{
  "best_metric": 1.718157410621643,
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-42000",
  "epoch": 5.125815470643057,
  "global_step": 44000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "learning_rate": 0.0004659832246039143,
      "loss": 1.8699,
      "step": 2000
    },
    {
      "epoch": 0.23,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.925290377655787,
      "eval_bleu": 0.3545199637679763,
      "eval_f1": null,
      "eval_loss": 1.959277629852295,
      "eval_rouge1": 0.5633837391336356,
      "eval_rouge2": 0.34674934645388344,
      "eval_rougeL": 0.5064883659799413,
      "eval_rougeLsum": 0.5086541050813081,
      "eval_runtime": 133.1355,
      "eval_samples_per_second": 73.925,
      "eval_steps_per_second": 1.157,
      "step": 2000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009319664492078286,
      "loss": 1.5318,
      "step": 4000
    },
    {
      "epoch": 0.47,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9287383144911022,
      "eval_bleu": 0.37953656724001,
      "eval_f1": null,
      "eval_loss": 1.9824762344360352,
      "eval_rouge1": 0.5844859677476962,
      "eval_rouge2": 0.36581607147006445,
      "eval_rougeL": 0.5259486949820125,
      "eval_rougeLsum": 0.527845210467109,
      "eval_runtime": 119.611,
      "eval_samples_per_second": 82.283,
      "eval_steps_per_second": 1.288,
      "step": 4000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0009790552803256977,
      "loss": 1.4554,
      "step": 6000
    },
    {
      "epoch": 0.7,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9303612746835797,
      "eval_bleu": 0.38752191605471603,
      "eval_f1": null,
      "eval_loss": 1.8406306505203247,
      "eval_rouge1": 0.5927229059335931,
      "eval_rouge2": 0.38003492861574106,
      "eval_rougeL": 0.5346859072251302,
      "eval_rougeLsum": 0.5366150157714622,
      "eval_runtime": 119.2462,
      "eval_samples_per_second": 82.535,
      "eval_steps_per_second": 1.291,
      "step": 6000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0009545298474518076,
      "loss": 1.4072,
      "step": 8000
    },
    {
      "epoch": 0.93,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9313987933433873,
      "eval_bleu": 0.38894349752263974,
      "eval_f1": null,
      "eval_loss": 1.8335192203521729,
      "eval_rouge1": 0.5951490622955975,
      "eval_rouge2": 0.38132596191494406,
      "eval_rougeL": 0.5372774002496402,
      "eval_rougeLsum": 0.5390370987815991,
      "eval_runtime": 124.2778,
      "eval_samples_per_second": 79.194,
      "eval_steps_per_second": 1.239,
      "step": 8000
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0009300044145779173,
      "loss": 1.3591,
      "step": 10000
    },
    {
      "epoch": 1.16,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9315006548288609,
      "eval_bleu": 0.3865096435890867,
      "eval_f1": null,
      "eval_loss": 1.7958769798278809,
      "eval_rouge1": 0.6050046650220731,
      "eval_rouge2": 0.3969760699443571,
      "eval_rougeL": 0.5467681117587176,
      "eval_rougeLsum": 0.5491745425215071,
      "eval_runtime": 127.9598,
      "eval_samples_per_second": 76.915,
      "eval_steps_per_second": 1.204,
      "step": 10000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0009054789817040271,
      "loss": 1.3314,
      "step": 12000
    },
    {
      "epoch": 1.4,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9321439913486325,
      "eval_bleu": 0.40043826944150546,
      "eval_f1": null,
      "eval_loss": 1.8358908891677856,
      "eval_rouge1": 0.6033740241419494,
      "eval_rouge2": 0.3943871885637782,
      "eval_rougeL": 0.5446854297032411,
      "eval_rougeLsum": 0.5468056362503415,
      "eval_runtime": 123.4557,
      "eval_samples_per_second": 79.721,
      "eval_steps_per_second": 1.247,
      "step": 12000
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0008809535488301369,
      "loss": 1.322,
      "step": 14000
    },
    {
      "epoch": 1.63,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9318598681253477,
      "eval_bleu": 0.3901308120455454,
      "eval_f1": null,
      "eval_loss": 1.8139214515686035,
      "eval_rouge1": 0.6077021217894953,
      "eval_rouge2": 0.39737953301577167,
      "eval_rougeL": 0.5487431215145148,
      "eval_rougeLsum": 0.5508016845003574,
      "eval_runtime": 128.2981,
      "eval_samples_per_second": 76.712,
      "eval_steps_per_second": 1.2,
      "step": 14000
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0008564281159562467,
      "loss": 1.3046,
      "step": 16000
    },
    {
      "epoch": 1.86,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9335851898597426,
      "eval_bleu": 0.4074581189783245,
      "eval_f1": null,
      "eval_loss": 1.7547861337661743,
      "eval_rouge1": 0.6106875900448452,
      "eval_rouge2": 0.40481219032920934,
      "eval_rougeL": 0.5549309353470346,
      "eval_rougeLsum": 0.5570675429924621,
      "eval_runtime": 123.362,
      "eval_samples_per_second": 79.781,
      "eval_steps_per_second": 1.248,
      "step": 16000
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0008319026830823564,
      "loss": 1.2811,
      "step": 18000
    },
    {
      "epoch": 2.1,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9323258479783458,
      "eval_bleu": 0.3945938807031178,
      "eval_f1": null,
      "eval_loss": 1.8054404258728027,
      "eval_rouge1": 0.6125229180885745,
      "eval_rouge2": 0.40770947555297465,
      "eval_rougeL": 0.5571630795127507,
      "eval_rougeLsum": 0.5593601401592401,
      "eval_runtime": 130.5972,
      "eval_samples_per_second": 75.361,
      "eval_steps_per_second": 1.179,
      "step": 18000
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0008073772502084662,
      "loss": 1.2522,
      "step": 20000
    },
    {
      "epoch": 2.33,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9318601747725316,
      "eval_bleu": 0.3868721016074339,
      "eval_f1": null,
      "eval_loss": 1.764616847038269,
      "eval_rouge1": 0.6049734000636491,
      "eval_rouge2": 0.3941804569991841,
      "eval_rougeL": 0.5483693677450392,
      "eval_rougeLsum": 0.5501449485616742,
      "eval_runtime": 127.6902,
      "eval_samples_per_second": 77.077,
      "eval_steps_per_second": 1.206,
      "step": 20000
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.000782851817334576,
      "loss": 1.2499,
      "step": 22000
    },
    {
      "epoch": 2.56,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.931423125071294,
      "eval_bleu": 0.3902916555092431,
      "eval_f1": null,
      "eval_loss": 1.8007221221923828,
      "eval_rouge1": 0.6006911915544173,
      "eval_rouge2": 0.39035654600491987,
      "eval_rougeL": 0.5444104696749834,
      "eval_rougeLsum": 0.5462500361747902,
      "eval_runtime": 124.7647,
      "eval_samples_per_second": 78.884,
      "eval_steps_per_second": 1.234,
      "step": 22000
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0007583263844606856,
      "loss": 1.2518,
      "step": 24000
    },
    {
      "epoch": 2.8,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9337686031202891,
      "eval_bleu": 0.40558306708684894,
      "eval_f1": null,
      "eval_loss": 1.7533162832260132,
      "eval_rouge1": 0.6171082316570229,
      "eval_rouge2": 0.41294766957360146,
      "eval_rougeL": 0.5605456269621005,
      "eval_rougeLsum": 0.5627524417212678,
      "eval_runtime": 126.2473,
      "eval_samples_per_second": 77.958,
      "eval_steps_per_second": 1.22,
      "step": 24000
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0007338009515867955,
      "loss": 1.2371,
      "step": 26000
    },
    {
      "epoch": 3.03,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9339726343069636,
      "eval_bleu": 0.40189250216565836,
      "eval_f1": null,
      "eval_loss": 1.7669899463653564,
      "eval_rouge1": 0.6127257914599264,
      "eval_rouge2": 0.40628759904088707,
      "eval_rougeL": 0.5562894564458545,
      "eval_rougeLsum": 0.5582640573742271,
      "eval_runtime": 126.8636,
      "eval_samples_per_second": 77.579,
      "eval_steps_per_second": 1.214,
      "step": 26000
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0007092755187129053,
      "loss": 1.2049,
      "step": 28000
    },
    {
      "epoch": 3.26,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9329962301511053,
      "eval_bleu": 0.4018379705338028,
      "eval_f1": null,
      "eval_loss": 1.7540892362594604,
      "eval_rouge1": 0.6126118264923794,
      "eval_rouge2": 0.401721192722568,
      "eval_rougeL": 0.5560492232539358,
      "eval_rougeLsum": 0.5578878696736621,
      "eval_runtime": 127.0162,
      "eval_samples_per_second": 77.486,
      "eval_steps_per_second": 1.212,
      "step": 28000
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0006847500858390151,
      "loss": 1.2022,
      "step": 30000
    },
    {
      "epoch": 3.49,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9332761396675715,
      "eval_bleu": 0.40081654671926936,
      "eval_f1": null,
      "eval_loss": 1.7528060674667358,
      "eval_rouge1": 0.6126150736720647,
      "eval_rouge2": 0.4040778291827031,
      "eval_rougeL": 0.5534874799735049,
