300
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000594448365090567,
      "loss": 2.5677,
      "step": 3450
    },
    {
      "epoch": 0.41,
      "eval_gen_len": 18.8491,
      "eval_loss": 2.343312978744507,
      "eval_rouge1": 30.496,
      "eval_rouge2": 9.4356,
      "eval_rougeL": 24.31,
      "eval_rougeLsum": 24.3125,
      "eval_runtime": 342.0548,
      "eval_samples_per_second": 33.129,
      "eval_steps_per_second": 1.383,
      "step": 3450
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005768054575394025,
      "loss": 2.5456,
      "step": 3600
    },
    {
      "epoch": 0.42,
      "eval_gen_len": 18.809,
      "eval_loss": 2.3360698223114014,
      "eval_rouge1": 30.5752,
      "eval_rouge2": 9.4803,
      "eval_rougeL": 24.3462,
      "eval_rougeLsum": 24.3559,
      "eval_runtime": 341.7402,
      "eval_samples_per_second": 33.16,
      "eval_steps_per_second": 1.384,
      "step": 3600
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005591625499882381,
      "loss": 2.5669,
      "step": 3750
    },
    {
      "epoch": 0.44,
      "eval_gen_len": 18.8287,
      "eval_loss": 2.327768325805664,
      "eval_rouge1": 30.0561,
      "eval_rouge2": 9.2402,
      "eval_rougeL": 24.0535,
      "eval_rougeLsum": 24.0713,
      "eval_runtime": 341.71,
      "eval_samples_per_second": 33.163,
      "eval_steps_per_second": 1.384,
      "step": 3750
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005415196424370737,
      "loss": 2.5446,
      "step": 3900
    },
    {
      "epoch": 0.46,
      "eval_gen_len": 18.8118,
      "eval_loss": 2.3254404067993164,
      "eval_rouge1": 30.3142,
      "eval_rouge2": 9.4929,
      "eval_rougeL": 24.335,
      "eval_rougeLsum": 24.3432,
      "eval_runtime": 341.8271,
      "eval_samples_per_second": 33.151,
      "eval_steps_per_second": 1.384,
      "step": 3900
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005238767348859092,
      "loss": 2.5536,
      "step": 4050
    },
    {
      "epoch": 0.48,
      "eval_gen_len": 18.9035,
      "eval_loss": 2.3251070976257324,
      "eval_rouge1": 30.2523,
      "eval_rouge2": 9.3005,
      "eval_rougeL": 24.163,
      "eval_rougeLsum": 24.1711,
      "eval_runtime": 341.8151,
      "eval_samples_per_second": 33.152,
      "eval_steps_per_second": 1.384,
      "step": 4050
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005062338273347448,
      "loss": 2.5154,
      "step": 4200
    },
    {
      "epoch": 0.49,
      "eval_gen_len": 18.7458,
      "eval_loss": 2.313904047012329,
      "eval_rouge1": 30.7718,
      "eval_rouge2": 9.8676,
      "eval_rougeL": 24.7111,
      "eval_rougeLsum": 24.7266,
      "eval_runtime": 341.6852,
      "eval_samples_per_second": 33.165,
      "eval_steps_per_second": 1.384,
      "step": 4200
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0004885909197835804,
      "loss": 2.5176,
      "step": 4350
    },
    {
      "epoch": 0.51,
      "eval_gen_len": 18.7983,
      "eval_loss": 2.309589385986328,
      "eval_rouge1": 30.5617,
      "eval_rouge2": 9.6562,
      "eval_rougeL": 24.4754,
      "eval_rougeLsum": 24.4862,
      "eval_runtime": 341.8284,
      "eval_samples_per_second": 33.151,
      "eval_steps_per_second": 1.384,
      "step": 4350
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0004709480122324159,
      "loss": 2.5307,
      "step": 4500
    },
    {
      "epoch": 0.53,
      "eval_gen_len": 18.8217,
      "eval_loss": 2.3089160919189453,
      "eval_rouge1": 30.601,
      "eval_rouge2": 9.6672,
      "eval_rougeL": 24.4465,
      "eval_rougeLsum": 24.4567,
      "eval_runtime": 341.6213,
      "eval_samples_per_second": 33.171,
      "eval_steps_per_second": 1.385,
      "step": 4500
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00045330510468125144,
      "loss": 2.515,
      "step": 4650
    },
    {
      "epoch": 0.55,
      "eval_gen_len": 18.8096,
      "eval_loss": 2.2991859912872314,
      "eval_rouge1": 31.1807,
      "eval_rouge2": 10.0105,
      "eval_rougeL": 24.9947,
      "eval_rougeLsum": 25.0096,
      "eval_runtime": 341.7452,
      "eval_samples_per_second": 33.159,
      "eval_steps_per_second": 1.384,
      "step": 4650
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000435662197130087,
      "loss": 2.5168,
      "step": 4800
    },
    {
      "epoch": 0.56,
      "eval_gen_len": 18.8254,
      "eval_loss": 2.292003631591797,
      "eval_rouge1": 30.8999,
      "eval_rouge2": 9.8832,
      "eval_rougeL": 24.7713,
      "eval_rougeLsum": 24.7823,
      "eval_runtime": 341.8542,
      "eval_samples_per_second": 33.149,
      "eval_steps_per_second": 1.384,
      "step": 4800
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0004180192895789226,
      "loss": 2.5021,
      "step": 4950
    },
    {
      "epoch": 0.58,
      "eval_gen_len": 18.8787,
      "eval_loss": 2.285507917404175,
      "eval_rouge1": 31.0569,
      "eval_rouge2": 9.8752,
      "eval_rougeL": 24.791,
      "eval_rougeLsum": 24.8033,
      "eval_runtime": 341.7747,
      "eval_samples_per_second": 33.156,
      "eval_steps_per_second": 1.384,
      "step": 4950
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00040037638202775815,
      "loss": 2.501,
      "step": 5100
    },
    {
      "epoch": 0.6,
      "eval_gen_len": 18.8315,
      "eval_loss": 2.2868235111236572,
      "eval_rouge1": 30.7132,
      "eval_rouge2": 9.8654,
      "eval_rougeL": 24.6084,
      "eval_rougeLsum": 24.6244,
      "eval_runtime": 341.9154,
      "eval_samples_per_second": 33.143,
      "eval_steps_per_second": 1.383,
      "step": 5100
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003827334744765937,
      "loss": 2.4849,
      "step": 5250
    },
    {
      "epoch": 0.62,
      "eval_gen_len": 18.8196,
      "eval_loss": 2.2783043384552,
      "eval_rouge1": 31.3434,
      "eval_rouge2": 10.206,
      "eval_rougeL": 25.0954,
      "eval_rougeLsum": 25.1114,
      "eval_runtime": 341.9076,
      "eval_samples_per_second": 33.143,
      "eval_steps_per_second": 1.383,
      "step": 5250
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003650905669254293,
      "loss": 2.4939,
      "step": 5400
    },
    {
      "epoch": 0.64,
      "eval_gen_len": 18.8579,
      "eval_loss": 2.275907039642334,
      "eval_rouge1": 31.1467,
      "eval_rouge2": 10.0457,
      "eval_rougeL": 24.964,
      "eval_rougeLsum": 24.9793,
      "eval_runtime": 341.6475,
      "eval_samples_per_second": 33.169,
      "eval_steps_per_second": 1.384,
      "step": 5400
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00034744765937426485,
      "loss": 2.4624,
      "step": 5550
    },
    {
      "epoch": 0.65,
      "eval_gen_len": 18.8098,
      "eval_loss": 2.2712931632995605,
      "eval_rouge1": 31.4288,
      "eval_rouge2": 10.1719,
      "eval_rougeL": 25.1096,
      "eval_rougeLsum": 25.1276,
      "eval_runtime": 341.723,
      "eval_samples_per_second": 33.161,
      "eval_steps_per_second": 1.384,
      "step": 5550
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003298047518231004,
      "loss": 2.456,
      "step": 5700
    },
    {
      "epoch": 0.67,
      "eval_gen_len": 18.8262,
      "eval_loss": 2.2674217224121094,
      "eval_rouge1": 31.1515,
      "eval_rouge2": 10.1208,
      "eval_rougeL": 25.0456,
      "eval_rougeLsum": 25.0532,
      "eval_runtime": 341.9008,
      "eval_samples_per_second": 33.144,
      "eval_steps_per_second": 1.383,
      "step": 5700
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000312161844271936,
      "loss": 2.4667,
      "step": 5850
    },
    {
      "epoch": 0.69,
      "eval_gen_len": 18.7816,
      "eval_loss": 2.262035608291626,
      "eval_rouge1": 31.3741,
      "eval_rouge2": 10.1733,
      "eval_rougeL": 25.1421,
      "eval_rougeLsum": 25.159,
      "eval_runtime": 341.6066,
      "eval_samples_per_second": 33.173,
      "eval_steps_per_second": 1.385,
      "step": 5850
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000294636556104446,
      "loss": 2.4658,
      "step": 6000
    },
    {
      "epoch": 0.71,
      "eval_gen_len": 18.8,
      "eval_loss": 2.258843183517456,
      "eval_rouge1": 31.3913,
      "eval_rouge2": 10.2645,
      "eval_rougeL": 25.1746,
      "eval_rougeLsum": 25.188,
      "eval_runtime": 341.9247,
      "eval_samples_per_second": 33.142,
      "eval_steps_per_second": 1.383,
      "step": 6000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00027699364855328156,
      "loss": 2.4943,
      "step": 6150
    },
    {
      "epoch": 0.72,
      "eval_gen_len": 18.8074,
      "eval_loss": 2.2533156871795654,
      "eval_rouge1": 31.3905,
      "eval_rouge2": 10.164,
      "eval_rougeL": 25.093,
      "eval_rougeLsum": 25.107,
      "eval_runtime": 341.8317,
      "eval_samples_per_second": 33.151,
      "eval_steps_per_second": 1.384,
      "step": 6150
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00025935074100211713,
      "loss": 2.473,
      "step": 6300
    },
    {
      "epoch": 0.74,
      "eval_gen_len": 18.7439,
      "eval_loss": 2.2551848888397217,
      "eval_rouge1": 31.1105,
      "eval_rouge2": 10.1939,
      "eval_rougeL": 24.9214,
      "eval_rougeLsum": 24.9321,
      "eval_runtime": 341.6034,
      "eval_samples_per_second": 33.173,
      "eval_steps_per_second": 1.385,
      "step": 6300
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00024170783345095273,
      "loss": 2.4687,
      "step": 6450
    },
    {
      "epoch": 0.76,
      "eval_gen_len": 18.7709,
      "eval_loss": 2.247098684310913,
      "eval_rouge1": 31.3387,
      "eval_rouge2": 10.2446,
      "eval_rougeL": 25.0746,
      "eval_rougeLsum": 25.0936,
      "eval_runtime": 341.7347,
      "eval_samples_per_second": 33.16,
      "eval_steps_per_second": 1.384,
      "step": 6450
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002240649258997883,
      "loss": 2.4286,
      "step": 6600
    },
    {
      "epoch": 0.78,
      "eval_gen_len": 18.8313,
      "eval_loss": 2.2467916011810303,
      "eval_rouge1": 31.1953,
      "eval_rouge2": 10.1277,
      "eval_rougeL": 24.9535,
      "eval_rougeLsum": 24.9714,
      "eval_runtime": 341.8485,
      "eval_samples_per_second": 33.149,
      "eval_steps_per_second": 1.384,
      "step": 6600
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00020642201834862386,
      "loss": 2.4492,
      "step": 6750
    },
    {
      "epoch": 0.79,
      "eval_gen_len": 18.7977,
      "eval_loss": 2.2422139644622803,
      "eval_rouge1": 31.7203,
      "eval_rouge2": 10.4934,
      "eval_rougeL": 25.3862,
      "eval_rougeLsum": 25.3946,
      "eval_runtime": 341.6909,
      "eval_samples_per_second": 33.164,
      "eval_steps_per_second": 1.384,
      "step": 6750
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018877911079745943,
      "loss": 2.4427,
      "step": 6900
    },
    {
      "epoch": 0.81,
      "eval_gen_len": 18.8144,
      "eval_loss": 2.2402756214141846,
      "eval_rouge1": 31.5498,
      "eval_rouge2": 10.4086,
      "eval_rougeL": 25.2384,
      "eval_rougeLsum": 25.2593,
      "eval_runtime": 341.7269,
      "eval_samples_per_second": 33.161,
      "eval_steps_per_second": 1.384,
      "step": 6900
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000171136203246295,
      "loss": 2.4641,
      "step": 7050
    },
    {
      "epoch": 0.83,
      "eval_gen_len": 18.7966,
      "eval_loss": 2.2365546226501465,
      "eval_rouge1": 31.4038,
      "eval_rouge2": 10.3691,
      "eval_rougeL": 25.1786,
      "eval_rougeLsum": 25.195,
      "eval_runtime": 341.8284,
      "eval_samples_per_second": 33.151,
      "eval_steps_per_second": 1.384,
      "step": 7050
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00015349329569513056,
      "loss": 2.4276,
      "step": 7200
    },
    {
      "epoch": 0.85,
      "eval_gen_len": 18.7789,
      "eval_loss": 2.2344412803649902,
      "eval_rouge1": 31.5076,
      "eval_rouge2": 10.4403,
      "eval_rougeL": 25.299,
      "eval_rougeLsum": 25.3201,
