{
  "best_metric": 29.9002,
  "best_model_checkpoint": "/content/drive/MyDrive/ArabartModel/checkpoint-54128",
  "epoch": 17.0,
  "eval_steps": 500,
  "global_step": 57511,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32722513089005234,
      "grad_norm": 1.563672423362732,
      "learning_rate": 4.6727748691099475e-05,
      "loss": 0.0195,
      "step": 500
    },
    {
      "epoch": 0.6544502617801047,
      "grad_norm": 1.7397737503051758,
      "learning_rate": 4.3455497382198955e-05,
      "loss": 0.0244,
      "step": 1000
    },
    {
      "epoch": 0.981675392670157,
      "grad_norm": 3.006633758544922,
      "learning_rate": 4.018324607329843e-05,
      "loss": 0.0293,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.626201629638672,
      "eval_rouge1": 25.2705,
      "eval_rouge2": 9.9865,
      "eval_rougeL": 21.8678,
      "eval_runtime": 372.5145,
      "eval_samples_per_second": 5.892,
      "eval_steps_per_second": 0.591,
      "step": 1528
    },
    {
      "epoch": 1.3089005235602094,
      "grad_norm": 3.4732136726379395,
      "learning_rate": 4.3455497382198955e-05,
      "loss": 0.0456,
      "step": 2000
    },
    {
      "epoch": 1.6361256544502618,
      "grad_norm": 2.2575156688690186,
      "learning_rate": 4.181937172774869e-05,
      "loss": 0.0619,
      "step": 2500
    },
    {
      "epoch": 1.9633507853403143,
      "grad_norm": 6.030032157897949,
      "learning_rate": 4.018324607329843e-05,
      "loss": 0.0993,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.542174339294434,
      "eval_rouge1": 25.0744,
      "eval_rouge2": 9.8534,
      "eval_rougeL": 21.6992,
      "eval_runtime": 411.9676,
      "eval_samples_per_second": 5.328,
      "eval_steps_per_second": 0.534,
      "step": 3056
    },
    {
      "epoch": 2.2905759162303667,
      "grad_norm": 6.401626110076904,
      "learning_rate": 3.8547120418848174e-05,
      "loss": 0.21,
      "step": 3500
    },
    {
      "epoch": 2.6178010471204187,
      "grad_norm": 5.806931495666504,
      "learning_rate": 3.691099476439791e-05,
      "loss": 0.3595,
      "step": 4000
    },
    {
      "epoch": 2.945026178010471,
      "grad_norm": 5.840355396270752,
      "learning_rate": 3.5274869109947647e-05,
      "loss": 0.6436,
      "step": 4500
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.927168369293213,
      "eval_rouge1": 25.5914,
      "eval_rouge2": 10.2904,
      "eval_rougeL": 22.3089,
      "eval_runtime": 412.3529,
      "eval_samples_per_second": 5.323,
      "eval_steps_per_second": 0.534,
      "step": 4584
    },
    {
      "epoch": 3.2722513089005236,
      "grad_norm": 5.320337772369385,
      "learning_rate": 3.3638743455497386e-05,
      "loss": 0.7617,
      "step": 5000
    },
    {
      "epoch": 3.599476439790576,
      "grad_norm": 5.708410739898682,
      "learning_rate": 3.2002617801047126e-05,
      "loss": 0.9186,
      "step": 5500
    },
    {
      "epoch": 3.9267015706806285,
      "grad_norm": 6.043923377990723,
      "learning_rate": 3.036649214659686e-05,
      "loss": 1.112,
      "step": 6000
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.2077620029449463,
      "eval_rouge1": 26.5258,
      "eval_rouge2": 11.116,
      "eval_rougeL": 23.3381,
      "eval_runtime": 397.8337,
      "eval_samples_per_second": 5.517,
      "eval_steps_per_second": 0.553,
      "step": 6112
    },
    {
      "epoch": 4.2539267015706805,
      "grad_norm": 5.179211139678955,
      "learning_rate": 2.87303664921466e-05,
      "loss": 1.0997,
      "step": 6500
    },
    {
      "epoch": 4.581151832460733,
      "grad_norm": 4.997713565826416,
      "learning_rate": 2.709424083769634e-05,
      "loss": 1.0736,
      "step": 7000
    },
    {
      "epoch": 4.908376963350785,
      "grad_norm": 5.441833972930908,
      "learning_rate": 2.545811518324607e-05,
      "loss": 1.0866,
      "step": 7500
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.3156800270080566,
      "eval_rouge1": 26.4275,
      "eval_rouge2": 10.8484,
      "eval_rougeL": 23.0503,
      "eval_runtime": 402.2407,
      "eval_samples_per_second": 5.457,
      "eval_steps_per_second": 0.547,
      "step": 7640
    },
    {
      "epoch": 5.2356020942408374,
      "grad_norm": 4.417330741882324,
      "learning_rate": 2.382198952879581e-05,
      "loss": 0.9343,
      "step": 8000
    },
    {
      "epoch": 5.56282722513089,
      "grad_norm": 5.149570465087891,
      "learning_rate": 2.218586387434555e-05,
      "loss": 0.9473,
      "step": 8500
    },
    {
      "epoch": 5.890052356020942,
      "grad_norm": 5.305272102355957,
      "learning_rate": 2.054973821989529e-05,
      "loss": 0.9589,
      "step": 9000
    },
    {
      "epoch": 6.0,
      "eval_loss": 3.433619737625122,
      "eval_rouge1": 26.3479,
      "eval_rouge2": 10.8544,
      "eval_rougeL": 23.0206,
      "eval_runtime": 385.2891,
      "eval_samples_per_second": 5.697,
      "eval_steps_per_second": 0.571,
      "step": 9168
    },
    {
      "epoch": 6.217277486910994,
      "grad_norm": 5.96689510345459,
      "learning_rate": 1.8913612565445027e-05,
      "loss": 0.8437,
      "step": 9500
    },
    {
      "epoch": 6.544502617801047,
      "grad_norm": 5.179261207580566,
      "learning_rate": 1.7277486910994763e-05,
      "loss": 0.8582,
      "step": 10000
    },
    {
      "epoch": 6.871727748691099,
      "grad_norm": 4.92213773727417,
      "learning_rate": 1.5641361256544503e-05,
      "loss": 0.8669,
      "step": 10500
    },
    {
      "epoch": 7.0,
      "eval_loss": 3.551990032196045,
      "eval_rouge1": 26.0878,
      "eval_rouge2": 10.6444,
      "eval_rougeL": 22.7671,
      "eval_runtime": 413.1448,
      "eval_samples_per_second": 5.313,
      "eval_steps_per_second": 0.533,
      "step": 10696
    },
    {
      "epoch": 7.198952879581152,
      "grad_norm": 4.538914203643799,
      "learning_rate": 1.4005235602094241e-05,
      "loss": 0.7803,
      "step": 11000
    },
    {
      "epoch": 7.526178010471204,
      "grad_norm": 5.420250415802002,
      "learning_rate": 1.236910994764398e-05,
      "loss": 0.7777,
      "step": 11500
    },
    {
      "epoch": 7.853403141361256,
      "grad_norm": 4.503458023071289,
      "learning_rate": 1.0732984293193717e-05,
      "loss": 0.7894,
      "step": 12000
    },
    {
      "epoch": 8.0,
      "eval_loss": 3.652216672897339,
      "eval_rouge1": 26.1239,
      "eval_rouge2": 10.689,
      "eval_rougeL": 22.8303,
      "eval_runtime": 389.5703,
      "eval_samples_per_second": 5.634,
      "eval_steps_per_second": 0.565,
      "step": 12224
    },
    {
      "epoch": 8.180628272251308,
      "grad_norm": 4.9211812019348145,
      "learning_rate": 9.096858638743457e-06,
      "loss": 0.7505,
      "step": 12500
    },
    {
      "epoch": 8.507853403141361,
      "grad_norm": 4.948258876800537,
      "learning_rate": 7.4607329842931935e-06,
      "loss": 0.731,
      "step": 13000
    },
    {
      "epoch": 8.835078534031414,
      "grad_norm": 4.717357158660889,
      "learning_rate": 5.824607329842932e-06,
      "loss": 0.7331,
      "step": 13500
    },
    {
      "epoch": 9.0,
      "eval_loss": 3.7317800521850586,
      "eval_rouge1": 26.2374,
      "eval_rouge2": 10.7166,
      "eval_rougeL": 22.9298,
      "eval_runtime": 385.8895,
      "eval_samples_per_second": 5.688,
      "eval_steps_per_second": 0.57,
      "step": 13752
    },
    {
      "epoch": 9.162303664921467,
      "grad_norm": 4.790928363800049,
      "learning_rate": 4.18848167539267e-06,
      "loss": 0.7187,
      "step": 14000
    },
    {
      "epoch": 9.489528795811518,
      "grad_norm": 4.424731254577637,
      "learning_rate": 2.5523560209424085e-06,
      "loss": 0.6988,
      "step": 14500
    },
    {
      "epoch": 9.81675392670157,
      "grad_norm": 4.868335723876953,
      "learning_rate": 9.162303664921465e-07,
      "loss": 0.7027,
      "step": 15000
    },
    {
      "epoch": 10.0,
      "eval_loss": 3.772279739379883,
      "eval_rouge1": 26.1242,
      "eval_rouge2": 10.7689,
      "eval_rougeL": 22.8692,
      "eval_runtime": 387.9211,
      "eval_samples_per_second": 5.658,
      "eval_steps_per_second": 0.567,
      "step": 15280
    },
    {
      "epoch": 4.141063318193962,
      "grad_norm": 4.127313613891602,
      "learning_rate": 3.619645560602013e-05,
      "loss": 2.3856,
      "step": 15500
    },
    {
      "epoch": 4.2746460058776385,
      "grad_norm": 3.7080917358398438,
      "learning_rate": 3.575117998040787e-05,
      "loss": 2.2343,
      "step": 16000
    },
    {
      "epoch": 4.408228693561314,
      "grad_norm": 3.771442413330078,
      "learning_rate": 3.530590435479562e-05,
      "loss": 2.2498,
      "step": 16500
    },
    {
      "epoch": 4.54181138124499,
      "grad_norm": 3.3883867263793945,
      "learning_rate": 3.486062872918336e-05,
      "loss": 2.2734,
      "step": 17000
    },
    {
      "epoch": 4.675394068928667,
      "grad_norm": 3.82869029045105,
      "learning_rate": 3.441535310357111e-05,
      "loss": 2.2957,
      "step": 17500
    },
    {
      "epoch": 4.808976756612343,
      "grad_norm": 3.480701208114624,
      "learning_rate": 3.397007747795886e-05,
      "loss": 2.255,
      "step": 18000
    },
    {
      "epoch": 4.94255944429602,
      "grad_norm": 3.433276891708374,
      "learning_rate": 3.3524801852346606e-05,
      "loss": 2.2527,
      "step": 18500
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.624432325363159,
      "eval_rouge1": 27.5622,
      "eval_rouge2": 11.8188,
      "eval_rougeL": 24.2339,
      "eval_runtime": 862.1361,
      "eval_samples_per_second": 5.439,
      "eval_steps_per_second": 0.544,
      "step": 18715
    },
    {
      "epoch": 5.0761421319796955,
      "grad_norm": 3.8290796279907227,
      "learning_rate": 3.307952622673435e-05,
      "loss": 2.1614,
      "step": 19000
    },
    {
      "epoch": 5.209724819663371,
      "grad_norm": 4.148732662200928,
      "learning_rate": 3.2634250601122095e-05,
      "loss": 2.028,
      "step": 19500
    },
    {