      "eval_rougeLsum": 0.5555363649376426,
      "eval_runtime": 129.054,
      "eval_samples_per_second": 76.263,
      "eval_steps_per_second": 1.193,
      "step": 30000
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0006602246529651248,
      "loss": 1.2035,
      "step": 32000
    },
    {
      "epoch": 3.73,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9329427619807436,
      "eval_bleu": 0.39769307763442124,
      "eval_f1": null,
      "eval_loss": 1.726220726966858,
      "eval_rouge1": 0.6151881785872779,
      "eval_rouge2": 0.4071357730525864,
      "eval_rougeL": 0.5581296316289542,
      "eval_rougeLsum": 0.5599612741043438,
      "eval_runtime": 128.7277,
      "eval_samples_per_second": 76.456,
      "eval_steps_per_second": 1.196,
      "step": 32000
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0006356992200912346,
      "loss": 1.2025,
      "step": 34000
    },
    {
      "epoch": 3.96,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9327217574600184,
      "eval_bleu": 0.39532580118131083,
      "eval_f1": null,
      "eval_loss": 1.7384415864944458,
      "eval_rouge1": 0.6151113892112338,
      "eval_rouge2": 0.4060270300193623,
      "eval_rougeL": 0.5568165666491858,
      "eval_rougeLsum": 0.5588803581261892,
      "eval_runtime": 127.62,
      "eval_samples_per_second": 77.12,
      "eval_steps_per_second": 1.207,
      "step": 34000
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0006111737872173444,
      "loss": 1.1673,
      "step": 36000
    },
    {
      "epoch": 4.19,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9335783984609746,
      "eval_bleu": 0.40091900271325864,
      "eval_f1": null,
      "eval_loss": 1.733450174331665,
      "eval_rouge1": 0.6145618299704365,
      "eval_rouge2": 0.4081499359458297,
      "eval_rougeL": 0.5577521621232591,
      "eval_rougeLsum": 0.5597557085924665,
      "eval_runtime": 124.8207,
      "eval_samples_per_second": 78.849,
      "eval_steps_per_second": 1.234,
      "step": 36000
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0005866483543434542,
      "loss": 1.1623,
      "step": 38000
    },
    {
      "epoch": 4.43,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9334935503286018,
      "eval_bleu": 0.4019902251412491,
      "eval_f1": null,
      "eval_loss": 1.7328290939331055,
      "eval_rouge1": 0.6131765183291862,
      "eval_rouge2": 0.4016827316456552,
      "eval_rougeL": 0.5554221776720798,
      "eval_rougeLsum": 0.5570871691893517,
      "eval_runtime": 120.9799,
      "eval_samples_per_second": 81.352,
      "eval_steps_per_second": 1.273,
      "step": 38000
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0005621229214695639,
      "loss": 1.165,
      "step": 40000
    },
    {
      "epoch": 4.66,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9347834876762903,
      "eval_bleu": 0.41110556909183305,
      "eval_f1": null,
      "eval_loss": 1.7455238103866577,
      "eval_rouge1": 0.6222414096206548,
      "eval_rouge2": 0.41303505089517123,
      "eval_rougeL": 0.5654989953242198,
      "eval_rougeLsum": 0.5674212008550099,
      "eval_runtime": 122.4394,
      "eval_samples_per_second": 80.383,
      "eval_steps_per_second": 1.258,
      "step": 40000
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0005375974885956737,
      "loss": 1.1674,
      "step": 42000
    },
    {
      "epoch": 4.89,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9342498932154143,
      "eval_bleu": 0.4057773557512404,
      "eval_f1": null,
      "eval_loss": 1.718157410621643,
      "eval_rouge1": 0.6173759208611083,
      "eval_rouge2": 0.4116919174551955,
      "eval_rougeL": 0.5609282546294716,
      "eval_rougeLsum": 0.5629408116210994,
      "eval_runtime": 126.5334,
      "eval_samples_per_second": 77.782,
      "eval_steps_per_second": 1.217,
      "step": 42000
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0005130720557217835,
      "loss": 1.1438,
      "step": 44000
    },
    {
      "epoch": 5.13,
      "eval_accuracy": null,
      "eval_bertscore_f1": 0.9344984365233898,
      "eval_bleu": 0.40721752035612685,
      "eval_f1": null,
      "eval_loss": 1.7338136434555054,
      "eval_rouge1": 0.6163319555760827,
      "eval_rouge2": 0.4104974025783942,
      "eval_rougeL": 0.560882495272792,
      "eval_rougeLsum": 0.5632657540547901,
      "eval_runtime": 123.093,
      "eval_samples_per_second": 79.956,
      "eval_steps_per_second": 1.251,
      "step": 44000
    }
  ],
  "max_steps": 85840,
  "num_train_epochs": 10,
  "total_flos": 4.392879598111949e+16,
  "trial_name": null,
  "trial_params": null
}