      "eval_runtime": 342.6233,
      "eval_samples_per_second": 33.074,
      "eval_steps_per_second": 1.381,
      "step": 7200
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00013585038814396613,
      "loss": 2.4402,
      "step": 7350
    },
    {
      "epoch": 0.86,
      "eval_gen_len": 18.7713,
      "eval_loss": 2.2317440509796143,
      "eval_rouge1": 31.5216,
      "eval_rouge2": 10.3901,
      "eval_rougeL": 25.276,
      "eval_rougeLsum": 25.2943,
      "eval_runtime": 345.4971,
      "eval_samples_per_second": 32.799,
      "eval_steps_per_second": 1.369,
      "step": 7350
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00011820748059280171,
      "loss": 2.44,
      "step": 7500
    },
    {
      "epoch": 0.88,
      "eval_gen_len": 18.7671,
      "eval_loss": 2.2292771339416504,
      "eval_rouge1": 31.4244,
      "eval_rouge2": 10.4211,
      "eval_rougeL": 25.2592,
      "eval_rougeLsum": 25.2735,
      "eval_runtime": 342.0133,
      "eval_samples_per_second": 33.133,
      "eval_steps_per_second": 1.383,
      "step": 7500
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00010056457304163728,
      "loss": 2.4251,
      "step": 7650
    },
    {
      "epoch": 0.9,
      "eval_gen_len": 18.7972,
      "eval_loss": 2.226907968521118,
      "eval_rouge1": 31.4887,
      "eval_rouge2": 10.3959,
      "eval_rougeL": 25.2335,
      "eval_rougeLsum": 25.2545,
      "eval_runtime": 341.7402,
      "eval_samples_per_second": 33.16,
      "eval_steps_per_second": 1.384,
      "step": 7650
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.292166549047284e-05,
      "loss": 2.456,
      "step": 7800
    },
    {
      "epoch": 0.92,
      "eval_gen_len": 18.786,
      "eval_loss": 2.224229097366333,
      "eval_rouge1": 31.4508,
      "eval_rouge2": 10.4079,
      "eval_rougeL": 25.2328,
      "eval_rougeLsum": 25.2564,
      "eval_runtime": 341.8379,
      "eval_samples_per_second": 33.15,
      "eval_steps_per_second": 1.384,
      "step": 7800
    },
    {
      "epoch": 0.94,
      "learning_rate": 6.527875793930841e-05,
      "loss": 2.4181,
      "step": 7950
    },
    {
      "epoch": 0.94,
      "eval_gen_len": 18.8012,
      "eval_loss": 2.2223522663116455,
      "eval_rouge1": 31.6181,
      "eval_rouge2": 10.5558,
      "eval_rougeL": 25.3867,
      "eval_rougeLsum": 25.4042,
      "eval_runtime": 342.1259,
      "eval_samples_per_second": 33.122,
      "eval_steps_per_second": 1.383,
      "step": 7950
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.763585038814397e-05,
      "loss": 2.4288,
      "step": 8100
    },
    {
      "epoch": 0.95,
      "eval_gen_len": 18.7953,
      "eval_loss": 2.22170352935791,
      "eval_rouge1": 31.7626,
      "eval_rouge2": 10.6059,
      "eval_rougeL": 25.4827,
      "eval_rougeLsum": 25.4958,
      "eval_runtime": 341.8728,
      "eval_samples_per_second": 33.147,
      "eval_steps_per_second": 1.384,
      "step": 8100
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.9992942836979537e-05,
      "loss": 2.4327,
      "step": 8250
    },
    {
      "epoch": 0.97,
      "eval_gen_len": 18.7827,
      "eval_loss": 2.220174789428711,
      "eval_rouge1": 31.6839,
      "eval_rouge2": 10.5615,
      "eval_rougeL": 25.4137,
      "eval_rougeLsum": 25.433,
      "eval_runtime": 342.1089,
      "eval_samples_per_second": 33.124,
      "eval_steps_per_second": 1.383,
      "step": 8250
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.2350035285815103e-05,
      "loss": 2.4118,
      "step": 8400
    },
    {
      "epoch": 0.99,
      "eval_gen_len": 18.7979,
      "eval_loss": 2.2196593284606934,
      "eval_rouge1": 31.6519,
      "eval_rouge2": 10.4949,
      "eval_rougeL": 25.3751,
      "eval_rougeLsum": 25.3984,
      "eval_runtime": 342.1132,
      "eval_samples_per_second": 33.124,
      "eval_steps_per_second": 1.383,
      "step": 8400
    }
  ],
  "max_steps": 8502,
  "num_train_epochs": 1,
  "total_flos": 4.261943991730176e+16,
  "trial_name": null,
  "trial_params": null
}