      "epoch": 5.343307507347048,
      "grad_norm": 3.9491941928863525,
      "learning_rate": 3.218897497550984e-05,
      "loss": 2.0413,
      "step": 20000
    },
    {
      "epoch": 5.476890195030724,
      "grad_norm": 4.000278472900391,
      "learning_rate": 3.174369934989759e-05,
      "loss": 2.1058,
      "step": 20500
    },
    {
      "epoch": 5.6104728827144,
      "grad_norm": 4.109215259552002,
      "learning_rate": 3.129842372428534e-05,
      "loss": 2.0563,
      "step": 21000
    },
    {
      "epoch": 5.744055570398077,
      "grad_norm": 3.3794937133789062,
      "learning_rate": 3.085314809867308e-05,
      "loss": 2.0737,
      "step": 21500
    },
    {
      "epoch": 5.8776382580817526,
      "grad_norm": 3.326864719390869,
      "learning_rate": 3.0407872473060827e-05,
      "loss": 2.085,
      "step": 22000
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.6439783573150635,
      "eval_rouge1": 27.1127,
      "eval_rouge2": 11.6364,
      "eval_rougeL": 23.8039,
      "eval_runtime": 879.7933,
      "eval_samples_per_second": 5.33,
      "eval_steps_per_second": 0.533,
      "step": 22458
    },
    {
      "epoch": 6.011220945765428,
      "grad_norm": 3.5264782905578613,
      "learning_rate": 2.9962596847448572e-05,
      "loss": 1.8559,
      "step": 22500
    },
    {
      "epoch": 6.144803633449105,
      "grad_norm": 3.7577388286590576,
      "learning_rate": 2.951732122183632e-05,
      "loss": 1.8982,
      "step": 23000
    },
    {
      "epoch": 6.278386321132781,
      "grad_norm": 3.2084107398986816,
      "learning_rate": 2.907204559622406e-05,
      "loss": 1.8801,
      "step": 23500
    },
    {
      "epoch": 6.411969008816458,
      "grad_norm": 4.275125503540039,
      "learning_rate": 2.8626769970611812e-05,
      "loss": 1.9144,
      "step": 24000
    },
    {
      "epoch": 6.545551696500134,
      "grad_norm": 3.5503015518188477,
      "learning_rate": 2.8181494344999553e-05,
      "loss": 1.9229,
      "step": 24500
    },
    {
      "epoch": 6.67913438418381,
      "grad_norm": 3.489950656890869,
      "learning_rate": 2.77362187193873e-05,
      "loss": 1.9033,
      "step": 25000
    },
    {
      "epoch": 6.812717071867486,
      "grad_norm": 3.5493781566619873,
      "learning_rate": 2.7290943093775046e-05,
      "loss": 1.9058,
      "step": 25500
    },
    {
      "epoch": 6.946299759551162,
      "grad_norm": 3.603605031967163,
      "learning_rate": 2.6845667468162793e-05,
      "loss": 1.8774,
      "step": 26000
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.670841693878174,
      "eval_rouge1": 27.7286,
      "eval_rouge2": 11.9572,
      "eval_rougeL": 24.3316,
      "eval_runtime": 903.5292,
      "eval_samples_per_second": 5.19,
      "eval_steps_per_second": 0.519,
      "step": 26201
    },
    {
      "epoch": 7.079882447234838,
      "grad_norm": 3.9646942615509033,
      "learning_rate": 2.640039184255054e-05,
      "loss": 1.8442,
      "step": 26500
    },
    {
      "epoch": 7.213465134918515,
      "grad_norm": 4.019280433654785,
      "learning_rate": 2.5955116216938286e-05,
      "loss": 1.729,
      "step": 27000
    },
    {
      "epoch": 7.347047822602191,
      "grad_norm": 3.9131412506103516,
      "learning_rate": 2.5509840591326034e-05,
      "loss": 1.7656,
      "step": 27500
    },
    {
      "epoch": 7.480630510285867,
      "grad_norm": 3.336970806121826,
      "learning_rate": 2.5064564965713778e-05,
      "loss": 1.7733,
      "step": 28000
    },
    {
      "epoch": 7.614213197969543,
      "grad_norm": 3.7517452239990234,
      "learning_rate": 2.4619289340101523e-05,
      "loss": 1.7842,
      "step": 28500
    },
    {
      "epoch": 7.747795885653219,
      "grad_norm": 3.8601882457733154,
      "learning_rate": 2.4174013714489267e-05,
      "loss": 1.7876,
      "step": 29000
    },
    {
      "epoch": 7.881378573336896,
      "grad_norm": 3.928703784942627,
      "learning_rate": 2.372873808887702e-05,
      "loss": 1.7826,
      "step": 29500
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.7165374755859375,
      "eval_rouge1": 27.5923,
      "eval_rouge2": 11.9,
      "eval_rougeL": 24.2586,
      "eval_runtime": 898.7001,
      "eval_samples_per_second": 5.218,
      "eval_steps_per_second": 0.522,
      "step": 29944
    },
    {
      "epoch": 9.151921903599757,
      "grad_norm": 4.411174774169922,
      "learning_rate": 1.949359365466748e-05,
      "loss": 1.3756,
      "step": 30000
    },
    {
      "epoch": 9.304453935326418,
      "grad_norm": 4.3166985511779785,
      "learning_rate": 1.8985153548911936e-05,
      "loss": 1.4059,
      "step": 30500
    },
    {
      "epoch": 9.45698596705308,
      "grad_norm": 3.6181671619415283,
      "learning_rate": 1.8476713443156397e-05,
      "loss": 1.4086,
      "step": 31000
    },
    {
      "epoch": 9.609517998779744,
      "grad_norm": 4.077247142791748,
      "learning_rate": 1.7968273337400855e-05,
      "loss": 1.417,
      "step": 31500
    },
    {
      "epoch": 9.762050030506407,
      "grad_norm": 3.4715030193328857,
      "learning_rate": 1.7459833231645312e-05,
      "loss": 1.4021,
      "step": 32000
    },
    {
      "epoch": 9.91458206223307,
      "grad_norm": 3.7810068130493164,
      "learning_rate": 1.6951393125889773e-05,
      "loss": 1.4047,
      "step": 32500
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.808703899383545,
      "eval_rouge1": 27.8772,
      "eval_rouge2": 12.0303,
      "eval_rougeL": 24.5034,
      "eval_runtime": 743.946,
      "eval_samples_per_second": 5.877,
      "eval_steps_per_second": 0.589,
      "step": 32780
    },
    {
      "epoch": 10.06711409395973,
      "grad_norm": 3.981015682220459,
      "learning_rate": 1.644295302013423e-05,
      "loss": 1.3691,
      "step": 33000
    },
    {
      "epoch": 10.219646125686394,
      "grad_norm": 3.829094648361206,
      "learning_rate": 1.5934512914378688e-05,
      "loss": 1.3323,
      "step": 33500
    },
    {
      "epoch": 10.372178157413057,
      "grad_norm": 3.636704206466675,
      "learning_rate": 1.5426072808623145e-05,
      "loss": 1.3337,
      "step": 34000
    },
    {
      "epoch": 10.52471018913972,
      "grad_norm": 4.167761325836182,
      "learning_rate": 1.4917632702867604e-05,
      "loss": 1.3512,
      "step": 34500
    },
    {
      "epoch": 10.677242220866383,
      "grad_norm": 3.829911470413208,
      "learning_rate": 1.4409192597112062e-05,
      "loss": 1.3453,
      "step": 35000
    },
    {
      "epoch": 10.829774252593044,
      "grad_norm": 4.00424861907959,
      "learning_rate": 1.390075249135652e-05,
      "loss": 1.3308,
      "step": 35500
    },
    {
      "epoch": 10.982306284319707,
      "grad_norm": 4.3669657707214355,
      "learning_rate": 1.3392312385600977e-05,
      "loss": 1.3781,
      "step": 36000
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.769470453262329,
      "eval_rouge1": 28.0814,
      "eval_rouge2": 12.3353,
      "eval_rougeL": 24.7091,
      "eval_runtime": 745.2741,
      "eval_samples_per_second": 5.866,
      "eval_steps_per_second": 0.588,
      "step": 36058
    },
    {
      "epoch": 11.13483831604637,
      "grad_norm": 3.7836453914642334,
      "learning_rate": 1.2883872279845436e-05,
      "loss": 1.275,
      "step": 36500
    },
    {
      "epoch": 11.287370347773033,
      "grad_norm": 4.0213751792907715,
      "learning_rate": 1.2375432174089893e-05,
      "loss": 1.2572,
      "step": 37000
    },
    {
      "epoch": 11.439902379499696,
      "grad_norm": 3.626115083694458,
      "learning_rate": 1.186699206833435e-05,
      "loss": 1.2687,
      "step": 37500
    },
    {
      "epoch": 11.592434411226357,
      "grad_norm": 4.4103007316589355,
      "learning_rate": 1.1358551962578808e-05,
      "loss": 1.2807,
      "step": 38000
    },
    {
      "epoch": 11.74496644295302,
      "grad_norm": 3.681063413619995,
      "learning_rate": 1.0850111856823267e-05,
      "loss": 1.2986,
      "step": 38500
    },
    {
      "epoch": 11.897498474679683,
      "grad_norm": 4.0368170738220215,
      "learning_rate": 1.0341671751067725e-05,
      "loss": 1.2784,
      "step": 39000
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.83615779876709,
      "eval_rouge1": 28.2406,
      "eval_rouge2": 12.197,
      "eval_rougeL": 24.7367,
      "eval_runtime": 733.2323,
      "eval_samples_per_second": 5.963,
      "eval_steps_per_second": 0.597,
      "step": 39336
    },
    {
      "epoch": 12.050030506406346,
      "grad_norm": 4.6332173347473145,
      "learning_rate": 9.833231645312182e-06,
      "loss": 1.2071,
      "step": 39500
    },
    {
      "epoch": 12.202562538133009,
      "grad_norm": 3.7481937408447266,
      "learning_rate": 9.324791539556641e-06,
      "loss": 1.2085,
      "step": 40000
    },
    {
      "epoch": 12.35509456985967,
      "grad_norm": 4.701822757720947,
      "learning_rate": 8.816351433801099e-06,
      "loss": 1.2225,
      "step": 40500
    },
    {
      "epoch": 12.507626601586333,
      "grad_norm": 4.165287494659424,
      "learning_rate": 8.307911328045556e-06,
      "loss": 1.2187,
      "step": 41000
    },
    {
      "epoch": 12.660158633312996,
      "grad_norm": 4.279840469360352,
      "learning_rate": 7.799471222290014e-06,
      "loss": 1.2157,
      "step": 41500
    },
    {
      "epoch": 12.812690665039659,
      "grad_norm": 4.762269973754883,
      "learning_rate": 7.291031116534472e-06,
      "loss": 1.2277,
      "step": 42000
    },
    {
      "epoch": 12.965222696766322,
      "grad_norm": 4.380380153656006,
      "learning_rate": 6.782591010778931e-06,
      "loss": 1.2371,
      "step": 42500
    },
    {
      "epoch": 13.0,
      "eval_loss": 2.921924114227295,
      "eval_rouge1": 27.8556,
      "eval_rouge2": 12.033,
      "eval_rougeL": 24.4386,
      "eval_runtime": 791.9797,
      "eval_samples_per_second": 5.52,
      "eval_steps_per_second": 0.553,
      "step": 42614
    },
    {
      "epoch": 12.710611882944132,
      "grad_norm": 4.347652435302734,
      "learning_rate": 7.631293723519558e-06,
      "loss": 1.6632,
      "step": 43000
    },
    {
      "epoch": 12.858409695536507,
      "grad_norm": 4.261178493499756,
      "learning_rate": 7.138634348211647e-06,
      "loss": 1.627,
      "step": 43500
    },
    {
      "epoch": 13.0,
      "eval_loss": 3.073051929473877,
      "eval_rouge1": 29.5215,
      "eval_rouge2": 13.1839,
      "eval_rougeL": 25.617,
      "eval_runtime": 744.9289,
      "eval_samples_per_second": 6.049,
      "eval_steps_per_second": 0.605,
      "step": 43979
    },
    {
      "epoch": 13.00620750812888,
      "grad_norm": 5.098820686340332,
      "learning_rate": 6.645974972903735e-06,
      "loss": 1.5807,
      "step": 44000
    },
    {
      "epoch": 13.154005320721254,
      "grad_norm": 3.9083046913146973,
      "learning_rate": 6.153315597595822e-06,
      "loss": 1.562,
      "step": 44500
    },
    {
      "epoch": 13.301803133313626,
      "grad_norm": 4.274121284484863,
      "learning_rate": 5.66065622228791e-06,
      "loss": 1.5721,
      "step": 45000
    },
    {
      "epoch": 13.449600945906,
      "grad_norm": 4.222695827484131,
      "learning_rate": 5.167996846979999e-06,
      "loss": 1.5415,
      "step": 45500
    },
    {
      "epoch": 13.597398758498374,
      "grad_norm": 4.467597484588623,
      "learning_rate": 4.675337471672086e-06,
      "loss": 1.5718,
      "step": 46000
    },
    {
      "epoch": 13.745196571090748,
      "grad_norm": 4.109827995300293,
      "learning_rate": 4.182678096364174e-06,
      "loss": 1.5285,
      "step": 46500
    },
    {
      "epoch": 13.89299438368312,
      "grad_norm": 4.74594783782959,
      "learning_rate": 3.690018721056262e-06,
      "loss": 1.5215,
      "step": 47000
    },
    {
      "epoch": 14.0,
      "eval_loss": 3.0527069568634033,
      "eval_rouge1": 29.7103,
      "eval_rouge2": 13.2821,
      "eval_rougeL": 25.7681,
      "eval_runtime": 741.3618,
      "eval_samples_per_second": 6.078,
      "eval_steps_per_second": 0.608,
      "step": 47362
    },
    {
      "epoch": 14.040792196275495,
      "grad_norm": 4.313952922821045,
      "learning_rate": 1.4898019509311262e-05,
      "loss": 1.4804,
      "step": 47500
    },
    {
      "epoch": 14.18859000886787,
      "grad_norm": 4.262555122375488,
      "learning_rate": 1.4528524977830329e-05,
      "loss": 1.534,
      "step": 48000
    },
    {
      "epoch": 14.336387821460242,
      "grad_norm": 4.611397743225098,
      "learning_rate": 1.4159030446349395e-05,
      "loss": 1.5168,
      "step": 48500
    },
    {
      "epoch": 14.484185634052617,
      "grad_norm": 4.340530872344971,
      "learning_rate": 1.378953591486846e-05,
      "loss": 1.5254,
      "step": 49000
    },
    {
      "epoch": 14.63198344664499,
      "grad_norm": 4.0280375480651855,
      "learning_rate": 1.3420041383387528e-05,
      "loss": 1.5317,
      "step": 49500
    },
    {
      "epoch": 14.779781259237364,
      "grad_norm": 4.776717662811279,
      "learning_rate": 1.3050546851906593e-05,
      "loss": 1.5312,
      "step": 50000
    },
    {
      "epoch": 14.927579071829737,
      "grad_norm": 4.440686225891113,
      "learning_rate": 1.2681052320425657e-05,
      "loss": 1.5348,
      "step": 50500
    },
    {
      "epoch": 15.0,
      "eval_loss": 3.036102056503296,
      "eval_rouge1": 29.8805,
      "eval_rouge2": 13.4576,
      "eval_rougeL": 25.9729,
      "eval_runtime": 726.153,
      "eval_samples_per_second": 6.205,
      "eval_steps_per_second": 0.621,
      "step": 50745
    },
    {
      "epoch": 15.075376884422111,
      "grad_norm": 4.464206695556641,
      "learning_rate": 1.2311557788944725e-05,
      "loss": 1.4799,
      "step": 51000
    },
    {
      "epoch": 15.223174697014484,
      "grad_norm": 4.814591884613037,
      "learning_rate": 1.194206325746379e-05,
      "loss": 1.4313,
      "step": 51500
    },
    {
      "epoch": 15.370972509606858,
      "grad_norm": 3.8840887546539307,
      "learning_rate": 1.1572568725982856e-05,
      "loss": 1.458,
      "step": 52000
    },
    {
      "epoch": 15.51877032219923,
      "grad_norm": 4.051957130432129,
      "learning_rate": 1.1203074194501923e-05,
      "loss": 1.4723,
      "step": 52500
    },
    {
      "epoch": 15.666568134791605,
      "grad_norm": 4.178130626678467,
      "learning_rate": 1.0833579663020987e-05,
      "loss": 1.4597,
      "step": 53000
    },
    {
      "epoch": 15.814365947383978,
      "grad_norm": 4.45131254196167,
      "learning_rate": 1.0464085131540054e-05,
      "loss": 1.4332,
      "step": 53500
    },
    {
      "epoch": 15.962163759976352,
      "grad_norm": 4.57073974609375,
      "learning_rate": 1.009459060005912e-05,
      "loss": 1.4437,
      "step": 54000
    },
    {
      "epoch": 16.0,
      "eval_loss": 3.0735461711883545,
      "eval_rouge1": 29.9002,
      "eval_rouge2": 13.5403,
      "eval_rougeL": 26.0194,
      "eval_runtime": 722.6691,
      "eval_samples_per_second": 6.235,
      "eval_steps_per_second": 0.624,
      "step": 54128
    },
    {
      "epoch": 16.109961572568725,
      "grad_norm": 4.4488444328308105,
      "learning_rate": 9.725096068578185e-06,
      "loss": 1.3652,
      "step": 54500
    },
    {
      "epoch": 16.2577593851611,
      "grad_norm": 4.422569751739502,
      "learning_rate": 9.355601537097251e-06,
      "loss": 1.3663,
      "step": 55000
    },
    {
      "epoch": 16.405557197753474,
      "grad_norm": 4.383566379547119,
      "learning_rate": 8.986107005616317e-06,
      "loss": 1.3829,
      "step": 55500
    },
    {
      "epoch": 16.553355010345847,
      "grad_norm": 3.979015827178955,
      "learning_rate": 8.616612474135382e-06,
      "loss": 1.3908,
      "step": 56000
    },
    {
      "epoch": 16.70115282293822,
      "grad_norm": 4.212048530578613,
      "learning_rate": 8.247117942654448e-06,
      "loss": 1.3937,
      "step": 56500
    },
    {
      "epoch": 16.848950635530596,
      "grad_norm": 5.7812581062316895,
      "learning_rate": 7.877623411173515e-06,
      "loss": 1.3842,
      "step": 57000
    },
    {
      "epoch": 16.99674844812297,
      "grad_norm": 4.071883678436279,
      "learning_rate": 7.50812887969258e-06,
      "loss": 1.3967,
      "step": 57500
    },
    {
      "epoch": 17.0,
      "eval_loss": 3.1532084941864014,
      "eval_rouge1": 29.8426,
      "eval_rouge2": 13.3464,
      "eval_rougeL": 25.9413,
      "eval_runtime": 715.7403,
      "eval_samples_per_second": 6.296,
      "eval_steps_per_second": 0.63,
      "step": 57511
    }
  ],
  "logging_steps": 500,
  "max_steps": 67660,
  "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": 2.8774476037291622e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}