{
  "best_metric": 28.5073,
  "best_model_checkpoint": "/content/drive/MyDrive/checkpoint-26201",
  "epoch": 13.696473551637279,
  "eval_steps": 500,
  "global_step": 43500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1335826876836762,
      "grad_norm": 5.345764636993408,
      "learning_rate": 3.7102997922232118e-06,
      "loss": 3.9988,
      "step": 500
    },
    {
      "epoch": 0.2671653753673524,
      "grad_norm": 5.3753743171691895,
      "learning_rate": 7.4205995844464235e-06,
      "loss": 3.2671,
      "step": 1000
    },
    {
      "epoch": 0.4007480630510286,
      "grad_norm": 3.7295212745666504,
      "learning_rate": 1.1130899376669635e-05,
      "loss": 3.1006,
      "step": 1500
    },
    {
      "epoch": 0.5343307507347048,
      "grad_norm": 4.027897834777832,
      "learning_rate": 1.4841199168892847e-05,
      "loss": 2.9767,
      "step": 2000
    },
    {
      "epoch": 0.667913438418381,
      "grad_norm": 3.9697580337524414,
      "learning_rate": 1.855149896111606e-05,
      "loss": 2.8914,
      "step": 2500
    },
    {
      "epoch": 0.8014961261020572,
      "grad_norm": 3.5195724964141846,
      "learning_rate": 2.226179875333927e-05,
      "loss": 2.8273,
      "step": 3000
    },
    {
      "epoch": 0.9350788137857333,
      "grad_norm": 3.447735071182251,
      "learning_rate": 2.5972098545562486e-05,
      "loss": 2.7964,
      "step": 3500
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.2515146732330322,
      "eval_rouge1": 25.9968,
      "eval_rouge2": 10.7383,
      "eval_rougeL": 22.8305,
      "eval_runtime": 801.3334,
      "eval_samples_per_second": 5.851,
      "eval_steps_per_second": 0.585,
      "step": 3743
    },
    {
      "epoch": 1.0686615014694096,
      "grad_norm": 3.5466370582580566,
      "learning_rate": 2.9682398337785694e-05,
      "loss": 2.7258,
      "step": 4000
    },
    {
      "epoch": 1.2022441891530857,
      "grad_norm": 3.380523681640625,
      "learning_rate": 3.33926981300089e-05,
      "loss": 2.6799,
      "step": 4500
    },
    {
      "epoch": 1.3358268768367618,
      "grad_norm": 3.3388278484344482,
      "learning_rate": 3.710299792223212e-05,
      "loss": 2.6635,
      "step": 5000
    },
    {
      "epoch": 1.4694095645204381,
      "grad_norm": 4.365349292755127,
      "learning_rate": 4.0813297714455326e-05,
      "loss": 2.653,
      "step": 5500
    },
    {
      "epoch": 1.6029922522041145,
      "grad_norm": 2.9895472526550293,
      "learning_rate": 4.452359750667854e-05,
      "loss": 2.6307,
      "step": 6000
    },
    {
      "epoch": 1.7365749398877905,
      "grad_norm": 3.2920846939086914,
      "learning_rate": 4.8233897298901756e-05,
      "loss": 2.6279,
      "step": 6500
    },
    {
      "epoch": 1.8701576275714666,
      "grad_norm": 2.7936699390411377,
      "learning_rate": 4.708305499888667e-05,
      "loss": 2.6157,
      "step": 7000
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.2093820571899414,
      "eval_rouge1": 27.1603,
      "eval_rouge2": 11.6742,
      "eval_rougeL": 23.9152,
      "eval_runtime": 800.4224,
      "eval_samples_per_second": 5.858,
      "eval_steps_per_second": 0.586,
      "step": 7486
    },
    {
      "epoch": 2.003740315255143,
      "grad_norm": 2.9695687294006348,
      "learning_rate": 4.1516366065464264e-05,
      "loss": 2.5275,
      "step": 7500
    },
    {
      "epoch": 2.1373230029388193,
      "grad_norm": 2.902341842651367,
      "learning_rate": 3.594967713204186e-05,
      "loss": 2.434,
      "step": 8000
    },
    {
      "epoch": 2.270905690622495,
      "grad_norm": 2.9437291622161865,
      "learning_rate": 3.0382988198619462e-05,
      "loss": 2.4224,
      "step": 8500
    },
    {
      "epoch": 2.4044883783061715,
      "grad_norm": 3.196054458618164,
      "learning_rate": 2.4816299265197063e-05,
      "loss": 2.4284,
      "step": 9000
    },
    {
      "epoch": 2.5380710659898478,
      "grad_norm": 2.9762144088745117,
      "learning_rate": 1.924961033177466e-05,
      "loss": 2.4025,
      "step": 9500
    },
    {
      "epoch": 2.6716537536735236,
      "grad_norm": 2.9706368446350098,
      "learning_rate": 1.3682921398352261e-05,
      "loss": 2.4134,
      "step": 10000
    },
    {
      "epoch": 2.8052364413572,
      "grad_norm": 3.00219464302063,
      "learning_rate": 8.11623246492986e-06,
      "loss": 2.393,
      "step": 10500
    },
    {
      "epoch": 2.9388191290408763,
      "grad_norm": 3.0556745529174805,
      "learning_rate": 2.5495435315074595e-06,
      "loss": 2.4,
      "step": 11000
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.151719093322754,
      "eval_rouge1": 28.0829,
      "eval_rouge2": 12.389,
      "eval_rougeL": 24.8018,
      "eval_runtime": 828.6501,
      "eval_samples_per_second": 5.659,
      "eval_steps_per_second": 0.566,
      "step": 11229
    },
    {
      "epoch": 3.0724018167245526,
      "grad_norm": 2.9094104766845703,
      "learning_rate": 2.4396651527295397e-05,
      "loss": 2.3046,
      "step": 11500
    },
    {
      "epoch": 3.205984504408229,
      "grad_norm": 3.2464346885681152,
      "learning_rate": 2.3283462463264763e-05,
      "loss": 2.3092,
      "step": 12000
    },
    {
      "epoch": 3.339567192091905,
      "grad_norm": 2.8669161796569824,
      "learning_rate": 2.2170273399234126e-05,
      "loss": 2.311,
      "step": 12500
    },
    {
      "epoch": 3.473149879775581,
      "grad_norm": 2.9395506381988525,
      "learning_rate": 2.1057084335203492e-05,
      "loss": 2.3464,
      "step": 13000
    },
    {
      "epoch": 3.6067325674592574,
      "grad_norm": 2.589228630065918,
      "learning_rate": 1.994389527117286e-05,
      "loss": 2.3138,
      "step": 13500
    },
    {
      "epoch": 3.7403152551429333,
      "grad_norm": 3.119093418121338,
      "learning_rate": 1.883070620714222e-05,
      "loss": 2.3379,
      "step": 14000
    },
    {
      "epoch": 3.8738979428266096,
      "grad_norm": 3.049482822418213,
      "learning_rate": 1.7717517143111588e-05,
      "loss": 2.3203,
      "step": 14500
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.1520700454711914,
      "eval_rouge1": 27.9025,
      "eval_rouge2": 12.1745,
      "eval_rougeL": 24.6421,
      "eval_runtime": 806.5195,
      "eval_samples_per_second": 5.814,
      "eval_steps_per_second": 0.582,
      "step": 14972
    },
    {
      "epoch": 4.007480630510286,
      "grad_norm": 2.8268468379974365,
      "learning_rate": 1.6604328079080954e-05,
      "loss": 2.3081,
      "step": 15000
    },
    {
      "epoch": 4.141063318193962,
      "grad_norm": 3.0538229942321777,
      "learning_rate": 1.5491139015050317e-05,
      "loss": 2.21,
      "step": 15500
    },
    {
      "epoch": 4.2746460058776385,
      "grad_norm": 2.8657615184783936,
      "learning_rate": 1.4377949951019681e-05,
      "loss": 2.2212,
      "step": 16000
    },
    {
      "epoch": 4.408228693561314,
      "grad_norm": 3.4228334426879883,
      "learning_rate": 1.3264760886989048e-05,
      "loss": 2.2211,
      "step": 16500
    },
    {
      "epoch": 4.54181138124499,
      "grad_norm": 2.928118944168091,
      "learning_rate": 1.2151571822958412e-05,
      "loss": 2.2231,
      "step": 17000
    },
    {
      "epoch": 4.675394068928667,
      "grad_norm": 3.1149392127990723,
      "learning_rate": 1.1038382758927777e-05,
      "loss": 2.2522,
      "step": 17500
    },
    {
      "epoch": 4.808976756612343,
      "grad_norm": 3.263375759124756,
      "learning_rate": 9.925193694897141e-06,
      "loss": 2.2262,
      "step": 18000
    },
    {
      "epoch": 4.94255944429602,
      "grad_norm": 2.9795596599578857,
      "learning_rate": 8.812004630866506e-06,
      "loss": 2.2432,
      "step": 18500
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.1519482135772705,
      "eval_rouge1": 28.2114,
      "eval_rouge2": 12.4638,
      "eval_rougeL": 24.9195,
      "eval_runtime": 801.5692,
      "eval_samples_per_second": 5.85,
      "eval_steps_per_second": 0.585,
      "step": 18715
    },
    {
      "epoch": 5.0761421319796955,
      "grad_norm": 3.917699098587036,
      "learning_rate": 2.4619289340101523e-05,
      "loss": 2.1744,
      "step": 19000
    },
    {
      "epoch": 5.209724819663371,
      "grad_norm": 3.097011089324951,
      "learning_rate": 2.3951375901683144e-05,
      "loss": 2.187,
      "step": 19500
    },
    {
      "epoch": 5.343307507347048,
      "grad_norm": 3.4347126483917236,
      "learning_rate": 2.3283462463264763e-05,
      "loss": 2.2042,
      "step": 20000
    },
    {
      "epoch": 5.476890195030724,
      "grad_norm": 3.750795364379883,
      "learning_rate": 2.261554902484638e-05,
      "loss": 2.2261,
      "step": 20500
    },
    {
      "epoch": 5.6104728827144,
      "grad_norm": 3.1423909664154053,
      "learning_rate": 2.1947635586428e-05,
      "loss": 2.1995,
      "step": 21000
    },
    {
      "epoch": 5.744055570398077,
      "grad_norm": 3.2796082496643066,
      "learning_rate": 2.1279722148009618e-05,
      "loss": 2.2165,
      "step": 21500
    },
    {
      "epoch": 5.8776382580817526,
      "grad_norm": 3.300898313522339,
      "learning_rate": 2.0611808709591237e-05,
      "loss": 2.2252,
      "step": 22000
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.169365644454956,
      "eval_rouge1": 28.1516,
      "eval_rouge2": 12.3777,
      "eval_rougeL": 24.7436,
      "eval_runtime": 795.9208,
      "eval_samples_per_second": 5.891,
      "eval_steps_per_second": 0.589,
      "step": 22458
    },
    {
      "epoch": 6.011220945765428,
      "grad_norm": 3.3653814792633057,
      "learning_rate": 1.994389527117286e-05,
      "loss": 2.044,
      "step": 22500
    },
    {
      "epoch": 6.144803633449105,
      "grad_norm": 3.162733554840088,
      "learning_rate": 1.9275981832754473e-05,
      "loss": 2.1435,
      "step": 23000
    },
    {
      "epoch": 6.278386321132781,
      "grad_norm": 2.9544992446899414,
      "learning_rate": 1.8608068394336095e-05,
      "loss": 2.1289,
      "step": 23500
    },
    {
      "epoch": 6.411969008816458,
      "grad_norm": 3.7476911544799805,
      "learning_rate": 1.7940154955917714e-05,
      "loss": 2.1454,
      "step": 24000
    },
    {
      "epoch": 6.545551696500134,
      "grad_norm": 3.191617727279663,
      "learning_rate": 1.7272241517499332e-05,
      "loss": 2.1435,
      "step": 24500
    },
    {
      "epoch": 6.67913438418381,
      "grad_norm": 3.208509922027588,
      "learning_rate": 1.6604328079080954e-05,
      "loss": 2.1357,
      "step": 25000
    },
    {
      "epoch": 6.812717071867486,
      "grad_norm": 3.2755982875823975,
      "learning_rate": 1.593641464066257e-05,
      "loss": 2.1371,
      "step": 25500
    },
    {
      "epoch": 6.946299759551162,
      "grad_norm": 3.220367431640625,
      "learning_rate": 1.526850120224419e-05,
      "loss": 2.1313,
      "step": 26000
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.18220853805542,
      "eval_rouge1": 28.5073,
      "eval_rouge2": 12.6157,
      "eval_rougeL": 25.1244,
      "eval_runtime": 795.4817,
      "eval_samples_per_second": 5.895,
      "eval_steps_per_second": 0.59,
      "step": 26201
    },
    {
      "epoch": 7.079882447234838,
      "grad_norm": 3.261324167251587,
      "learning_rate": 1.4600587763825809e-05,
      "loss": 2.0706,
      "step": 26500
    },
    {
      "epoch": 7.213465134918515,
      "grad_norm": 3.2409138679504395,
      "learning_rate": 1.3932674325407427e-05,
      "loss": 2.0684,
      "step": 27000
    },
    {
      "epoch": 7.347047822602191,
      "grad_norm": 3.02018666267395,
      "learning_rate": 1.3264760886989048e-05,
      "loss": 2.0621,
      "step": 27500
    },
    {
      "epoch": 7.480630510285867,
      "grad_norm": 3.306445598602295,
      "learning_rate": 1.2596847448570668e-05,
      "loss": 2.0637,
      "step": 28000
    },
    {
      "epoch": 7.614213197969543,
      "grad_norm": 3.3543508052825928,
      "learning_rate": 1.1928934010152284e-05,
      "loss": 2.0804,
      "step": 28500
    },
    {
      "epoch": 7.747795885653219,
      "grad_norm": 3.1137688159942627,
      "learning_rate": 1.1261020571733903e-05,
      "loss": 2.0845,
      "step": 29000
    },
    {
      "epoch": 7.881378573336896,
      "grad_norm": 3.7980918884277344,
      "learning_rate": 1.0593107133315523e-05,
      "loss": 2.0796,
      "step": 29500
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.18402361869812,
      "eval_rouge1": 28.743,
      "eval_rouge2": 12.8907,
      "eval_rougeL": 25.4018,
      "eval_runtime": 821.2111,
      "eval_samples_per_second": 5.71,
      "eval_steps_per_second": 0.571,
      "step": 29944
    },
    {
      "epoch": 8.014961261020572,
      "grad_norm": 3.3595690727233887,
      "learning_rate": 9.925193694897141e-06,
      "loss": 2.1025,
      "step": 30000
    },
    {
      "epoch": 8.148543948704248,
      "grad_norm": 3.24507737159729,
      "learning_rate": 9.25728025647876e-06,
      "loss": 2.0176,
      "step": 30500
    },
    {
      "epoch": 8.282126636387924,
      "grad_norm": 3.5450592041015625,
      "learning_rate": 8.58936681806038e-06,
      "loss": 2.0326,
      "step": 31000
    },
    {
      "epoch": 8.4157093240716,
      "grad_norm": 3.5833873748779297,
      "learning_rate": 7.921453379642e-06,
      "loss": 2.0427,
      "step": 31500
    },
    {
      "epoch": 8.549292011755277,
      "grad_norm": 4.691043376922607,
      "learning_rate": 7.2535399412236176e-06,
      "loss": 2.0352,
      "step": 32000
    },
    {
      "epoch": 10.232997481108312,
      "grad_norm": 3.2953643798828125,
      "learning_rate": 7.362510495382033e-06,
      "loss": 1.8856,
      "step": 32500
    },
    {
      "epoch": 10.3904282115869,
      "grad_norm": 3.4494450092315674,
      "learning_rate": 6.70654911838791e-06,
      "loss": 1.8634,
      "step": 33000
    },
    {
      "epoch": 10.547858942065492,
      "grad_norm": 2.9981698989868164,
      "learning_rate": 6.050587741393787e-06,
      "loss": 1.8751,
      "step": 33500
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 3.224597454071045,
      "learning_rate": 5.394626364399664e-06,
      "loss": 1.8864,
      "step": 34000
    },
    {
      "epoch": 10.86272040302267,
      "grad_norm": 3.196687698364258,
      "learning_rate": 4.738664987405542e-06,
      "loss": 1.8653,
      "step": 34500
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.1366946697235107,
      "eval_rouge1": 29.2809,
      "eval_rouge2": 13.0769,
      "eval_rougeL": 25.8435,
      "eval_runtime": 656.6282,
      "eval_samples_per_second": 6.468,
      "eval_steps_per_second": 0.647,
      "step": 34936
    },
    {
      "epoch": 11.02015113350126,
      "grad_norm": 3.253657341003418,
      "learning_rate": 4.082703610411419e-06,
      "loss": 1.8604,
      "step": 35000
    },
    {
      "epoch": 11.17758186397985,
      "grad_norm": 3.6433730125427246,
      "learning_rate": 3.4267422334172966e-06,
      "loss": 1.838,
      "step": 35500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 3.041062355041504,
      "learning_rate": 2.770780856423174e-06,
      "loss": 1.8356,
      "step": 36000
    },
    {
      "epoch": 11.492443324937028,
      "grad_norm": 2.9957120418548584,
      "learning_rate": 2.114819479429051e-06,
      "loss": 1.8549,
      "step": 36500
    },
    {
      "epoch": 11.649874055415617,
      "grad_norm": 3.1265900135040283,
      "learning_rate": 1.4588581024349287e-06,
      "loss": 1.8613,
      "step": 37000
    },
    {
      "epoch": 11.807304785894207,
      "grad_norm": 3.275404691696167,
      "learning_rate": 8.028967254408061e-07,
      "loss": 1.8527,
      "step": 37500
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 3.625509023666382,
      "learning_rate": 1.4693534844668346e-07,
      "loss": 1.8359,
      "step": 38000
    },
    {
      "epoch": 12.122166246851386,
      "grad_norm": 3.2058401107788086,
      "learning_rate": 1.9694584382871536e-05,
      "loss": 1.861,
      "step": 38500
    },
    {
      "epoch": 12.279596977329975,
      "grad_norm": 3.0847251415252686,
      "learning_rate": 1.9301007556675063e-05,
      "loss": 1.8648,
      "step": 39000
    },
    {
      "epoch": 12.437027707808564,
      "grad_norm": 3.7241926193237305,
      "learning_rate": 1.890743073047859e-05,
      "loss": 1.8878,
      "step": 39500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 3.053447723388672,
      "learning_rate": 1.8513853904282116e-05,
      "loss": 1.8892,
      "step": 40000
    },
    {
      "epoch": 12.751889168765743,
      "grad_norm": 3.691380500793457,
      "learning_rate": 1.8120277078085644e-05,
      "loss": 1.9009,
      "step": 40500
    },
    {
      "epoch": 12.909319899244332,
      "grad_norm": 3.542070150375366,
      "learning_rate": 1.7726700251889168e-05,
      "loss": 1.8996,
      "step": 41000
    },
    {
      "epoch": 13.0,
      "eval_loss": 2.1603260040283203,
      "eval_rouge1": 29.3365,
      "eval_rouge2": 13.1558,
      "eval_rougeL": 25.9522,
      "eval_runtime": 687.7919,
      "eval_samples_per_second": 6.175,
      "eval_steps_per_second": 0.618,
      "step": 41288
    },
    {
      "epoch": 13.066750629722922,
      "grad_norm": 2.955968141555786,
      "learning_rate": 1.7333123425692696e-05,
      "loss": 1.848,
      "step": 41500
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 3.35233998298645,
      "learning_rate": 1.6939546599496224e-05,
      "loss": 1.8086,
      "step": 42000
    },
    {
      "epoch": 13.3816120906801,
      "grad_norm": 3.3190128803253174,
      "learning_rate": 1.6545969773299748e-05,
      "loss": 1.8255,
      "step": 42500
    },
    {
      "epoch": 13.53904282115869,
      "grad_norm": 4.00574254989624,
      "learning_rate": 1.6152392947103276e-05,
      "loss": 1.8365,
      "step": 43000
    },
    {
      "epoch": 13.696473551637279,
      "grad_norm": 2.998016357421875,
      "learning_rate": 1.5758816120906804e-05,
      "loss": 1.8473,
      "step": 43500
    }
  ],
  "logging_steps": 500,
  "max_steps": 63520,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.446994738874286e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}