| { | |
| "best_metric": 1.7131295204162598, | |
| "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000", | |
| "epoch": 8.387698042870456, | |
| "global_step": 72000, | |
| "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 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 0.0004885466228478932, | |
| "loss": 1.1271, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9343265120005904, | |
| "eval_bleu": 0.4107679859085796, | |
| "eval_f1": null, | |
| "eval_loss": 1.7594177722930908, | |
| "eval_rouge1": 0.6214337711077422, | |
| "eval_rouge2": 0.415499095864183, | |
| "eval_rougeL": 0.5634811122039034, | |
| "eval_rougeLsum": 0.565609388415719, | |
| "eval_runtime": 148.0927, | |
| "eval_samples_per_second": 66.458, | |
| "eval_steps_per_second": 1.04, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.00046402118997400306, | |
| "loss": 1.1347, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9346181902246392, | |
| "eval_bleu": 0.41025657015747313, | |
| "eval_f1": null, | |
| "eval_loss": 1.7323421239852905, | |
| "eval_rouge1": 0.6202134304651805, | |
| "eval_rouge2": 0.41367504192967947, | |
| "eval_rougeL": 0.563684952549099, | |
| "eval_rougeLsum": 0.5657342582828795, | |
| "eval_runtime": 141.36, | |
| "eval_samples_per_second": 69.624, | |
| "eval_steps_per_second": 1.089, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.0004394957571001128, | |
| "loss": 1.1324, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9344481716817822, | |
| "eval_bleu": 0.4110716343495672, | |
| "eval_f1": null, | |
| "eval_loss": 1.7247016429901123, | |
| "eval_rouge1": 0.6206955757960952, | |
| "eval_rouge2": 0.4147409191504623, | |
| "eval_rougeL": 0.5632791739699408, | |
| "eval_rougeLsum": 0.565299463519248, | |
| "eval_runtime": 141.5482, | |
| "eval_samples_per_second": 69.531, | |
| "eval_steps_per_second": 1.088, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.0004149703242262226, | |
| "loss": 1.1232, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9342022908821602, | |
| "eval_bleu": 0.40558909867684073, | |
| "eval_f1": null, | |
| "eval_loss": 1.7131295204162598, | |
| "eval_rouge1": 0.617381846208605, | |
| "eval_rouge2": 0.4075391372025301, | |
| "eval_rougeL": 0.5593319238191912, | |
| "eval_rougeLsum": 0.5613898662787742, | |
| "eval_runtime": 141.3568, | |
| "eval_samples_per_second": 69.625, | |
| "eval_steps_per_second": 1.089, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.0003904448913523324, | |
| "loss": 1.099, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9344165326315463, | |
| "eval_bleu": 0.4117161078695893, | |
| "eval_f1": null, | |
| "eval_loss": 1.7616441249847412, | |
| "eval_rouge1": 0.6196071982260033, | |
| "eval_rouge2": 0.41061524172454117, | |
| "eval_rougeL": 0.5611350900753369, | |
| "eval_rougeLsum": 0.5630504417819058, | |
| "eval_runtime": 140.5199, | |
| "eval_samples_per_second": 70.04, | |
| "eval_steps_per_second": 1.096, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 0.00036591945847844215, | |
| "loss": 1.1034, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9348069845879133, | |
| "eval_bleu": 0.4108533042307904, | |
| "eval_f1": null, | |
| "eval_loss": 1.7296594381332397, | |
| "eval_rouge1": 0.6208000465641403, | |
| "eval_rouge2": 0.4153571257641863, | |
| "eval_rougeL": 0.5634391781002251, | |
| "eval_rougeLsum": 0.5653490268367348, | |
| "eval_runtime": 144.1405, | |
| "eval_samples_per_second": 68.281, | |
| "eval_steps_per_second": 1.068, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.0003413940256045519, | |
| "loss": 1.1021, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9347718441130257, | |
| "eval_bleu": 0.4145601483938376, | |
| "eval_f1": null, | |
| "eval_loss": 1.7501702308654785, | |
| "eval_rouge1": 0.6220518407228575, | |
| "eval_rouge2": 0.41616106256237295, | |
| "eval_rougeL": 0.5653493806262004, | |
| "eval_rougeLsum": 0.5674926448995362, | |
| "eval_runtime": 143.3032, | |
| "eval_samples_per_second": 68.68, | |
| "eval_steps_per_second": 1.075, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0003168685927306617, | |
| "loss": 1.1028, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9349691032866738, | |
| "eval_bleu": 0.4172329212718154, | |
| "eval_f1": null, | |
| "eval_loss": 1.7387073040008545, | |
| "eval_rouge1": 0.6208100385324387, | |
| "eval_rouge2": 0.41548384315009723, | |
| "eval_rougeL": 0.5641532320511615, | |
| "eval_rougeLsum": 0.5660333813467002, | |
| "eval_runtime": 142.0461, | |
| "eval_samples_per_second": 69.287, | |
| "eval_steps_per_second": 1.084, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.00029234315985677146, | |
| "loss": 1.0711, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9346298167519491, | |
| "eval_bleu": 0.40834821818709055, | |
| "eval_f1": null, | |
| "eval_loss": 1.7485404014587402, | |
| "eval_rouge1": 0.6197656710094954, | |
| "eval_rouge2": 0.41278766530342237, | |
| "eval_rougeL": 0.5630552402252382, | |
| "eval_rougeLsum": 0.5650759439058759, | |
| "eval_runtime": 146.6193, | |
| "eval_samples_per_second": 67.126, | |
| "eval_steps_per_second": 1.05, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 0.0002678177269828813, | |
| "loss": 1.0755, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9339887901089875, | |
| "eval_bleu": 0.4076539996327793, | |
| "eval_f1": null, | |
| "eval_loss": 1.752874732017517, | |
| "eval_rouge1": 0.6144795036298025, | |
| "eval_rouge2": 0.4050923100648689, | |
| "eval_rougeL": 0.5573353646470276, | |
| "eval_rougeLsum": 0.5593645460867931, | |
| "eval_runtime": 141.9841, | |
| "eval_samples_per_second": 69.318, | |
| "eval_steps_per_second": 1.085, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00024329229410899103, | |
| "loss": 1.0723, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9346891578390598, | |
| "eval_bleu": 0.4112701971087721, | |
| "eval_f1": null, | |
| "eval_loss": 1.741502046585083, | |
| "eval_rouge1": 0.6224682653237195, | |
| "eval_rouge2": 0.4152409831528609, | |
| "eval_rougeL": 0.5646046534183624, | |
| "eval_rougeLsum": 0.5666606650250839, | |
| "eval_runtime": 142.1817, | |
| "eval_samples_per_second": 69.221, | |
| "eval_steps_per_second": 1.083, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 0.0002187668612351008, | |
| "loss": 1.0751, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9340490757014009, | |
| "eval_bleu": 0.40620204839955465, | |
| "eval_f1": null, | |
| "eval_loss": 1.7554686069488525, | |
| "eval_rouge1": 0.6164376145373307, | |
| "eval_rouge2": 0.40876980632820026, | |
| "eval_rougeL": 0.5595624559170196, | |
| "eval_rougeLsum": 0.5614936851444701, | |
| "eval_runtime": 141.9779, | |
| "eval_samples_per_second": 69.321, | |
| "eval_steps_per_second": 1.085, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 0.0001942414283612106, | |
| "loss": 1.053, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9347367377463842, | |
| "eval_bleu": 0.4099625767370798, | |
| "eval_f1": null, | |
| "eval_loss": 1.767859935760498, | |
| "eval_rouge1": 0.6194533859109013, | |
| "eval_rouge2": 0.4117428622305384, | |
| "eval_rougeL": 0.5620848425359636, | |
| "eval_rougeLsum": 0.5640752528686849, | |
| "eval_runtime": 142.9599, | |
| "eval_samples_per_second": 68.844, | |
| "eval_steps_per_second": 1.077, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.00016971599548732037, | |
| "loss": 1.0488, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "eval_accuracy": null, | |
| "eval_bertscore_f1": 0.9345181620816249, | |
| "eval_bleu": 0.4124889872953633, | |
| "eval_f1": null, | |
| "eval_loss": 1.7536756992340088, | |
| "eval_rouge1": 0.6217065929610754, | |
| "eval_rouge2": 0.4146562066585521, | |
| "eval_rougeL": 0.5638042099155474, | |
| "eval_rougeLsum": 0.5658427165750861, | |
| "eval_runtime": 141.3859, | |
| "eval_samples_per_second": 69.611, | |
| "eval_steps_per_second": 1.089, | |
| "step": 72000 | |
| } | |
| ], | |
| "max_steps": 85840, | |
| "num_train_epochs": 10, | |
| "total_flos": 7.189532808609792e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |