| { | |
| "best_metric": 0.12932655215263367, | |
| "best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/fine_scale/dinov2-base-2024_09_09-batch-size32_epochs150_freeze/checkpoint-13377", | |
| "epoch": 59.0, | |
| "eval_steps": 500, | |
| "global_step": 16107, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.23284823284823286, | |
| "eval_f1_macro": 0.6250897780499145, | |
| "eval_f1_micro": 0.7633800438966739, | |
| "eval_loss": 0.16006726026535034, | |
| "eval_roc_auc": 0.8452995641064989, | |
| "eval_runtime": 455.8596, | |
| "eval_samples_per_second": 6.331, | |
| "eval_steps_per_second": 0.2, | |
| "learning_rate": 0.001, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.8315018315018317, | |
| "grad_norm": 0.4072045385837555, | |
| "learning_rate": 0.001, | |
| "loss": 0.1759, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.24982674982674982, | |
| "eval_f1_macro": 0.646165211379598, | |
| "eval_f1_micro": 0.7780064686856808, | |
| "eval_loss": 0.150440976023674, | |
| "eval_roc_auc": 0.8546135818062216, | |
| "eval_runtime": 451.8319, | |
| "eval_samples_per_second": 6.387, | |
| "eval_steps_per_second": 0.201, | |
| "learning_rate": 0.001, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.2564102564102564, | |
| "eval_f1_macro": 0.6644318154557648, | |
| "eval_f1_micro": 0.7816936696175046, | |
| "eval_loss": 0.14829224348068237, | |
| "eval_roc_auc": 0.8582657995297673, | |
| "eval_runtime": 444.7156, | |
| "eval_samples_per_second": 6.49, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 0.001, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 3.663003663003663, | |
| "grad_norm": 0.4122166037559509, | |
| "learning_rate": 0.001, | |
| "loss": 0.1474, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.2553707553707554, | |
| "eval_f1_macro": 0.680888104485521, | |
| "eval_f1_micro": 0.7862639635912287, | |
| "eval_loss": 0.14641565084457397, | |
| "eval_roc_auc": 0.8633757977162271, | |
| "eval_runtime": 456.1173, | |
| "eval_samples_per_second": 6.327, | |
| "eval_steps_per_second": 0.2, | |
| "learning_rate": 0.001, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.2681912681912682, | |
| "eval_f1_macro": 0.6919100708566497, | |
| "eval_f1_micro": 0.7891243298442687, | |
| "eval_loss": 0.14226503670215607, | |
| "eval_roc_auc": 0.8571516929773072, | |
| "eval_runtime": 446.9545, | |
| "eval_samples_per_second": 6.457, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 0.001, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": 0.4282256066799164, | |
| "learning_rate": 0.001, | |
| "loss": 0.1397, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.26507276507276506, | |
| "eval_f1_macro": 0.6987715680115144, | |
| "eval_f1_micro": 0.7901946045268521, | |
| "eval_loss": 0.1439608633518219, | |
| "eval_roc_auc": 0.8629406419717581, | |
| "eval_runtime": 465.0998, | |
| "eval_samples_per_second": 6.205, | |
| "eval_steps_per_second": 0.196, | |
| "learning_rate": 0.001, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.2681912681912682, | |
| "eval_f1_macro": 0.6849790066180481, | |
| "eval_f1_micro": 0.7937821236053655, | |
| "eval_loss": 0.1425073742866516, | |
| "eval_roc_auc": 0.8647460265764118, | |
| "eval_runtime": 459.0682, | |
| "eval_samples_per_second": 6.287, | |
| "eval_steps_per_second": 0.198, | |
| "learning_rate": 0.001, | |
| "step": 1911 | |
| }, | |
| { | |
| "epoch": 7.326007326007326, | |
| "grad_norm": 0.4099022448062897, | |
| "learning_rate": 0.001, | |
| "loss": 0.1356, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.2636867636867637, | |
| "eval_f1_macro": 0.6880365824342907, | |
| "eval_f1_micro": 0.793083667950504, | |
| "eval_loss": 0.14294348657131195, | |
| "eval_roc_auc": 0.8699640457613058, | |
| "eval_runtime": 467.5382, | |
| "eval_samples_per_second": 6.173, | |
| "eval_steps_per_second": 0.195, | |
| "learning_rate": 0.001, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.25571725571725573, | |
| "eval_f1_macro": 0.6884565577441364, | |
| "eval_f1_micro": 0.7926595005517636, | |
| "eval_loss": 0.14630228281021118, | |
| "eval_roc_auc": 0.8704441778385391, | |
| "eval_runtime": 469.2736, | |
| "eval_samples_per_second": 6.15, | |
| "eval_steps_per_second": 0.194, | |
| "learning_rate": 0.001, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 9.157509157509157, | |
| "grad_norm": 0.35209059715270996, | |
| "learning_rate": 0.001, | |
| "loss": 0.1315, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.27442827442827444, | |
| "eval_f1_macro": 0.7049759390767861, | |
| "eval_f1_micro": 0.8009224940284985, | |
| "eval_loss": 0.13922064006328583, | |
| "eval_roc_auc": 0.8728939594088932, | |
| "eval_runtime": 446.1349, | |
| "eval_samples_per_second": 6.469, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 0.001, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": 0.47372138500213623, | |
| "learning_rate": 0.001, | |
| "loss": 0.1308, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.26992376992376993, | |
| "eval_f1_macro": 0.6892328865834217, | |
| "eval_f1_micro": 0.785345272946444, | |
| "eval_loss": 0.14429208636283875, | |
| "eval_roc_auc": 0.8519184223488243, | |
| "eval_runtime": 447.1698, | |
| "eval_samples_per_second": 6.454, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 0.001, | |
| "step": 3003 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.2713097713097713, | |
| "eval_f1_macro": 0.6976448599197044, | |
| "eval_f1_micro": 0.7888341543513957, | |
| "eval_loss": 0.14520499110221863, | |
| "eval_roc_auc": 0.867032334670059, | |
| "eval_runtime": 443.567, | |
| "eval_samples_per_second": 6.506, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 0.001, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 12.820512820512821, | |
| "grad_norm": 0.40755951404571533, | |
| "learning_rate": 0.001, | |
| "loss": 0.1277, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.2765072765072765, | |
| "eval_f1_macro": 0.7032121010324246, | |
| "eval_f1_micro": 0.8007200870802982, | |
| "eval_loss": 0.13695523142814636, | |
| "eval_roc_auc": 0.8680389701881897, | |
| "eval_runtime": 444.0658, | |
| "eval_samples_per_second": 6.499, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 0.001, | |
| "step": 3549 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.273042273042273, | |
| "eval_f1_macro": 0.6875097222118577, | |
| "eval_f1_micro": 0.7983576642335767, | |
| "eval_loss": 0.14012356102466583, | |
| "eval_roc_auc": 0.869430406200805, | |
| "eval_runtime": 440.0286, | |
| "eval_samples_per_second": 6.559, | |
| "eval_steps_per_second": 0.207, | |
| "learning_rate": 0.001, | |
| "step": 3822 | |
| }, | |
| { | |
| "epoch": 14.652014652014651, | |
| "grad_norm": 0.3442566990852356, | |
| "learning_rate": 0.001, | |
| "loss": 0.1257, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.2817047817047817, | |
| "eval_f1_macro": 0.7001361694791496, | |
| "eval_f1_micro": 0.8048810652595126, | |
| "eval_loss": 0.13785772025585175, | |
| "eval_roc_auc": 0.8748105574865406, | |
| "eval_runtime": 441.6171, | |
| "eval_samples_per_second": 6.535, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.001, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.2681912681912682, | |
| "eval_f1_macro": 0.7063273106998997, | |
| "eval_f1_micro": 0.7968854097268487, | |
| "eval_loss": 0.1429404616355896, | |
| "eval_roc_auc": 0.8674701731662587, | |
| "eval_runtime": 440.4364, | |
| "eval_samples_per_second": 6.553, | |
| "eval_steps_per_second": 0.207, | |
| "learning_rate": 0.001, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 16.483516483516482, | |
| "grad_norm": 0.44264066219329834, | |
| "learning_rate": 0.001, | |
| "loss": 0.1257, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.26126126126126126, | |
| "eval_f1_macro": 0.6860743816280108, | |
| "eval_f1_micro": 0.7956287718153646, | |
| "eval_loss": 0.1451471894979477, | |
| "eval_roc_auc": 0.8727966023485881, | |
| "eval_runtime": 445.5579, | |
| "eval_samples_per_second": 6.477, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 0.001, | |
| "step": 4641 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.2713097713097713, | |
| "eval_f1_macro": 0.6849355289660601, | |
| "eval_f1_micro": 0.7906203368151778, | |
| "eval_loss": 0.141770601272583, | |
| "eval_roc_auc": 0.8574113028622815, | |
| "eval_runtime": 440.4062, | |
| "eval_samples_per_second": 6.553, | |
| "eval_steps_per_second": 0.207, | |
| "learning_rate": 0.001, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 18.315018315018314, | |
| "grad_norm": 0.38295412063598633, | |
| "learning_rate": 0.001, | |
| "loss": 0.1251, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.2654192654192654, | |
| "eval_f1_macro": 0.6794374521554336, | |
| "eval_f1_micro": 0.7899699957136733, | |
| "eval_loss": 0.14384245872497559, | |
| "eval_roc_auc": 0.8555935775996669, | |
| "eval_runtime": 441.9996, | |
| "eval_samples_per_second": 6.529, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.001, | |
| "step": 5187 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.28655578655578656, | |
| "eval_f1_macro": 0.7201978132992005, | |
| "eval_f1_micro": 0.8068363147728227, | |
| "eval_loss": 0.13193023204803467, | |
| "eval_roc_auc": 0.8705382753554913, | |
| "eval_runtime": 445.6167, | |
| "eval_samples_per_second": 6.476, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 0.0001, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 20.146520146520146, | |
| "grad_norm": 0.34160131216049194, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1161, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.2875952875952876, | |
| "eval_f1_macro": 0.7236910659256566, | |
| "eval_f1_micro": 0.8080536912751679, | |
| "eval_loss": 0.13121400773525238, | |
| "eval_roc_auc": 0.8715230464470173, | |
| "eval_runtime": 442.006, | |
| "eval_samples_per_second": 6.529, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.0001, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 21.978021978021978, | |
| "grad_norm": 0.25530439615249634, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1109, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.2934857934857935, | |
| "eval_f1_macro": 0.7222147145142929, | |
| "eval_f1_micro": 0.810120343368793, | |
| "eval_loss": 0.1310088187456131, | |
| "eval_roc_auc": 0.8788407212738992, | |
| "eval_runtime": 442.6084, | |
| "eval_samples_per_second": 6.52, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.0001, | |
| "step": 6006 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.2934857934857935, | |
| "eval_f1_macro": 0.7226400439644629, | |
| "eval_f1_micro": 0.8120394137616957, | |
| "eval_loss": 0.1304517388343811, | |
| "eval_roc_auc": 0.8775576952587192, | |
| "eval_runtime": 443.2768, | |
| "eval_samples_per_second": 6.511, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 0.0001, | |
| "step": 6279 | |
| }, | |
| { | |
| "epoch": 23.80952380952381, | |
| "grad_norm": 0.31216299533843994, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1103, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.29521829521829523, | |
| "eval_f1_macro": 0.7237916982943077, | |
| "eval_f1_micro": 0.8096162584162916, | |
| "eval_loss": 0.13093852996826172, | |
| "eval_roc_auc": 0.8768767860419646, | |
| "eval_runtime": 445.0523, | |
| "eval_samples_per_second": 6.485, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 0.0001, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.2948717948717949, | |
| "eval_f1_macro": 0.7170657451815683, | |
| "eval_f1_micro": 0.8093388464269307, | |
| "eval_loss": 0.13081994652748108, | |
| "eval_roc_auc": 0.8734838965144617, | |
| "eval_runtime": 438.7401, | |
| "eval_samples_per_second": 6.578, | |
| "eval_steps_per_second": 0.207, | |
| "learning_rate": 0.0001, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 0.38898253440856934, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1099, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.2910602910602911, | |
| "eval_f1_macro": 0.7200172245050901, | |
| "eval_f1_micro": 0.8099862459884133, | |
| "eval_loss": 0.13007444143295288, | |
| "eval_roc_auc": 0.8744510016858411, | |
| "eval_runtime": 440.3465, | |
| "eval_samples_per_second": 6.554, | |
| "eval_steps_per_second": 0.207, | |
| "learning_rate": 0.0001, | |
| "step": 7098 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.29244629244629244, | |
| "eval_f1_macro": 0.7207907434740295, | |
| "eval_f1_micro": 0.8082065853250877, | |
| "eval_loss": 0.13034380972385406, | |
| "eval_roc_auc": 0.8727246375334137, | |
| "eval_runtime": 441.8582, | |
| "eval_samples_per_second": 6.532, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.0001, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 27.47252747252747, | |
| "grad_norm": 0.23454292118549347, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1107, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.29695079695079696, | |
| "eval_f1_macro": 0.7217805682073449, | |
| "eval_f1_micro": 0.810349848163401, | |
| "eval_loss": 0.13018907606601715, | |
| "eval_roc_auc": 0.8752133458313793, | |
| "eval_runtime": 442.3473, | |
| "eval_samples_per_second": 6.524, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.0001, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.29625779625779625, | |
| "eval_f1_macro": 0.723719101965087, | |
| "eval_f1_micro": 0.8104190823256585, | |
| "eval_loss": 0.13019531965255737, | |
| "eval_roc_auc": 0.8765812809388343, | |
| "eval_runtime": 443.3045, | |
| "eval_samples_per_second": 6.51, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 0.0001, | |
| "step": 7917 | |
| }, | |
| { | |
| "epoch": 29.304029304029303, | |
| "grad_norm": 0.30432701110839844, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1103, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.718144679800513, | |
| "eval_f1_micro": 0.8096606287736832, | |
| "eval_loss": 0.13030356168746948, | |
| "eval_roc_auc": 0.87453866059864, | |
| "eval_runtime": 441.0327, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 0.0001, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.2959112959112959, | |
| "eval_f1_macro": 0.7189603352791966, | |
| "eval_f1_micro": 0.8092418049879057, | |
| "eval_loss": 0.1301266849040985, | |
| "eval_roc_auc": 0.8738562356271575, | |
| "eval_runtime": 443.1469, | |
| "eval_samples_per_second": 6.513, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 0.0001, | |
| "step": 8463 | |
| }, | |
| { | |
| "epoch": 31.135531135531135, | |
| "grad_norm": 0.3088095188140869, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1104, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.2927927927927928, | |
| "eval_f1_macro": 0.7210148516296496, | |
| "eval_f1_micro": 0.8097980303789017, | |
| "eval_loss": 0.1301257312297821, | |
| "eval_roc_auc": 0.8739934717919385, | |
| "eval_runtime": 440.0353, | |
| "eval_samples_per_second": 6.559, | |
| "eval_steps_per_second": 0.207, | |
| "learning_rate": 0.0001, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 32.967032967032964, | |
| "grad_norm": 0.3049701750278473, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1093, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.29625779625779625, | |
| "eval_f1_macro": 0.7204264964359948, | |
| "eval_f1_micro": 0.8099594769603543, | |
| "eval_loss": 0.12959885597229004, | |
| "eval_roc_auc": 0.8737537142697711, | |
| "eval_runtime": 441.033, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 1e-05, | |
| "step": 9009 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.722168676552786, | |
| "eval_f1_micro": 0.8100854344655136, | |
| "eval_loss": 0.12959957122802734, | |
| "eval_roc_auc": 0.874530303826999, | |
| "eval_runtime": 444.1246, | |
| "eval_samples_per_second": 6.498, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 1e-05, | |
| "step": 9282 | |
| }, | |
| { | |
| "epoch": 34.798534798534796, | |
| "grad_norm": 0.3583316504955292, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1084, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7220033007887567, | |
| "eval_f1_micro": 0.8108894430590192, | |
| "eval_loss": 0.12954092025756836, | |
| "eval_roc_auc": 0.875769077852382, | |
| "eval_runtime": 441.2982, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 1e-05, | |
| "step": 9555 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.29313929313929316, | |
| "eval_f1_macro": 0.7211650841899886, | |
| "eval_f1_micro": 0.8104569713142095, | |
| "eval_loss": 0.12953610718250275, | |
| "eval_roc_auc": 0.8746018662294139, | |
| "eval_runtime": 447.4449, | |
| "eval_samples_per_second": 6.45, | |
| "eval_steps_per_second": 0.203, | |
| "learning_rate": 1e-05, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 36.63003663003663, | |
| "grad_norm": 0.3639417588710785, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1091, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.29625779625779625, | |
| "eval_f1_macro": 0.7239071903959954, | |
| "eval_f1_micro": 0.8118778893007372, | |
| "eval_loss": 0.1295497566461563, | |
| "eval_roc_auc": 0.8757186018785701, | |
| "eval_runtime": 444.3576, | |
| "eval_samples_per_second": 6.495, | |
| "eval_steps_per_second": 0.205, | |
| "learning_rate": 1e-05, | |
| "step": 10101 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.2959112959112959, | |
| "eval_f1_macro": 0.7212977755433345, | |
| "eval_f1_micro": 0.8104318798247445, | |
| "eval_loss": 0.12949061393737793, | |
| "eval_roc_auc": 0.8743562200671975, | |
| "eval_runtime": 450.6653, | |
| "eval_samples_per_second": 6.404, | |
| "eval_steps_per_second": 0.202, | |
| "learning_rate": 1e-05, | |
| "step": 10374 | |
| }, | |
| { | |
| "epoch": 38.46153846153846, | |
| "grad_norm": 0.30328261852264404, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1075, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.2966042966042966, | |
| "eval_f1_macro": 0.7221707642640621, | |
| "eval_f1_micro": 0.8106218263547823, | |
| "eval_loss": 0.12945865094661713, | |
| "eval_roc_auc": 0.8752056060926364, | |
| "eval_runtime": 456.2278, | |
| "eval_samples_per_second": 6.326, | |
| "eval_steps_per_second": 0.199, | |
| "learning_rate": 1e-05, | |
| "step": 10647 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7232749192333074, | |
| "eval_f1_micro": 0.8113418729013804, | |
| "eval_loss": 0.12946291267871857, | |
| "eval_roc_auc": 0.8767900795060302, | |
| "eval_runtime": 456.1604, | |
| "eval_samples_per_second": 6.327, | |
| "eval_steps_per_second": 0.199, | |
| "learning_rate": 1e-05, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 40.29304029304029, | |
| "grad_norm": 0.3177196681499481, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1088, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.2945252945252945, | |
| "eval_f1_macro": 0.722313917509489, | |
| "eval_f1_micro": 0.8100071001962995, | |
| "eval_loss": 0.1294611394405365, | |
| "eval_roc_auc": 0.8738531504626673, | |
| "eval_runtime": 455.3171, | |
| "eval_samples_per_second": 6.338, | |
| "eval_steps_per_second": 0.2, | |
| "learning_rate": 1e-05, | |
| "step": 11193 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.2972972972972973, | |
| "eval_f1_macro": 0.7219276596712088, | |
| "eval_f1_micro": 0.8111398315684148, | |
| "eval_loss": 0.12951640784740448, | |
| "eval_roc_auc": 0.8750042655752517, | |
| "eval_runtime": 453.9232, | |
| "eval_samples_per_second": 6.358, | |
| "eval_steps_per_second": 0.2, | |
| "learning_rate": 1e-05, | |
| "step": 11466 | |
| }, | |
| { | |
| "epoch": 42.124542124542124, | |
| "grad_norm": 0.3328670561313629, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1085, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.29313929313929316, | |
| "eval_f1_macro": 0.7212066160587719, | |
| "eval_f1_micro": 0.8097862391449566, | |
| "eval_loss": 0.12940654158592224, | |
| "eval_roc_auc": 0.8738407561496718, | |
| "eval_runtime": 457.3356, | |
| "eval_samples_per_second": 6.31, | |
| "eval_steps_per_second": 0.199, | |
| "learning_rate": 1e-05, | |
| "step": 11739 | |
| }, | |
| { | |
| "epoch": 43.956043956043956, | |
| "grad_norm": 0.2574955224990845, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1084, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.29695079695079696, | |
| "eval_f1_macro": 0.7211905265653523, | |
| "eval_f1_micro": 0.8108311081441923, | |
| "eval_loss": 0.12948854267597198, | |
| "eval_roc_auc": 0.8746136435095113, | |
| "eval_runtime": 457.7561, | |
| "eval_samples_per_second": 6.305, | |
| "eval_steps_per_second": 0.199, | |
| "learning_rate": 1e-05, | |
| "step": 12012 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.2945252945252945, | |
| "eval_f1_macro": 0.7217673828508766, | |
| "eval_f1_micro": 0.8103943697164036, | |
| "eval_loss": 0.12943118810653687, | |
| "eval_roc_auc": 0.8749209258927392, | |
| "eval_runtime": 454.0903, | |
| "eval_samples_per_second": 6.356, | |
| "eval_steps_per_second": 0.2, | |
| "learning_rate": 1e-05, | |
| "step": 12285 | |
| }, | |
| { | |
| "epoch": 45.78754578754579, | |
| "grad_norm": 0.35246723890304565, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1083, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.29764379764379767, | |
| "eval_f1_macro": 0.7232663108413819, | |
| "eval_f1_micro": 0.8113435070065285, | |
| "eval_loss": 0.12941767275333405, | |
| "eval_roc_auc": 0.8758867969983227, | |
| "eval_runtime": 464.2204, | |
| "eval_samples_per_second": 6.217, | |
| "eval_steps_per_second": 0.196, | |
| "learning_rate": 1e-05, | |
| "step": 12558 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.2945252945252945, | |
| "eval_f1_macro": 0.7229077354567445, | |
| "eval_f1_micro": 0.8107185952648442, | |
| "eval_loss": 0.12936843931674957, | |
| "eval_roc_auc": 0.8753446933561116, | |
| "eval_runtime": 462.6765, | |
| "eval_samples_per_second": 6.238, | |
| "eval_steps_per_second": 0.197, | |
| "learning_rate": 1e-05, | |
| "step": 12831 | |
| }, | |
| { | |
| "epoch": 47.61904761904762, | |
| "grad_norm": 0.23883384466171265, | |
| "learning_rate": 1e-05, | |
| "loss": 0.109, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7208766406208041, | |
| "eval_f1_micro": 0.8102512730611904, | |
| "eval_loss": 0.12944123148918152, | |
| "eval_roc_auc": 0.8741709760601966, | |
| "eval_runtime": 461.7262, | |
| "eval_samples_per_second": 6.25, | |
| "eval_steps_per_second": 0.197, | |
| "learning_rate": 1e-05, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.2959112959112959, | |
| "eval_f1_macro": 0.7215165769975259, | |
| "eval_f1_micro": 0.8111032502392942, | |
| "eval_loss": 0.12932655215263367, | |
| "eval_roc_auc": 0.875509186278476, | |
| "eval_runtime": 467.4634, | |
| "eval_samples_per_second": 6.174, | |
| "eval_steps_per_second": 0.195, | |
| "learning_rate": 1e-05, | |
| "step": 13377 | |
| }, | |
| { | |
| "epoch": 49.45054945054945, | |
| "grad_norm": 0.37183043360710144, | |
| "learning_rate": 1e-05, | |
| "loss": 0.108, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.2966042966042966, | |
| "eval_f1_macro": 0.7210862927892402, | |
| "eval_f1_micro": 0.8106959890041235, | |
| "eval_loss": 0.1294257938861847, | |
| "eval_roc_auc": 0.8750392620715779, | |
| "eval_runtime": 461.0793, | |
| "eval_samples_per_second": 6.259, | |
| "eval_steps_per_second": 0.197, | |
| "learning_rate": 1e-05, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.29244629244629244, | |
| "eval_f1_macro": 0.7224236625273444, | |
| "eval_f1_micro": 0.8098573930447837, | |
| "eval_loss": 0.12937645614147186, | |
| "eval_roc_auc": 0.8742456236271018, | |
| "eval_runtime": 450.9312, | |
| "eval_samples_per_second": 6.4, | |
| "eval_steps_per_second": 0.202, | |
| "learning_rate": 1e-05, | |
| "step": 13923 | |
| }, | |
| { | |
| "epoch": 51.282051282051285, | |
| "grad_norm": 0.2766432762145996, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1084, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.2972972972972973, | |
| "eval_f1_macro": 0.7223932851056244, | |
| "eval_f1_micro": 0.8110019973368842, | |
| "eval_loss": 0.12941104173660278, | |
| "eval_roc_auc": 0.8754896692596356, | |
| "eval_runtime": 461.8073, | |
| "eval_samples_per_second": 6.249, | |
| "eval_steps_per_second": 0.197, | |
| "learning_rate": 1e-05, | |
| "step": 14196 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.29799029799029797, | |
| "eval_f1_macro": 0.7225026360610024, | |
| "eval_f1_micro": 0.8110783049860689, | |
| "eval_loss": 0.12947481870651245, | |
| "eval_roc_auc": 0.8757151813701134, | |
| "eval_runtime": 469.6848, | |
| "eval_samples_per_second": 6.145, | |
| "eval_steps_per_second": 0.194, | |
| "learning_rate": 1e-05, | |
| "step": 14469 | |
| }, | |
| { | |
| "epoch": 53.11355311355312, | |
| "grad_norm": 0.3167434334754944, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1086, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.29625779625779625, | |
| "eval_f1_macro": 0.7221711249170111, | |
| "eval_f1_micro": 0.8104531646623112, | |
| "eval_loss": 0.12942463159561157, | |
| "eval_roc_auc": 0.8751730777279024, | |
| "eval_runtime": 467.6515, | |
| "eval_samples_per_second": 6.171, | |
| "eval_steps_per_second": 0.195, | |
| "learning_rate": 1e-05, | |
| "step": 14742 | |
| }, | |
| { | |
| "epoch": 54.94505494505494, | |
| "grad_norm": 0.39026910066604614, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1083, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7231230527181782, | |
| "eval_f1_micro": 0.8107163657542226, | |
| "eval_loss": 0.12934881448745728, | |
| "eval_roc_auc": 0.875404478478429, | |
| "eval_runtime": 485.1549, | |
| "eval_samples_per_second": 5.949, | |
| "eval_steps_per_second": 0.188, | |
| "learning_rate": 1e-05, | |
| "step": 15015 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.2959112959112959, | |
| "eval_f1_macro": 0.7226955143721722, | |
| "eval_f1_micro": 0.810738813735692, | |
| "eval_loss": 0.12935101985931396, | |
| "eval_roc_auc": 0.875258268509109, | |
| "eval_runtime": 477.6234, | |
| "eval_samples_per_second": 6.042, | |
| "eval_steps_per_second": 0.191, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 56.776556776556774, | |
| "grad_norm": 0.2914769947528839, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.108, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7230703100391168, | |
| "eval_f1_micro": 0.8110560712650376, | |
| "eval_loss": 0.12934598326683044, | |
| "eval_roc_auc": 0.8754097500855798, | |
| "eval_runtime": 449.1576, | |
| "eval_samples_per_second": 6.425, | |
| "eval_steps_per_second": 0.203, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 15561 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.2966042966042966, | |
| "eval_f1_macro": 0.7230017316798248, | |
| "eval_f1_micro": 0.8112406328059951, | |
| "eval_loss": 0.1293543428182602, | |
| "eval_roc_auc": 0.875475423847946, | |
| "eval_runtime": 441.9495, | |
| "eval_samples_per_second": 6.53, | |
| "eval_steps_per_second": 0.206, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 15834 | |
| }, | |
| { | |
| "epoch": 58.608058608058606, | |
| "grad_norm": 0.25508466362953186, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1089, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.2966042966042966, | |
| "eval_f1_macro": 0.7227156089091311, | |
| "eval_f1_micro": 0.8110088687179914, | |
| "eval_loss": 0.12936049699783325, | |
| "eval_roc_auc": 0.8753103138926834, | |
| "eval_runtime": 445.121, | |
| "eval_samples_per_second": 6.484, | |
| "eval_steps_per_second": 0.204, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 16107 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 16107, | |
| "total_flos": 2.151593295698903e+20, | |
| "train_loss": 0.11777938241923686, | |
| "train_runtime": 108362.28, | |
| "train_samples_per_second": 12.065, | |
| "train_steps_per_second": 0.378 | |
| } | |
| ], | |
| "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": 2.151593295698903e+20, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |