| { | |
| "best_metric": 0.8108949416342413, | |
| "best_model_checkpoint": "finetune_results/omarmomen/structformer_s2_final_with_pos/qqp/checkpoint-10000", | |
| "epoch": 5.911330049261084, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.7234556674957275, | |
| "eval_f1": 0.6753688989784338, | |
| "eval_loss": 0.5372109413146973, | |
| "eval_mcc": 0.4346909424161479, | |
| "eval_runtime": 51.7649, | |
| "eval_samples_per_second": 519.444, | |
| "eval_steps_per_second": 64.947, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.876847290640394e-05, | |
| "loss": 0.5934, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.7503811717033386, | |
| "eval_f1": 0.7230337542295948, | |
| "eval_loss": 0.5017327070236206, | |
| "eval_mcc": 0.5014557368856788, | |
| "eval_runtime": 51.7433, | |
| "eval_samples_per_second": 519.661, | |
| "eval_steps_per_second": 64.975, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.753694581280788e-05, | |
| "loss": 0.5159, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.7581911087036133, | |
| "eval_f1": 0.7443579460564599, | |
| "eval_loss": 0.48863014578819275, | |
| "eval_mcc": 0.5320171029709727, | |
| "eval_runtime": 51.7388, | |
| "eval_samples_per_second": 519.707, | |
| "eval_steps_per_second": 64.98, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.630541871921182e-05, | |
| "loss": 0.4792, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.7796124815940857, | |
| "eval_f1": 0.7622944243882872, | |
| "eval_loss": 0.4617643356323242, | |
| "eval_mcc": 0.5687201331096594, | |
| "eval_runtime": 51.762, | |
| "eval_samples_per_second": 519.474, | |
| "eval_steps_per_second": 64.951, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.507389162561577e-05, | |
| "loss": 0.4542, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.789095938205719, | |
| "eval_f1": 0.7523039965057874, | |
| "eval_loss": 0.44058433175086975, | |
| "eval_mcc": 0.5688664310414974, | |
| "eval_runtime": 51.7652, | |
| "eval_samples_per_second": 519.442, | |
| "eval_steps_per_second": 64.947, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.792219877243042, | |
| "eval_f1": 0.7745268170628354, | |
| "eval_loss": 0.4416797161102295, | |
| "eval_mcc": 0.59239707340152, | |
| "eval_runtime": 51.7802, | |
| "eval_samples_per_second": 519.291, | |
| "eval_steps_per_second": 64.928, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.384236453201971e-05, | |
| "loss": 0.3933, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.7879801988601685, | |
| "eval_f1": 0.7779206108059679, | |
| "eval_loss": 0.45901182293891907, | |
| "eval_mcc": 0.5959266879901132, | |
| "eval_runtime": 51.7681, | |
| "eval_samples_per_second": 519.412, | |
| "eval_steps_per_second": 64.943, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.261083743842365e-05, | |
| "loss": 0.3802, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_accuracy": 0.8091784715652466, | |
| "eval_f1": 0.7775995838931992, | |
| "eval_loss": 0.41946539282798767, | |
| "eval_mcc": 0.6110078146235389, | |
| "eval_runtime": 51.7792, | |
| "eval_samples_per_second": 519.301, | |
| "eval_steps_per_second": 64.93, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.3713, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.8115586042404175, | |
| "eval_f1": 0.7876629091061476, | |
| "eval_loss": 0.4056394398212433, | |
| "eval_mcc": 0.6219198677315879, | |
| "eval_runtime": 51.7731, | |
| "eval_samples_per_second": 519.362, | |
| "eval_steps_per_second": 64.937, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.014778325123153e-05, | |
| "loss": 0.3679, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.8167652487754822, | |
| "eval_f1": 0.7969168624541445, | |
| "eval_loss": 0.40430837869644165, | |
| "eval_mcc": 0.6363171595176773, | |
| "eval_runtime": 51.7659, | |
| "eval_samples_per_second": 519.434, | |
| "eval_steps_per_second": 64.946, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.8047528862953186, | |
| "eval_f1": 0.7935509241053873, | |
| "eval_loss": 0.45002058148384094, | |
| "eval_mcc": 0.6264120987418264, | |
| "eval_runtime": 51.7934, | |
| "eval_samples_per_second": 519.159, | |
| "eval_steps_per_second": 64.912, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.891625615763547e-05, | |
| "loss": 0.2934, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_accuracy": 0.8004016280174255, | |
| "eval_f1": 0.7906541326988337, | |
| "eval_loss": 0.4479910731315613, | |
| "eval_mcc": 0.6206352234514999, | |
| "eval_runtime": 51.7752, | |
| "eval_samples_per_second": 519.341, | |
| "eval_steps_per_second": 64.935, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.768472906403941e-05, | |
| "loss": 0.2895, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.8060173392295837, | |
| "eval_f1": 0.7936219039328954, | |
| "eval_loss": 0.4439913034439087, | |
| "eval_mcc": 0.6267733245835018, | |
| "eval_runtime": 51.7787, | |
| "eval_samples_per_second": 519.306, | |
| "eval_steps_per_second": 64.93, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.645320197044335e-05, | |
| "loss": 0.2901, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.8209676742553711, | |
| "eval_f1": 0.8036864856047631, | |
| "eval_loss": 0.4141245186328888, | |
| "eval_mcc": 0.6476398578041523, | |
| "eval_runtime": 51.7588, | |
| "eval_samples_per_second": 519.505, | |
| "eval_steps_per_second": 64.955, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.522167487684729e-05, | |
| "loss": 0.2882, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.8188106417655945, | |
| "eval_f1": 0.8016609672691744, | |
| "eval_loss": 0.4020179808139801, | |
| "eval_mcc": 0.643743269882208, | |
| "eval_runtime": 51.7887, | |
| "eval_samples_per_second": 519.206, | |
| "eval_steps_per_second": 64.918, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_accuracy": 0.8268436789512634, | |
| "eval_f1": 0.8052534716412916, | |
| "eval_loss": 0.47344014048576355, | |
| "eval_mcc": 0.6533536137012623, | |
| "eval_runtime": 51.8108, | |
| "eval_samples_per_second": 518.985, | |
| "eval_steps_per_second": 64.89, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.399014778325123e-05, | |
| "loss": 0.2247, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_accuracy": 0.8171743154525757, | |
| "eval_f1": 0.8004546192563728, | |
| "eval_loss": 0.47986865043640137, | |
| "eval_mcc": 0.6412550092053579, | |
| "eval_runtime": 51.7925, | |
| "eval_samples_per_second": 519.168, | |
| "eval_steps_per_second": 64.913, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.275862068965517e-05, | |
| "loss": 0.2198, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_accuracy": 0.8249841928482056, | |
| "eval_f1": 0.8056656755863892, | |
| "eval_loss": 0.44043195247650146, | |
| "eval_mcc": 0.6525207506387493, | |
| "eval_runtime": 51.8061, | |
| "eval_samples_per_second": 519.032, | |
| "eval_steps_per_second": 64.896, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.152709359605912e-05, | |
| "loss": 0.2178, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.825653612613678, | |
| "eval_f1": 0.8072685413583294, | |
| "eval_loss": 0.4325750470161438, | |
| "eval_mcc": 0.6549889472807147, | |
| "eval_runtime": 51.7769, | |
| "eval_samples_per_second": 519.324, | |
| "eval_steps_per_second": 64.932, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.0295566502463057e-05, | |
| "loss": 0.2234, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.8143478631973267, | |
| "eval_f1": 0.8024222274994064, | |
| "eval_loss": 0.46264368295669556, | |
| "eval_mcc": 0.643552030907142, | |
| "eval_runtime": 51.7905, | |
| "eval_samples_per_second": 519.188, | |
| "eval_steps_per_second": 64.915, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_accuracy": 0.8114470839500427, | |
| "eval_f1": 0.7995096488453021, | |
| "eval_loss": 0.5472643375396729, | |
| "eval_mcc": 0.6379765063766293, | |
| "eval_runtime": 51.7718, | |
| "eval_samples_per_second": 519.375, | |
| "eval_steps_per_second": 64.939, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 2.9064039408866993e-05, | |
| "loss": 0.1747, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_accuracy": 0.8158354759216309, | |
| "eval_f1": 0.801172408255039, | |
| "eval_loss": 0.5199980735778809, | |
| "eval_mcc": 0.6418079417002838, | |
| "eval_runtime": 51.8043, | |
| "eval_samples_per_second": 519.049, | |
| "eval_steps_per_second": 64.898, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.7832512315270936e-05, | |
| "loss": 0.1652, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_accuracy": 0.8288519382476807, | |
| "eval_f1": 0.8095040980213594, | |
| "eval_loss": 0.4734426736831665, | |
| "eval_mcc": 0.6597842225635926, | |
| "eval_runtime": 51.7806, | |
| "eval_samples_per_second": 519.287, | |
| "eval_steps_per_second": 64.928, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.660098522167488e-05, | |
| "loss": 0.1639, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_accuracy": 0.8255420327186584, | |
| "eval_f1": 0.809083879369989, | |
| "eval_loss": 0.5020354390144348, | |
| "eval_mcc": 0.657461047074956, | |
| "eval_runtime": 51.784, | |
| "eval_samples_per_second": 519.253, | |
| "eval_steps_per_second": 64.924, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.5369458128078822e-05, | |
| "loss": 0.1684, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "eval_accuracy": 0.8282940983772278, | |
| "eval_f1": 0.8108949416342413, | |
| "eval_loss": 0.4710612893104553, | |
| "eval_mcc": 0.6613084269281064, | |
| "eval_runtime": 51.7629, | |
| "eval_samples_per_second": 519.465, | |
| "eval_steps_per_second": 64.95, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_accuracy": 0.8276618719100952, | |
| "eval_f1": 0.8096450870851134, | |
| "eval_loss": 0.5808185338973999, | |
| "eval_mcc": 0.6592695922742537, | |
| "eval_runtime": 51.8111, | |
| "eval_samples_per_second": 518.982, | |
| "eval_steps_per_second": 64.89, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.413793103448276e-05, | |
| "loss": 0.1323, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_accuracy": 0.8322362303733826, | |
| "eval_f1": 0.8096222831821059, | |
| "eval_loss": 0.5204941034317017, | |
| "eval_mcc": 0.6624782529759075, | |
| "eval_runtime": 51.8048, | |
| "eval_samples_per_second": 519.045, | |
| "eval_steps_per_second": 64.897, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.29064039408867e-05, | |
| "loss": 0.1216, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_accuracy": 0.8215999007225037, | |
| "eval_f1": 0.8064555174500707, | |
| "eval_loss": 0.5831347703933716, | |
| "eval_mcc": 0.651990774420572, | |
| "eval_runtime": 51.808, | |
| "eval_samples_per_second": 519.013, | |
| "eval_steps_per_second": 64.893, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 2.1674876847290644e-05, | |
| "loss": 0.1237, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_accuracy": 0.8242031931877136, | |
| "eval_f1": 0.8080250172602851, | |
| "eval_loss": 0.6121179461479187, | |
| "eval_mcc": 0.6553446821187937, | |
| "eval_runtime": 51.8296, | |
| "eval_samples_per_second": 518.797, | |
| "eval_steps_per_second": 64.866, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2.0443349753694584e-05, | |
| "loss": 0.1248, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_accuracy": 0.8253932595252991, | |
| "eval_f1": 0.805871407897457, | |
| "eval_loss": 0.6064007878303528, | |
| "eval_mcc": 0.6530389230916024, | |
| "eval_runtime": 51.78, | |
| "eval_samples_per_second": 519.293, | |
| "eval_steps_per_second": 64.928, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "step": 12000, | |
| "total_flos": 1.2015943752264192e+17, | |
| "train_loss": 0.28238233852386474, | |
| "train_runtime": 8038.3604, | |
| "train_samples_per_second": 302.92, | |
| "train_steps_per_second": 2.525 | |
| } | |
| ], | |
| "max_steps": 20300, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.2015943752264192e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |