| { | |
| "best_metric": 0.96593837535014, | |
| "best_model_checkpoint": "../output/bert-base-uncased-yelp_bin/checkpoint-3500", | |
| "epoch": 0.20019447463250015, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.9071428571428571, | |
| "eval_f1": 0.907100199071002, | |
| "eval_loss": 0.2581118941307068, | |
| "eval_precision": 0.9072309595785661, | |
| "eval_recall": 0.9081054824813692, | |
| "eval_runtime": 2.7939, | |
| "eval_samples_per_second": 200.435, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.8892857142857142, | |
| "eval_f1": 0.8868598391532736, | |
| "eval_loss": 0.3021739721298218, | |
| "eval_precision": 0.908363774630291, | |
| "eval_recall": 0.8843936546893175, | |
| "eval_runtime": 2.8003, | |
| "eval_samples_per_second": 199.98, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.9160714285714285, | |
| "eval_f1": 0.9160647373036754, | |
| "eval_loss": 0.2224453091621399, | |
| "eval_precision": 0.9192965828167426, | |
| "eval_recall": 0.9184658255678695, | |
| "eval_runtime": 2.8002, | |
| "eval_samples_per_second": 199.989, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.9232142857142858, | |
| "eval_f1": 0.922669569769197, | |
| "eval_loss": 0.1851794272661209, | |
| "eval_precision": 0.9266868624100254, | |
| "eval_recall": 0.9213035753090207, | |
| "eval_runtime": 2.8015, | |
| "eval_samples_per_second": 199.89, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.942801578676429e-05, | |
| "loss": 0.2853, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.9232142857142858, | |
| "eval_f1": 0.9232081639161285, | |
| "eval_loss": 0.17731928825378418, | |
| "eval_precision": 0.9242238562091503, | |
| "eval_recall": 0.9247932405312472, | |
| "eval_runtime": 2.805, | |
| "eval_samples_per_second": 199.641, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.9375, | |
| "eval_f1": 0.9374119856047567, | |
| "eval_loss": 0.1572866588830948, | |
| "eval_precision": 0.9371936274509804, | |
| "eval_recall": 0.937780419526786, | |
| "eval_runtime": 2.8024, | |
| "eval_samples_per_second": 199.83, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.9375, | |
| "eval_f1": 0.9370177924736262, | |
| "eval_loss": 0.1771181970834732, | |
| "eval_precision": 0.9418188420834197, | |
| "eval_recall": 0.9354539760453018, | |
| "eval_runtime": 2.8029, | |
| "eval_samples_per_second": 199.79, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_f1": 0.9278499278499278, | |
| "eval_loss": 0.19192437827587128, | |
| "eval_precision": 0.9352719102297815, | |
| "eval_recall": 0.9259245056307601, | |
| "eval_runtime": 2.8042, | |
| "eval_samples_per_second": 199.7, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.9410714285714286, | |
| "eval_f1": 0.9410035148879929, | |
| "eval_loss": 0.1547766625881195, | |
| "eval_precision": 0.9407763769077637, | |
| "eval_recall": 0.941525737878846, | |
| "eval_runtime": 2.8036, | |
| "eval_samples_per_second": 199.741, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8856031573528572e-05, | |
| "loss": 0.1949, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9482142857142857, | |
| "eval_f1": 0.9480551050892563, | |
| "eval_loss": 0.14137934148311615, | |
| "eval_precision": 0.9485757467083356, | |
| "eval_recall": 0.9476869783078319, | |
| "eval_runtime": 2.8033, | |
| "eval_samples_per_second": 199.761, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_f1": 0.9428214062360404, | |
| "eval_loss": 0.14555300772190094, | |
| "eval_precision": 0.9427798823964592, | |
| "eval_recall": 0.9437307461236595, | |
| "eval_runtime": 2.8027, | |
| "eval_samples_per_second": 199.809, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.9535714285714286, | |
| "eval_f1": 0.9533787591577437, | |
| "eval_loss": 0.13459965586662292, | |
| "eval_precision": 0.95473282736834, | |
| "eval_recall": 0.9526402576983548, | |
| "eval_runtime": 2.8033, | |
| "eval_samples_per_second": 199.763, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.925, | |
| "eval_f1": 0.9239435526639158, | |
| "eval_loss": 0.19309227168560028, | |
| "eval_precision": 0.9362357952666323, | |
| "eval_recall": 0.9215144891411333, | |
| "eval_runtime": 2.8036, | |
| "eval_samples_per_second": 199.744, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.95, | |
| "eval_f1": 0.9497687053908944, | |
| "eval_loss": 0.14192207157611847, | |
| "eval_precision": 0.9515268402442945, | |
| "eval_recall": 0.948894939346295, | |
| "eval_runtime": 2.8032, | |
| "eval_samples_per_second": 199.768, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.828404736029286e-05, | |
| "loss": 0.1747, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.95, | |
| "eval_f1": 0.9497435897435897, | |
| "eval_loss": 0.13348396122455597, | |
| "eval_precision": 0.9519640535077443, | |
| "eval_recall": 0.9487287648119032, | |
| "eval_runtime": 2.8033, | |
| "eval_samples_per_second": 199.761, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.9535714285714286, | |
| "eval_f1": 0.9533787591577437, | |
| "eval_loss": 0.15492305159568787, | |
| "eval_precision": 0.95473282736834, | |
| "eval_recall": 0.9526402576983548, | |
| "eval_runtime": 2.8024, | |
| "eval_samples_per_second": 199.83, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.9517857142857142, | |
| "eval_f1": 0.9515966386554622, | |
| "eval_loss": 0.12274421751499176, | |
| "eval_precision": 0.9527568150315725, | |
| "eval_recall": 0.9509337730567167, | |
| "eval_runtime": 2.8039, | |
| "eval_samples_per_second": 199.723, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.95, | |
| "eval_f1": 0.9496603356833737, | |
| "eval_loss": 0.15004612505435944, | |
| "eval_precision": 0.9535641758611323, | |
| "eval_recall": 0.948230241208728, | |
| "eval_runtime": 2.8029, | |
| "eval_samples_per_second": 199.79, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.9482142857142857, | |
| "eval_f1": 0.9481413595010841, | |
| "eval_loss": 0.14852674305438995, | |
| "eval_precision": 0.9479166666666667, | |
| "eval_recall": 0.9485178509797907, | |
| "eval_runtime": 2.803, | |
| "eval_samples_per_second": 199.789, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7712063147057142e-05, | |
| "loss": 0.1688, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.9303571428571429, | |
| "eval_f1": 0.9303515905285817, | |
| "eval_loss": 0.15722833573818207, | |
| "eval_precision": 0.9313725490196079, | |
| "eval_recall": 0.9319515281665836, | |
| "eval_runtime": 2.8087, | |
| "eval_samples_per_second": 199.379, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_f1": 0.9569230769230769, | |
| "eval_loss": 0.12534742057323456, | |
| "eval_precision": 0.9591739516679327, | |
| "eval_recall": 0.9558870524472396, | |
| "eval_runtime": 2.8059, | |
| "eval_samples_per_second": 199.582, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.9517857142857142, | |
| "eval_f1": 0.9514723581802134, | |
| "eval_loss": 0.13627249002456665, | |
| "eval_precision": 0.9550765095119934, | |
| "eval_recall": 0.950102900384758, | |
| "eval_runtime": 2.8027, | |
| "eval_samples_per_second": 199.804, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.9553571428571429, | |
| "eval_f1": 0.9552679926511702, | |
| "eval_loss": 0.12657539546489716, | |
| "eval_precision": 0.9551983234512369, | |
| "eval_recall": 0.9553437895463435, | |
| "eval_runtime": 2.8014, | |
| "eval_samples_per_second": 199.901, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9482142857142857, | |
| "eval_f1": 0.9480338292092119, | |
| "eval_loss": 0.12863141298294067, | |
| "eval_precision": 0.9488461538461539, | |
| "eval_recall": 0.9475208037734402, | |
| "eval_runtime": 2.8027, | |
| "eval_samples_per_second": 199.809, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7140078933821426e-05, | |
| "loss": 0.165, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9357142857142857, | |
| "eval_f1": 0.9357011635027557, | |
| "eval_loss": 0.1396503895521164, | |
| "eval_precision": 0.9362679425837321, | |
| "eval_recall": 0.9370709820914982, | |
| "eval_runtime": 2.8041, | |
| "eval_samples_per_second": 199.709, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_f1": 0.9570024570024569, | |
| "eval_loss": 0.11459986865520477, | |
| "eval_precision": 0.9576750086495214, | |
| "eval_recall": 0.9565517505848065, | |
| "eval_runtime": 2.8039, | |
| "eval_samples_per_second": 199.72, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.9589285714285715, | |
| "eval_f1": 0.9588591725199715, | |
| "eval_loss": 0.11520295590162277, | |
| "eval_precision": 0.9586845466155811, | |
| "eval_recall": 0.9590891078984034, | |
| "eval_runtime": 2.8102, | |
| "eval_samples_per_second": 199.272, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.95, | |
| "eval_f1": 0.9498919865526454, | |
| "eval_loss": 0.11789484322071075, | |
| "eval_precision": 0.9498919865526454, | |
| "eval_recall": 0.9498919865526454, | |
| "eval_runtime": 2.8046, | |
| "eval_samples_per_second": 199.675, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.9535714285714286, | |
| "eval_f1": 0.9532277960526315, | |
| "eval_loss": 0.12774023413658142, | |
| "eval_precision": 0.9578231292517008, | |
| "eval_recall": 0.9516432104920045, | |
| "eval_runtime": 2.8037, | |
| "eval_samples_per_second": 199.733, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6568094720585712e-05, | |
| "loss": 0.1585, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.9589285714285715, | |
| "eval_f1": 0.9588181315325859, | |
| "eval_loss": 0.11161162704229355, | |
| "eval_precision": 0.9591011466011465, | |
| "eval_recall": 0.9585905842952283, | |
| "eval_runtime": 2.8029, | |
| "eval_samples_per_second": 199.797, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.9535714285714286, | |
| "eval_f1": 0.9534859946841137, | |
| "eval_loss": 0.11447751522064209, | |
| "eval_precision": 0.9533591384662554, | |
| "eval_recall": 0.9536373049047053, | |
| "eval_runtime": 2.8035, | |
| "eval_samples_per_second": 199.752, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.9553571428571429, | |
| "eval_f1": 0.955237099491941, | |
| "eval_loss": 0.10215133428573608, | |
| "eval_precision": 0.9555180180180181, | |
| "eval_recall": 0.95501144047756, | |
| "eval_runtime": 2.7996, | |
| "eval_samples_per_second": 200.03, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_f1": 0.957063995093028, | |
| "eval_loss": 0.10696452111005783, | |
| "eval_precision": 0.9569360875841542, | |
| "eval_recall": 0.9572164487223735, | |
| "eval_runtime": 2.8029, | |
| "eval_samples_per_second": 199.795, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.9589285714285715, | |
| "eval_f1": 0.9587854507521336, | |
| "eval_loss": 0.10249486565589905, | |
| "eval_precision": 0.9596153846153845, | |
| "eval_recall": 0.9582582352264448, | |
| "eval_runtime": 2.8023, | |
| "eval_samples_per_second": 199.835, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.599611050735e-05, | |
| "loss": 0.1469, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.9660714285714286, | |
| "eval_f1": 0.96593837535014, | |
| "eval_loss": 0.09906778484582901, | |
| "eval_precision": 0.96713126957236, | |
| "eval_recall": 0.9652503483273893, | |
| "eval_runtime": 2.8009, | |
| "eval_samples_per_second": 199.939, | |
| "step": 3500 | |
| } | |
| ], | |
| "max_steps": 17483, | |
| "num_train_epochs": 1, | |
| "total_flos": 9417555087360000, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |