| { | |
| "best_metric": 0.1206900030374527, | |
| "best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/fine_scale/DinoVdeau-giant-2024_08_28-batch-size32_epochs150_freeze/checkpoint-25935", | |
| "epoch": 105.0, | |
| "eval_steps": 500, | |
| "global_step": 28665, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.21205821205821207, | |
| "eval_f1_macro": 0.5175126673232894, | |
| "eval_f1_micro": 0.7424333879451582, | |
| "eval_loss": 0.17437300086021423, | |
| "eval_roc_auc": 0.8285535192873753, | |
| "eval_runtime": 747.1492, | |
| "eval_samples_per_second": 3.863, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.8315018315018317, | |
| "grad_norm": 0.29891085624694824, | |
| "learning_rate": 0.001, | |
| "loss": 0.2593, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.24774774774774774, | |
| "eval_f1_macro": 0.5912510936495889, | |
| "eval_f1_micro": 0.7776526996039191, | |
| "eval_loss": 0.1514047533273697, | |
| "eval_roc_auc": 0.856455760350861, | |
| "eval_runtime": 745.2688, | |
| "eval_samples_per_second": 3.872, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.23873873873873874, | |
| "eval_f1_macro": 0.6203462640123141, | |
| "eval_f1_micro": 0.7752795082305376, | |
| "eval_loss": 0.1557399332523346, | |
| "eval_roc_auc": 0.8580342914691714, | |
| "eval_runtime": 748.2805, | |
| "eval_samples_per_second": 3.857, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 3.663003663003663, | |
| "grad_norm": 0.24181818962097168, | |
| "learning_rate": 0.001, | |
| "loss": 0.1694, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.2494802494802495, | |
| "eval_f1_macro": 0.6112936548561337, | |
| "eval_f1_micro": 0.7691087713115115, | |
| "eval_loss": 0.1499096304178238, | |
| "eval_roc_auc": 0.8372664798756062, | |
| "eval_runtime": 747.4138, | |
| "eval_samples_per_second": 3.861, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.24497574497574498, | |
| "eval_f1_macro": 0.6316545255681125, | |
| "eval_f1_micro": 0.7744962975718961, | |
| "eval_loss": 0.15773828327655792, | |
| "eval_roc_auc": 0.8461026726645842, | |
| "eval_runtime": 747.0386, | |
| "eval_samples_per_second": 3.863, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": 0.17729038000106812, | |
| "learning_rate": 0.001, | |
| "loss": 0.1637, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.25744975744975745, | |
| "eval_f1_macro": 0.6220908262048482, | |
| "eval_f1_micro": 0.7803354441211706, | |
| "eval_loss": 0.1529887616634369, | |
| "eval_roc_auc": 0.8508892919574323, | |
| "eval_runtime": 747.6468, | |
| "eval_samples_per_second": 3.86, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.2616077616077616, | |
| "eval_f1_macro": 0.6318272608971183, | |
| "eval_f1_micro": 0.7837652308220353, | |
| "eval_loss": 0.14232446253299713, | |
| "eval_roc_auc": 0.8519980061789139, | |
| "eval_runtime": 743.8547, | |
| "eval_samples_per_second": 3.88, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 1911 | |
| }, | |
| { | |
| "epoch": 7.326007326007326, | |
| "grad_norm": 0.21456240117549896, | |
| "learning_rate": 0.001, | |
| "loss": 0.1598, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.2591822591822592, | |
| "eval_f1_macro": 0.6268140575796306, | |
| "eval_f1_micro": 0.7824785045129828, | |
| "eval_loss": 0.14342056214809418, | |
| "eval_roc_auc": 0.8521029956678926, | |
| "eval_runtime": 745.5826, | |
| "eval_samples_per_second": 3.871, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.25848925848925847, | |
| "eval_f1_macro": 0.6406683603322132, | |
| "eval_f1_micro": 0.7840562521179261, | |
| "eval_loss": 0.14322087168693542, | |
| "eval_roc_auc": 0.8556312702614824, | |
| "eval_runtime": 746.6555, | |
| "eval_samples_per_second": 3.865, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 9.157509157509157, | |
| "grad_norm": 0.17193137109279633, | |
| "learning_rate": 0.001, | |
| "loss": 0.157, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.2591822591822592, | |
| "eval_f1_macro": 0.6350156993693012, | |
| "eval_f1_micro": 0.7779440239394473, | |
| "eval_loss": 0.15065954625606537, | |
| "eval_roc_auc": 0.8421810798397646, | |
| "eval_runtime": 749.2424, | |
| "eval_samples_per_second": 3.852, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": 0.17156100273132324, | |
| "learning_rate": 0.001, | |
| "loss": 0.1564, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.26853776853776856, | |
| "eval_f1_macro": 0.6442254017268965, | |
| "eval_f1_micro": 0.7905542412977358, | |
| "eval_loss": 0.14012028276920319, | |
| "eval_roc_auc": 0.8599228950325096, | |
| "eval_runtime": 743.9581, | |
| "eval_samples_per_second": 3.879, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 3003 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.26056826056826055, | |
| "eval_f1_macro": 0.6412994039301575, | |
| "eval_f1_micro": 0.7896027049873203, | |
| "eval_loss": 0.14037516713142395, | |
| "eval_roc_auc": 0.8592624552114599, | |
| "eval_runtime": 747.0487, | |
| "eval_samples_per_second": 3.863, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 12.820512820512821, | |
| "grad_norm": 0.14995847642421722, | |
| "learning_rate": 0.001, | |
| "loss": 0.1556, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.2695772695772696, | |
| "eval_f1_macro": 0.6359393136512833, | |
| "eval_f1_micro": 0.7822141560798549, | |
| "eval_loss": 0.1420680731534958, | |
| "eval_roc_auc": 0.8492469381754499, | |
| "eval_runtime": 742.4635, | |
| "eval_samples_per_second": 3.887, | |
| "eval_steps_per_second": 0.123, | |
| "learning_rate": 0.001, | |
| "step": 3549 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.2636867636867637, | |
| "eval_f1_macro": 0.6459907944955716, | |
| "eval_f1_micro": 0.7887275978034142, | |
| "eval_loss": 0.13944004476070404, | |
| "eval_roc_auc": 0.8568078446879906, | |
| "eval_runtime": 744.9297, | |
| "eval_samples_per_second": 3.874, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 3822 | |
| }, | |
| { | |
| "epoch": 14.652014652014651, | |
| "grad_norm": 0.1688154637813568, | |
| "learning_rate": 0.001, | |
| "loss": 0.1547, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.2553707553707554, | |
| "eval_f1_macro": 0.6554204386045119, | |
| "eval_f1_micro": 0.7915315007683115, | |
| "eval_loss": 0.13796783983707428, | |
| "eval_roc_auc": 0.8575869560318454, | |
| "eval_runtime": 749.7594, | |
| "eval_samples_per_second": 3.849, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.255024255024255, | |
| "eval_f1_macro": 0.6452554527968026, | |
| "eval_f1_micro": 0.7857792404624779, | |
| "eval_loss": 0.1441228836774826, | |
| "eval_roc_auc": 0.8505811645074093, | |
| "eval_runtime": 751.9487, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 16.483516483516482, | |
| "grad_norm": 0.15101341903209686, | |
| "learning_rate": 0.001, | |
| "loss": 0.1539, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.26784476784476785, | |
| "eval_f1_macro": 0.6485416937632181, | |
| "eval_f1_micro": 0.7904489177124567, | |
| "eval_loss": 0.14113685488700867, | |
| "eval_roc_auc": 0.8607338640531657, | |
| "eval_runtime": 751.954, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 4641 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.26056826056826055, | |
| "eval_f1_macro": 0.654854199500387, | |
| "eval_f1_micro": 0.7940517933336151, | |
| "eval_loss": 0.1381485015153885, | |
| "eval_roc_auc": 0.8618218271900107, | |
| "eval_runtime": 756.1006, | |
| "eval_samples_per_second": 3.817, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.001, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 18.315018315018314, | |
| "grad_norm": 0.17647762596607208, | |
| "learning_rate": 0.001, | |
| "loss": 0.1552, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.2654192654192654, | |
| "eval_f1_macro": 0.6522812524843972, | |
| "eval_f1_micro": 0.793669650812508, | |
| "eval_loss": 0.13720253109931946, | |
| "eval_roc_auc": 0.8604083523719281, | |
| "eval_runtime": 753.1197, | |
| "eval_samples_per_second": 3.832, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 5187 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.253984753984754, | |
| "eval_f1_macro": 0.6515497507659908, | |
| "eval_f1_micro": 0.791502353390154, | |
| "eval_loss": 0.13964051008224487, | |
| "eval_roc_auc": 0.8593941380801585, | |
| "eval_runtime": 760.0428, | |
| "eval_samples_per_second": 3.797, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.001, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 20.146520146520146, | |
| "grad_norm": 0.15846939384937286, | |
| "learning_rate": 0.001, | |
| "loss": 0.1531, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.2577962577962578, | |
| "eval_f1_macro": 0.6542904488686327, | |
| "eval_f1_micro": 0.7925025501530093, | |
| "eval_loss": 0.13785456120967865, | |
| "eval_roc_auc": 0.8592903826569759, | |
| "eval_runtime": 757.5213, | |
| "eval_samples_per_second": 3.81, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.001, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 21.978021978021978, | |
| "grad_norm": 0.16983690857887268, | |
| "learning_rate": 0.001, | |
| "loss": 0.1536, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.2661122661122661, | |
| "eval_f1_macro": 0.6524154901292529, | |
| "eval_f1_micro": 0.7952276188864443, | |
| "eval_loss": 0.13633865118026733, | |
| "eval_roc_auc": 0.8620495257431491, | |
| "eval_runtime": 758.4735, | |
| "eval_samples_per_second": 3.805, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.001, | |
| "step": 6006 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.27096327096327094, | |
| "eval_f1_macro": 0.656651787807274, | |
| "eval_f1_micro": 0.7961679924728424, | |
| "eval_loss": 0.13627886772155762, | |
| "eval_roc_auc": 0.8595478597543244, | |
| "eval_runtime": 753.7633, | |
| "eval_samples_per_second": 3.829, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 6279 | |
| }, | |
| { | |
| "epoch": 23.80952380952381, | |
| "grad_norm": 0.1691550612449646, | |
| "learning_rate": 0.001, | |
| "loss": 0.1535, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.2661122661122661, | |
| "eval_f1_macro": 0.6438900918479138, | |
| "eval_f1_micro": 0.7871861324722778, | |
| "eval_loss": 0.14012865722179413, | |
| "eval_roc_auc": 0.8565085837324373, | |
| "eval_runtime": 758.2383, | |
| "eval_samples_per_second": 3.806, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.001, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.27546777546777546, | |
| "eval_f1_macro": 0.6538094573584412, | |
| "eval_f1_micro": 0.7960565795113589, | |
| "eval_loss": 0.1359640210866928, | |
| "eval_roc_auc": 0.8588707063899927, | |
| "eval_runtime": 765.0178, | |
| "eval_samples_per_second": 3.772, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 0.001, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 0.14603881537914276, | |
| "learning_rate": 0.001, | |
| "loss": 0.153, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.2692307692307692, | |
| "eval_f1_macro": 0.6407905722004358, | |
| "eval_f1_micro": 0.7942222975262623, | |
| "eval_loss": 0.1370791494846344, | |
| "eval_roc_auc": 0.8611700794845683, | |
| "eval_runtime": 750.2435, | |
| "eval_samples_per_second": 3.847, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 7098 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.2654192654192654, | |
| "eval_f1_macro": 0.6469565906332285, | |
| "eval_f1_micro": 0.7902460077686664, | |
| "eval_loss": 0.13669614493846893, | |
| "eval_roc_auc": 0.8538650806596136, | |
| "eval_runtime": 744.2164, | |
| "eval_samples_per_second": 3.878, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 27.47252747252747, | |
| "grad_norm": 0.1542704999446869, | |
| "learning_rate": 0.001, | |
| "loss": 0.1532, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.26888426888426886, | |
| "eval_f1_macro": 0.642689033704319, | |
| "eval_f1_micro": 0.7912144926283021, | |
| "eval_loss": 0.1371130496263504, | |
| "eval_roc_auc": 0.8539010295328042, | |
| "eval_runtime": 744.0106, | |
| "eval_samples_per_second": 3.879, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.2692307692307692, | |
| "eval_f1_macro": 0.6484600603294314, | |
| "eval_f1_micro": 0.7944120277694962, | |
| "eval_loss": 0.13781629502773285, | |
| "eval_roc_auc": 0.8597476308619466, | |
| "eval_runtime": 751.4281, | |
| "eval_samples_per_second": 3.841, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 7917 | |
| }, | |
| { | |
| "epoch": 29.304029304029303, | |
| "grad_norm": 0.15774671733379364, | |
| "learning_rate": 0.001, | |
| "loss": 0.1539, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.26507276507276506, | |
| "eval_f1_macro": 0.6472439075890195, | |
| "eval_f1_micro": 0.7938241064573914, | |
| "eval_loss": 0.13641151785850525, | |
| "eval_roc_auc": 0.8590391831986771, | |
| "eval_runtime": 743.8204, | |
| "eval_samples_per_second": 3.88, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.2747747747747748, | |
| "eval_f1_macro": 0.6533472550118105, | |
| "eval_f1_micro": 0.7999161777032691, | |
| "eval_loss": 0.13565559685230255, | |
| "eval_roc_auc": 0.8672849828142924, | |
| "eval_runtime": 745.046, | |
| "eval_samples_per_second": 3.874, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 8463 | |
| }, | |
| { | |
| "epoch": 31.135531135531135, | |
| "grad_norm": 0.15824691951274872, | |
| "learning_rate": 0.001, | |
| "loss": 0.1527, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.2664587664587665, | |
| "eval_f1_macro": 0.662032330499469, | |
| "eval_f1_micro": 0.7928646379853095, | |
| "eval_loss": 0.137930765748024, | |
| "eval_roc_auc": 0.8629893205019107, | |
| "eval_runtime": 747.6199, | |
| "eval_samples_per_second": 3.86, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 32.967032967032964, | |
| "grad_norm": 0.17653779685497284, | |
| "learning_rate": 0.001, | |
| "loss": 0.1524, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.273042273042273, | |
| "eval_f1_macro": 0.6722007856831675, | |
| "eval_f1_micro": 0.7989514185446704, | |
| "eval_loss": 0.13557712733745575, | |
| "eval_roc_auc": 0.8642597778252326, | |
| "eval_runtime": 743.3529, | |
| "eval_samples_per_second": 3.882, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 9009 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.273042273042273, | |
| "eval_f1_macro": 0.670590685863264, | |
| "eval_f1_micro": 0.7966670917825107, | |
| "eval_loss": 0.1347290426492691, | |
| "eval_roc_auc": 0.8614922779674185, | |
| "eval_runtime": 743.2445, | |
| "eval_samples_per_second": 3.883, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 9282 | |
| }, | |
| { | |
| "epoch": 34.798534798534796, | |
| "grad_norm": 0.15610426664352417, | |
| "learning_rate": 0.001, | |
| "loss": 0.1516, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.2772002772002772, | |
| "eval_f1_macro": 0.6482708127714739, | |
| "eval_f1_micro": 0.7946646145953571, | |
| "eval_loss": 0.13544337451457977, | |
| "eval_roc_auc": 0.8588431142884431, | |
| "eval_runtime": 750.5786, | |
| "eval_samples_per_second": 3.845, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 9555 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.25848925848925847, | |
| "eval_f1_macro": 0.6552995006011981, | |
| "eval_f1_micro": 0.7927604900328681, | |
| "eval_loss": 0.13763058185577393, | |
| "eval_roc_auc": 0.8582396561141522, | |
| "eval_runtime": 746.9319, | |
| "eval_samples_per_second": 3.864, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 36.63003663003663, | |
| "grad_norm": 0.176735520362854, | |
| "learning_rate": 0.001, | |
| "loss": 0.1527, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.2747747747747748, | |
| "eval_f1_macro": 0.6680976075122991, | |
| "eval_f1_micro": 0.7992204380799051, | |
| "eval_loss": 0.13456694781780243, | |
| "eval_roc_auc": 0.8638335422302681, | |
| "eval_runtime": 744.024, | |
| "eval_samples_per_second": 3.879, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 10101 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.27165627165627165, | |
| "eval_f1_macro": 0.6543467314054483, | |
| "eval_f1_micro": 0.7889066758966815, | |
| "eval_loss": 0.13784632086753845, | |
| "eval_roc_auc": 0.8524819477636044, | |
| "eval_runtime": 745.3518, | |
| "eval_samples_per_second": 3.872, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 10374 | |
| }, | |
| { | |
| "epoch": 38.46153846153846, | |
| "grad_norm": 0.16059936583042145, | |
| "learning_rate": 0.001, | |
| "loss": 0.1503, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.2664587664587665, | |
| "eval_f1_macro": 0.6627442989440849, | |
| "eval_f1_micro": 0.7965357098029371, | |
| "eval_loss": 0.13671767711639404, | |
| "eval_roc_auc": 0.865910488378856, | |
| "eval_runtime": 745.9061, | |
| "eval_samples_per_second": 3.869, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 10647 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.27373527373527373, | |
| "eval_f1_macro": 0.670153584497431, | |
| "eval_f1_micro": 0.8004978220286246, | |
| "eval_loss": 0.13730555772781372, | |
| "eval_roc_auc": 0.8705375510125241, | |
| "eval_runtime": 744.6796, | |
| "eval_samples_per_second": 3.875, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 40.29304029304029, | |
| "grad_norm": 0.16920654475688934, | |
| "learning_rate": 0.001, | |
| "loss": 0.152, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.26576576576576577, | |
| "eval_f1_macro": 0.6610276871242879, | |
| "eval_f1_micro": 0.7942296990711015, | |
| "eval_loss": 0.13770104944705963, | |
| "eval_roc_auc": 0.8582536198369102, | |
| "eval_runtime": 744.9969, | |
| "eval_samples_per_second": 3.874, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.001, | |
| "step": 11193 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.28101178101178104, | |
| "eval_f1_macro": 0.6705886094654014, | |
| "eval_f1_micro": 0.8001525876319246, | |
| "eval_loss": 0.13536451756954193, | |
| "eval_roc_auc": 0.8642216961644161, | |
| "eval_runtime": 751.3727, | |
| "eval_samples_per_second": 3.841, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 11466 | |
| }, | |
| { | |
| "epoch": 42.124542124542124, | |
| "grad_norm": 0.1676277071237564, | |
| "learning_rate": 0.001, | |
| "loss": 0.1515, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.26507276507276506, | |
| "eval_f1_macro": 0.6619628883017729, | |
| "eval_f1_micro": 0.8000498525196295, | |
| "eval_loss": 0.13665379583835602, | |
| "eval_roc_auc": 0.8698817657657271, | |
| "eval_runtime": 749.8198, | |
| "eval_samples_per_second": 3.849, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.001, | |
| "step": 11739 | |
| }, | |
| { | |
| "epoch": 43.956043956043956, | |
| "grad_norm": 0.15791508555412292, | |
| "learning_rate": 0.0001, | |
| "loss": 0.147, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.2869022869022869, | |
| "eval_f1_macro": 0.6825865030851337, | |
| "eval_f1_micro": 0.808658516161447, | |
| "eval_loss": 0.12908011674880981, | |
| "eval_roc_auc": 0.8723907154255005, | |
| "eval_runtime": 750.2309, | |
| "eval_samples_per_second": 3.847, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 12012 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.29972279972279975, | |
| "eval_f1_macro": 0.6938587241702103, | |
| "eval_f1_micro": 0.811512367788968, | |
| "eval_loss": 0.12761357426643372, | |
| "eval_roc_auc": 0.8720936945676423, | |
| "eval_runtime": 758.8984, | |
| "eval_samples_per_second": 3.803, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.0001, | |
| "step": 12285 | |
| }, | |
| { | |
| "epoch": 45.78754578754579, | |
| "grad_norm": 0.16074201464653015, | |
| "learning_rate": 0.0001, | |
| "loss": 0.139, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.2959112959112959, | |
| "eval_f1_macro": 0.6856377454961721, | |
| "eval_f1_micro": 0.8103163511624953, | |
| "eval_loss": 0.12698666751384735, | |
| "eval_roc_auc": 0.8699996458767716, | |
| "eval_runtime": 752.5715, | |
| "eval_samples_per_second": 3.835, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 12558 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.2972972972972973, | |
| "eval_f1_macro": 0.6942647446672258, | |
| "eval_f1_micro": 0.8124920976103174, | |
| "eval_loss": 0.12690682709217072, | |
| "eval_roc_auc": 0.8725812846946867, | |
| "eval_runtime": 759.108, | |
| "eval_samples_per_second": 3.802, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.0001, | |
| "step": 12831 | |
| }, | |
| { | |
| "epoch": 47.61904761904762, | |
| "grad_norm": 0.17895784974098206, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1375, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.29799029799029797, | |
| "eval_f1_macro": 0.694151320978192, | |
| "eval_f1_micro": 0.8131711409395973, | |
| "eval_loss": 0.12617328763008118, | |
| "eval_roc_auc": 0.8743386078020858, | |
| "eval_runtime": 767.7622, | |
| "eval_samples_per_second": 3.759, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 0.0001, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.2966042966042966, | |
| "eval_f1_macro": 0.6956458198072734, | |
| "eval_f1_micro": 0.8147346514047868, | |
| "eval_loss": 0.1263018250465393, | |
| "eval_roc_auc": 0.8774737921983433, | |
| "eval_runtime": 752.7691, | |
| "eval_samples_per_second": 3.834, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 13377 | |
| }, | |
| { | |
| "epoch": 49.45054945054945, | |
| "grad_norm": 0.22477330267429352, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1353, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.2927927927927928, | |
| "eval_f1_macro": 0.7006577033751422, | |
| "eval_f1_micro": 0.8153475224476222, | |
| "eval_loss": 0.1258096992969513, | |
| "eval_roc_auc": 0.8781952512075065, | |
| "eval_runtime": 751.7275, | |
| "eval_samples_per_second": 3.839, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.2972972972972973, | |
| "eval_f1_macro": 0.6994505755010588, | |
| "eval_f1_micro": 0.8151571934207786, | |
| "eval_loss": 0.12573884427547455, | |
| "eval_roc_auc": 0.8775850056713371, | |
| "eval_runtime": 754.5773, | |
| "eval_samples_per_second": 3.825, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 13923 | |
| }, | |
| { | |
| "epoch": 51.282051282051285, | |
| "grad_norm": 0.1825592815876007, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1337, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.2972972972972973, | |
| "eval_f1_macro": 0.6974514657531053, | |
| "eval_f1_micro": 0.8134649455833967, | |
| "eval_loss": 0.12501972913742065, | |
| "eval_roc_auc": 0.8728563740571469, | |
| "eval_runtime": 748.8299, | |
| "eval_samples_per_second": 3.854, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 14196 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.2948717948717949, | |
| "eval_f1_macro": 0.6962280886309719, | |
| "eval_f1_micro": 0.8132960287301124, | |
| "eval_loss": 0.12481856346130371, | |
| "eval_roc_auc": 0.8757195542554345, | |
| "eval_runtime": 754.8846, | |
| "eval_samples_per_second": 3.823, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 14469 | |
| }, | |
| { | |
| "epoch": 53.11355311355312, | |
| "grad_norm": 0.16182786226272583, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1338, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.30180180180180183, | |
| "eval_f1_macro": 0.6980743235485474, | |
| "eval_f1_micro": 0.8143470573377115, | |
| "eval_loss": 0.12473563104867935, | |
| "eval_roc_auc": 0.8739288040614714, | |
| "eval_runtime": 764.2531, | |
| "eval_samples_per_second": 3.776, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 0.0001, | |
| "step": 14742 | |
| }, | |
| { | |
| "epoch": 54.94505494505494, | |
| "grad_norm": 0.22775864601135254, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1322, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.30076230076230076, | |
| "eval_f1_macro": 0.7020497284253308, | |
| "eval_f1_micro": 0.8165587111775452, | |
| "eval_loss": 0.12453257292509079, | |
| "eval_roc_auc": 0.8792131676966645, | |
| "eval_runtime": 758.6078, | |
| "eval_samples_per_second": 3.804, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.0001, | |
| "step": 15015 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.3011088011088011, | |
| "eval_f1_macro": 0.7041152638460181, | |
| "eval_f1_micro": 0.8185497191939213, | |
| "eval_loss": 0.12440259009599686, | |
| "eval_roc_auc": 0.8819546448626913, | |
| "eval_runtime": 755.48, | |
| "eval_samples_per_second": 3.82, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 0.0001, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 56.776556776556774, | |
| "grad_norm": 0.26265445351600647, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1313, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.3004158004158004, | |
| "eval_f1_macro": 0.6984123654445143, | |
| "eval_f1_micro": 0.8162207357859533, | |
| "eval_loss": 0.12393573671579361, | |
| "eval_roc_auc": 0.8770029692696153, | |
| "eval_runtime": 749.3127, | |
| "eval_samples_per_second": 3.852, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 15561 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.30006930006930005, | |
| "eval_f1_macro": 0.7041206694443728, | |
| "eval_f1_micro": 0.8171478565179352, | |
| "eval_loss": 0.12355069816112518, | |
| "eval_roc_auc": 0.8785400518736873, | |
| "eval_runtime": 751.5939, | |
| "eval_samples_per_second": 3.84, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 15834 | |
| }, | |
| { | |
| "epoch": 58.608058608058606, | |
| "grad_norm": 0.19159354269504547, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1309, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.3049203049203049, | |
| "eval_f1_macro": 0.701908769020469, | |
| "eval_f1_micro": 0.8158932617269447, | |
| "eval_loss": 0.1237163171172142, | |
| "eval_roc_auc": 0.8757623441455382, | |
| "eval_runtime": 749.4527, | |
| "eval_samples_per_second": 3.851, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 16107 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.29902979902979904, | |
| "eval_f1_macro": 0.7008492179245241, | |
| "eval_f1_micro": 0.8152564590468943, | |
| "eval_loss": 0.12339853495359421, | |
| "eval_roc_auc": 0.8731348839280636, | |
| "eval_runtime": 748.7843, | |
| "eval_samples_per_second": 3.854, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 16380 | |
| }, | |
| { | |
| "epoch": 60.43956043956044, | |
| "grad_norm": 0.19487616419792175, | |
| "learning_rate": 0.0001, | |
| "loss": 0.13, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.3024948024948025, | |
| "eval_f1_macro": 0.7083200505706103, | |
| "eval_f1_micro": 0.8188720173535793, | |
| "eval_loss": 0.12294851988554001, | |
| "eval_roc_auc": 0.8791109816832443, | |
| "eval_runtime": 752.7718, | |
| "eval_samples_per_second": 3.834, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 16653 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.30284130284130284, | |
| "eval_f1_macro": 0.7054890147149661, | |
| "eval_f1_micro": 0.8166017506386899, | |
| "eval_loss": 0.12270853668451309, | |
| "eval_roc_auc": 0.876682675540494, | |
| "eval_runtime": 746.0294, | |
| "eval_samples_per_second": 3.868, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 16926 | |
| }, | |
| { | |
| "epoch": 62.27106227106227, | |
| "grad_norm": 0.20640559494495392, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1288, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.3038808038808039, | |
| "eval_f1_macro": 0.7105833307429198, | |
| "eval_f1_micro": 0.8176490288010717, | |
| "eval_loss": 0.12301415950059891, | |
| "eval_roc_auc": 0.8773957777780161, | |
| "eval_runtime": 748.1364, | |
| "eval_samples_per_second": 3.858, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 17199 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.3049203049203049, | |
| "eval_f1_macro": 0.7085844813380441, | |
| "eval_f1_micro": 0.8191759178412541, | |
| "eval_loss": 0.12328237295150757, | |
| "eval_roc_auc": 0.880258676287372, | |
| "eval_runtime": 749.8061, | |
| "eval_samples_per_second": 3.849, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 0.0001, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 64.1025641025641, | |
| "grad_norm": 0.2363331913948059, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1291, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.3049203049203049, | |
| "eval_f1_macro": 0.7103887558295827, | |
| "eval_f1_micro": 0.8187567612548888, | |
| "eval_loss": 0.12309526652097702, | |
| "eval_roc_auc": 0.8798153918051592, | |
| "eval_runtime": 745.0937, | |
| "eval_samples_per_second": 3.873, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 17745 | |
| }, | |
| { | |
| "epoch": 65.93406593406593, | |
| "grad_norm": 0.26966458559036255, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1283, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.30284130284130284, | |
| "eval_f1_macro": 0.7061406642055487, | |
| "eval_f1_micro": 0.8186407442947141, | |
| "eval_loss": 0.12194398790597916, | |
| "eval_roc_auc": 0.8789458717279818, | |
| "eval_runtime": 744.2128, | |
| "eval_samples_per_second": 3.878, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 18018 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.3042273042273042, | |
| "eval_f1_macro": 0.7154558287425048, | |
| "eval_f1_micro": 0.8196775527077305, | |
| "eval_loss": 0.12292120605707169, | |
| "eval_roc_auc": 0.8822622625898855, | |
| "eval_runtime": 743.6955, | |
| "eval_samples_per_second": 3.881, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 18291 | |
| }, | |
| { | |
| "epoch": 67.76556776556777, | |
| "grad_norm": 0.2636018991470337, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1273, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.30803880803880807, | |
| "eval_f1_macro": 0.7153434473934246, | |
| "eval_f1_micro": 0.8209686046990085, | |
| "eval_loss": 0.12254418432712555, | |
| "eval_roc_auc": 0.8843888396454903, | |
| "eval_runtime": 743.6093, | |
| "eval_samples_per_second": 3.881, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 18564 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.3031878031878032, | |
| "eval_f1_macro": 0.7101570111652898, | |
| "eval_f1_micro": 0.8195983668027664, | |
| "eval_loss": 0.12215162813663483, | |
| "eval_roc_auc": 0.87988510310888, | |
| "eval_runtime": 744.98, | |
| "eval_samples_per_second": 3.874, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 18837 | |
| }, | |
| { | |
| "epoch": 69.59706959706959, | |
| "grad_norm": 0.19965404272079468, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1265, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.30838530838530837, | |
| "eval_f1_macro": 0.7109091736321397, | |
| "eval_f1_micro": 0.8184682603033231, | |
| "eval_loss": 0.12227334082126617, | |
| "eval_roc_auc": 0.8767948413903521, | |
| "eval_runtime": 744.4872, | |
| "eval_samples_per_second": 3.876, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 19110 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.3076923076923077, | |
| "eval_f1_macro": 0.7120407268503043, | |
| "eval_f1_micro": 0.8170385739086251, | |
| "eval_loss": 0.12237659096717834, | |
| "eval_roc_auc": 0.8737123194105673, | |
| "eval_runtime": 747.0787, | |
| "eval_samples_per_second": 3.863, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 19383 | |
| }, | |
| { | |
| "epoch": 71.42857142857143, | |
| "grad_norm": 0.2734057903289795, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1264, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.3063063063063063, | |
| "eval_f1_macro": 0.7203981522602361, | |
| "eval_f1_micro": 0.8203632727878687, | |
| "eval_loss": 0.1220996230840683, | |
| "eval_roc_auc": 0.8803336591982435, | |
| "eval_runtime": 742.9487, | |
| "eval_samples_per_second": 3.885, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 0.0001, | |
| "step": 19656 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.3087318087318087, | |
| "eval_f1_macro": 0.7144193511981376, | |
| "eval_f1_micro": 0.8198457369189076, | |
| "eval_loss": 0.12169401347637177, | |
| "eval_roc_auc": 0.8798110725748728, | |
| "eval_runtime": 752.9878, | |
| "eval_samples_per_second": 3.833, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 19929 | |
| }, | |
| { | |
| "epoch": 73.26007326007326, | |
| "grad_norm": 0.20597431063652039, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1249, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.30665280665280664, | |
| "eval_f1_macro": 0.7124121424308173, | |
| "eval_f1_micro": 0.8190452070406484, | |
| "eval_loss": 0.12149834632873535, | |
| "eval_roc_auc": 0.8757233637628921, | |
| "eval_runtime": 756.5322, | |
| "eval_samples_per_second": 3.815, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1e-05, | |
| "step": 20202 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.30561330561330563, | |
| "eval_f1_macro": 0.7145366354361308, | |
| "eval_f1_micro": 0.8208643316893754, | |
| "eval_loss": 0.12120900303125381, | |
| "eval_roc_auc": 0.879641026356426, | |
| "eval_runtime": 752.1644, | |
| "eval_samples_per_second": 3.837, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 20475 | |
| }, | |
| { | |
| "epoch": 75.0915750915751, | |
| "grad_norm": 0.25457698106765747, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1236, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.30803880803880807, | |
| "eval_f1_macro": 0.7191205487713891, | |
| "eval_f1_micro": 0.8218541121766927, | |
| "eval_loss": 0.1215985044836998, | |
| "eval_roc_auc": 0.8821938390069956, | |
| "eval_runtime": 752.3495, | |
| "eval_samples_per_second": 3.836, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 20748 | |
| }, | |
| { | |
| "epoch": 76.92307692307692, | |
| "grad_norm": 0.2589890658855438, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1233, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.31323631323631324, | |
| "eval_f1_macro": 0.7202749659896155, | |
| "eval_f1_micro": 0.8236983547367989, | |
| "eval_loss": 0.1214083805680275, | |
| "eval_roc_auc": 0.8867951606378082, | |
| "eval_runtime": 755.0282, | |
| "eval_samples_per_second": 3.822, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 21021 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.3097713097713098, | |
| "eval_f1_macro": 0.7168480610158249, | |
| "eval_f1_micro": 0.8222591362126246, | |
| "eval_loss": 0.12110316008329391, | |
| "eval_roc_auc": 0.8823316922046746, | |
| "eval_runtime": 752.7354, | |
| "eval_samples_per_second": 3.834, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 21294 | |
| }, | |
| { | |
| "epoch": 78.75457875457876, | |
| "grad_norm": 0.26676803827285767, | |
| "learning_rate": 1e-05, | |
| "loss": 0.123, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.30665280665280664, | |
| "eval_f1_macro": 0.7160500850094047, | |
| "eval_f1_micro": 0.8202977563430488, | |
| "eval_loss": 0.12149946391582489, | |
| "eval_roc_auc": 0.878321716124089, | |
| "eval_runtime": 752.3192, | |
| "eval_samples_per_second": 3.836, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 21567 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.30734580734580735, | |
| "eval_f1_macro": 0.7150848378423871, | |
| "eval_f1_micro": 0.8219257062844905, | |
| "eval_loss": 0.121590256690979, | |
| "eval_roc_auc": 0.8846639290079505, | |
| "eval_runtime": 747.5776, | |
| "eval_samples_per_second": 3.86, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 1e-05, | |
| "step": 21840 | |
| }, | |
| { | |
| "epoch": 80.58608058608058, | |
| "grad_norm": 0.2525629699230194, | |
| "learning_rate": 1e-05, | |
| "loss": 0.123, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.3115038115038115, | |
| "eval_f1_macro": 0.7187103786018064, | |
| "eval_f1_micro": 0.8216162121591194, | |
| "eval_loss": 0.12097962200641632, | |
| "eval_roc_auc": 0.8807537244642276, | |
| "eval_runtime": 755.3491, | |
| "eval_samples_per_second": 3.821, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1e-05, | |
| "step": 22113 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.30942480942480943, | |
| "eval_f1_macro": 0.7156786549052798, | |
| "eval_f1_micro": 0.821175978238125, | |
| "eval_loss": 0.12082336097955704, | |
| "eval_roc_auc": 0.8794272915260457, | |
| "eval_runtime": 753.7414, | |
| "eval_samples_per_second": 3.829, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 22386 | |
| }, | |
| { | |
| "epoch": 82.41758241758242, | |
| "grad_norm": 0.23939679563045502, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1214, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.30006930006930005, | |
| "eval_f1_macro": 0.7102312532643303, | |
| "eval_f1_micro": 0.8180206046275968, | |
| "eval_loss": 0.12147542089223862, | |
| "eval_roc_auc": 0.8750765523206339, | |
| "eval_runtime": 745.2706, | |
| "eval_samples_per_second": 3.872, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 1e-05, | |
| "step": 22659 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.31185031185031187, | |
| "eval_f1_macro": 0.7195842513107142, | |
| "eval_f1_micro": 0.8215978053038491, | |
| "eval_loss": 0.12100570648908615, | |
| "eval_roc_auc": 0.8816901523695672, | |
| "eval_runtime": 742.6349, | |
| "eval_samples_per_second": 3.886, | |
| "eval_steps_per_second": 0.123, | |
| "learning_rate": 1e-05, | |
| "step": 22932 | |
| }, | |
| { | |
| "epoch": 84.24908424908425, | |
| "grad_norm": 0.30801209807395935, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1234, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.31011781011781014, | |
| "eval_f1_macro": 0.7201395616901511, | |
| "eval_f1_micro": 0.8233587533156498, | |
| "eval_loss": 0.1208326444029808, | |
| "eval_roc_auc": 0.8835425924395763, | |
| "eval_runtime": 742.1618, | |
| "eval_samples_per_second": 3.889, | |
| "eval_steps_per_second": 0.123, | |
| "learning_rate": 1e-05, | |
| "step": 23205 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.30942480942480943, | |
| "eval_f1_macro": 0.7215167678270465, | |
| "eval_f1_micro": 0.8218151540383014, | |
| "eval_loss": 0.1210438683629036, | |
| "eval_roc_auc": 0.8813373302757117, | |
| "eval_runtime": 754.9986, | |
| "eval_samples_per_second": 3.823, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 23478 | |
| }, | |
| { | |
| "epoch": 86.08058608058609, | |
| "grad_norm": 0.23295313119888306, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1216, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.3087318087318087, | |
| "eval_f1_macro": 0.7141558876633265, | |
| "eval_f1_micro": 0.8207271207689094, | |
| "eval_loss": 0.1212099939584732, | |
| "eval_roc_auc": 0.8796150036646389, | |
| "eval_runtime": 753.045, | |
| "eval_samples_per_second": 3.832, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1e-05, | |
| "step": 23751 | |
| }, | |
| { | |
| "epoch": 87.91208791208791, | |
| "grad_norm": 0.21838252246379852, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1219, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.31011781011781014, | |
| "eval_f1_macro": 0.7124615854591595, | |
| "eval_f1_micro": 0.8223957468017943, | |
| "eval_loss": 0.12096676975488663, | |
| "eval_roc_auc": 0.8823577148964619, | |
| "eval_runtime": 758.2188, | |
| "eval_samples_per_second": 3.806, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1e-05, | |
| "step": 24024 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.3121968121968122, | |
| "eval_f1_macro": 0.7249978662662346, | |
| "eval_f1_micro": 0.8240642149234173, | |
| "eval_loss": 0.12144902348518372, | |
| "eval_roc_auc": 0.8875640104562932, | |
| "eval_runtime": 760.5663, | |
| "eval_samples_per_second": 3.795, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 24297 | |
| }, | |
| { | |
| "epoch": 89.74358974358974, | |
| "grad_norm": 0.21705362200737, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1219, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.31046431046431044, | |
| "eval_f1_macro": 0.7198781344667567, | |
| "eval_f1_micro": 0.8233893154847453, | |
| "eval_loss": 0.12115956842899323, | |
| "eval_roc_auc": 0.8863713931744356, | |
| "eval_runtime": 763.5088, | |
| "eval_samples_per_second": 3.78, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 24570 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.3097713097713098, | |
| "eval_f1_macro": 0.7159843095789674, | |
| "eval_f1_micro": 0.8212459126351974, | |
| "eval_loss": 0.1208055168390274, | |
| "eval_roc_auc": 0.8789555162204534, | |
| "eval_runtime": 757.8368, | |
| "eval_samples_per_second": 3.808, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 24843 | |
| }, | |
| { | |
| "epoch": 91.57509157509158, | |
| "grad_norm": 0.23301896452903748, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1213, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.30734580734580735, | |
| "eval_f1_macro": 0.7144036362020703, | |
| "eval_f1_micro": 0.8223893065998329, | |
| "eval_loss": 0.12069901078939438, | |
| "eval_roc_auc": 0.8806577087797879, | |
| "eval_runtime": 763.0077, | |
| "eval_samples_per_second": 3.782, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 25116 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.30803880803880807, | |
| "eval_f1_macro": 0.7189178649032102, | |
| "eval_f1_micro": 0.8226574468966088, | |
| "eval_loss": 0.12093978375196457, | |
| "eval_roc_auc": 0.8834391187053254, | |
| "eval_runtime": 763.7654, | |
| "eval_samples_per_second": 3.779, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 25389 | |
| }, | |
| { | |
| "epoch": 93.4065934065934, | |
| "grad_norm": 0.2630571126937866, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.122, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.3097713097713098, | |
| "eval_f1_macro": 0.7187657914933285, | |
| "eval_f1_micro": 0.8223438666334908, | |
| "eval_loss": 0.12092197686433792, | |
| "eval_roc_auc": 0.8828028504773688, | |
| "eval_runtime": 758.2573, | |
| "eval_samples_per_second": 3.806, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 25662 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.30942480942480943, | |
| "eval_f1_macro": 0.7127077698746517, | |
| "eval_f1_micro": 0.8221934621968021, | |
| "eval_loss": 0.1206900030374527, | |
| "eval_roc_auc": 0.8807116052620565, | |
| "eval_runtime": 755.4845, | |
| "eval_samples_per_second": 3.82, | |
| "eval_steps_per_second": 0.12, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 25935 | |
| }, | |
| { | |
| "epoch": 95.23809523809524, | |
| "grad_norm": 0.32719686627388, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1209, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.30665280665280664, | |
| "eval_f1_macro": 0.7160309422692305, | |
| "eval_f1_micro": 0.8218438538205979, | |
| "eval_loss": 0.12142115086317062, | |
| "eval_roc_auc": 0.882100908487046, | |
| "eval_runtime": 764.2068, | |
| "eval_samples_per_second": 3.776, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 26208 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.30942480942480943, | |
| "eval_f1_macro": 0.71586766610014, | |
| "eval_f1_micro": 0.8208711661575798, | |
| "eval_loss": 0.12264719605445862, | |
| "eval_roc_auc": 0.879308955347207, | |
| "eval_runtime": 783.117, | |
| "eval_samples_per_second": 3.685, | |
| "eval_steps_per_second": 0.116, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 26481 | |
| }, | |
| { | |
| "epoch": 97.06959706959707, | |
| "grad_norm": 0.27319103479385376, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.122, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.31185031185031187, | |
| "eval_f1_macro": 0.7190138873820752, | |
| "eval_f1_micro": 0.8224561403508771, | |
| "eval_loss": 0.12095578759908676, | |
| "eval_roc_auc": 0.8842500877259815, | |
| "eval_runtime": 761.8672, | |
| "eval_samples_per_second": 3.788, | |
| "eval_steps_per_second": 0.119, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 26754 | |
| }, | |
| { | |
| "epoch": 98.9010989010989, | |
| "grad_norm": 0.314969539642334, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "loss": 0.1218, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.3097713097713098, | |
| "eval_f1_macro": 0.7177436878101541, | |
| "eval_f1_micro": 0.821403230518803, | |
| "eval_loss": 0.12075632065534592, | |
| "eval_roc_auc": 0.8803494740196957, | |
| "eval_runtime": 749.7836, | |
| "eval_samples_per_second": 3.849, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 27027 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.3108108108108108, | |
| "eval_f1_macro": 0.7191112023643382, | |
| "eval_f1_micro": 0.8218776194467728, | |
| "eval_loss": 0.12078335881233215, | |
| "eval_roc_auc": 0.8793780496180298, | |
| "eval_runtime": 751.4627, | |
| "eval_samples_per_second": 3.841, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 100.73260073260073, | |
| "grad_norm": 0.3180501163005829, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "loss": 0.1222, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.3097713097713098, | |
| "eval_f1_macro": 0.7199208624613478, | |
| "eval_f1_micro": 0.8230599775551769, | |
| "eval_loss": 0.12071150541305542, | |
| "eval_roc_auc": 0.8825144680800833, | |
| "eval_runtime": 753.7405, | |
| "eval_samples_per_second": 3.829, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 27573 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.31011781011781014, | |
| "eval_f1_macro": 0.7181176324357539, | |
| "eval_f1_micro": 0.821560093739538, | |
| "eval_loss": 0.12102664262056351, | |
| "eval_roc_auc": 0.8796515695707274, | |
| "eval_runtime": 750.0067, | |
| "eval_samples_per_second": 3.848, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 27846 | |
| }, | |
| { | |
| "epoch": 102.56410256410257, | |
| "grad_norm": 0.257368803024292, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "loss": 0.1212, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.31115731115731116, | |
| "eval_f1_macro": 0.7156251632807489, | |
| "eval_f1_micro": 0.8218559116391932, | |
| "eval_loss": 0.12072332948446274, | |
| "eval_roc_auc": 0.879889475994201, | |
| "eval_runtime": 747.7283, | |
| "eval_samples_per_second": 3.86, | |
| "eval_steps_per_second": 0.122, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 28119 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.3090783090783091, | |
| "eval_f1_macro": 0.7151217785983346, | |
| "eval_f1_micro": 0.8214226220223222, | |
| "eval_loss": 0.12122868001461029, | |
| "eval_roc_auc": 0.8810201217110805, | |
| "eval_runtime": 751.9776, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 28392 | |
| }, | |
| { | |
| "epoch": 104.3956043956044, | |
| "grad_norm": 0.2758227586746216, | |
| "learning_rate": 1.0000000000000004e-08, | |
| "loss": 0.1204, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.30838530838530837, | |
| "eval_f1_macro": 0.7175066761763569, | |
| "eval_f1_micro": 0.8216449497883642, | |
| "eval_loss": 0.12081456929445267, | |
| "eval_roc_auc": 0.882214590091632, | |
| "eval_runtime": 750.7114, | |
| "eval_samples_per_second": 3.844, | |
| "eval_steps_per_second": 0.121, | |
| "learning_rate": 1.0000000000000004e-08, | |
| "step": 28665 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "learning_rate": 1.0000000000000004e-08, | |
| "step": 28665, | |
| "total_flos": 5.049640374682393e+21, | |
| "train_loss": 0.023157235795491324, | |
| "train_runtime": 62002.1626, | |
| "train_samples_per_second": 21.086, | |
| "train_steps_per_second": 0.66 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 40950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.049640374682393e+21, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |