| { | |
| "best_metric": 0.10334235429763794, | |
| "best_model_checkpoint": "/home1/datahome/mcontini/multilabelTest/huggingface_multilabel/models/dino-large-2023_12_08-with_custom_head-imgsize1036/checkpoint-26264", | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 26800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.01, | |
| "loss": 0.2502, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4030010718113612, | |
| "eval_f1_macro": 0.5121125903883165, | |
| "eval_f1_micro": 0.6426868905742146, | |
| "eval_loss": 0.19902026653289795, | |
| "eval_roc_auc": 0.7509953312991865, | |
| "eval_runtime": 684.3444, | |
| "eval_samples_per_second": 4.09, | |
| "eval_steps_per_second": 0.256, | |
| "learning_rate": 0.01, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.01, | |
| "loss": 0.2164, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4047874240800286, | |
| "eval_f1_macro": 0.6295963337884725, | |
| "eval_f1_micro": 0.6769131832797427, | |
| "eval_loss": 1.1450586318969727, | |
| "eval_roc_auc": 0.7895166431869363, | |
| "eval_runtime": 697.1722, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 0.251, | |
| "learning_rate": 0.01, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.01, | |
| "loss": 0.2149, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3994283672740264, | |
| "eval_f1_macro": 0.5251308791060187, | |
| "eval_f1_micro": 0.651589690873045, | |
| "eval_loss": 0.2338775098323822, | |
| "eval_roc_auc": 0.7524284144947219, | |
| "eval_runtime": 691.846, | |
| "eval_samples_per_second": 4.046, | |
| "eval_steps_per_second": 0.253, | |
| "learning_rate": 0.01, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.01, | |
| "loss": 0.2159, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4115755627009646, | |
| "eval_f1_macro": 0.6028196862535703, | |
| "eval_f1_micro": 0.7376345424002986, | |
| "eval_loss": 0.16987967491149902, | |
| "eval_roc_auc": 0.8296525341756016, | |
| "eval_runtime": 692.4855, | |
| "eval_samples_per_second": 4.042, | |
| "eval_steps_per_second": 0.253, | |
| "learning_rate": 0.01, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.01, | |
| "loss": 0.2171, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.43944265809217575, | |
| "eval_f1_macro": 0.63036934398975, | |
| "eval_f1_micro": 0.7363523166655744, | |
| "eval_loss": 0.16497960686683655, | |
| "eval_roc_auc": 0.8166227130928913, | |
| "eval_runtime": 679.5828, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 0.258, | |
| "learning_rate": 0.01, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.01, | |
| "loss": 0.2166, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.39228295819935693, | |
| "eval_f1_macro": 0.5122569229120599, | |
| "eval_f1_micro": 0.6852550663871418, | |
| "eval_loss": 0.1748417615890503, | |
| "eval_roc_auc": 0.7773210612716831, | |
| "eval_runtime": 677.7081, | |
| "eval_samples_per_second": 4.13, | |
| "eval_steps_per_second": 0.258, | |
| "learning_rate": 0.01, | |
| "step": 3216 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.01, | |
| "loss": 0.2081, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4347981421936406, | |
| "eval_f1_macro": 0.6129188202062517, | |
| "eval_f1_micro": 0.7454787740338855, | |
| "eval_loss": 0.1636398434638977, | |
| "eval_roc_auc": 0.8290983004904813, | |
| "eval_runtime": 695.4612, | |
| "eval_samples_per_second": 4.025, | |
| "eval_steps_per_second": 0.252, | |
| "learning_rate": 0.01, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 0.01, | |
| "loss": 0.2111, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.42765273311897106, | |
| "eval_f1_macro": 0.6444819502221721, | |
| "eval_f1_micro": 0.7542994588093808, | |
| "eval_loss": 0.16511820256710052, | |
| "eval_roc_auc": 0.847560960415324, | |
| "eval_runtime": 698.6301, | |
| "eval_samples_per_second": 4.006, | |
| "eval_steps_per_second": 0.25, | |
| "learning_rate": 0.01, | |
| "step": 4288 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 0.01, | |
| "loss": 0.209, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.43586995355484104, | |
| "eval_f1_macro": 0.6522075091299645, | |
| "eval_f1_micro": 0.7062128001070019, | |
| "eval_loss": 0.1750405728816986, | |
| "eval_roc_auc": 0.7966230241843142, | |
| "eval_runtime": 689.5145, | |
| "eval_samples_per_second": 4.059, | |
| "eval_steps_per_second": 0.254, | |
| "learning_rate": 0.01, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.01, | |
| "loss": 0.2107, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.3829939264022865, | |
| "eval_f1_macro": 0.5923770104096581, | |
| "eval_f1_micro": 0.7244064088539991, | |
| "eval_loss": 0.17505380511283875, | |
| "eval_roc_auc": 0.8145635827712373, | |
| "eval_runtime": 706.021, | |
| "eval_samples_per_second": 3.964, | |
| "eval_steps_per_second": 0.248, | |
| "learning_rate": 0.01, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 0.01, | |
| "loss": 0.2162, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.42515183994283673, | |
| "eval_f1_macro": 0.678019114323704, | |
| "eval_f1_micro": 0.7505816381315993, | |
| "eval_loss": 0.22285762429237366, | |
| "eval_roc_auc": 0.8475316447819295, | |
| "eval_runtime": 709.1839, | |
| "eval_samples_per_second": 3.947, | |
| "eval_steps_per_second": 0.247, | |
| "learning_rate": 0.01, | |
| "step": 5896 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.01, | |
| "loss": 0.2153, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4105037513397642, | |
| "eval_f1_macro": 0.6543045937545326, | |
| "eval_f1_micro": 0.7501448603546181, | |
| "eval_loss": 0.1740036904811859, | |
| "eval_roc_auc": 0.8550110327013883, | |
| "eval_runtime": 710.4504, | |
| "eval_samples_per_second": 3.94, | |
| "eval_steps_per_second": 0.246, | |
| "learning_rate": 0.01, | |
| "step": 6432 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 0.01, | |
| "loss": 0.2197, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.41872097177563417, | |
| "eval_f1_macro": 0.6605308887240204, | |
| "eval_f1_micro": 0.748710897215538, | |
| "eval_loss": 0.1744571030139923, | |
| "eval_roc_auc": 0.857218077620948, | |
| "eval_runtime": 687.247, | |
| "eval_samples_per_second": 4.073, | |
| "eval_steps_per_second": 0.255, | |
| "learning_rate": 0.01, | |
| "step": 6968 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.001, | |
| "loss": 0.2128, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.18, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5058949624866024, | |
| "eval_f1_macro": 0.7455097936778116, | |
| "eval_f1_micro": 0.8036385688295937, | |
| "eval_loss": 0.13480359315872192, | |
| "eval_roc_auc": 0.8730946172404269, | |
| "eval_runtime": 700.8684, | |
| "eval_samples_per_second": 3.994, | |
| "eval_steps_per_second": 0.25, | |
| "learning_rate": 0.001, | |
| "step": 7504 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.164, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5173276170060735, | |
| "eval_f1_macro": 0.7782933504010985, | |
| "eval_f1_micro": 0.8159655831739961, | |
| "eval_loss": 0.13084079325199127, | |
| "eval_roc_auc": 0.8844182661393802, | |
| "eval_runtime": 699.1842, | |
| "eval_samples_per_second": 4.003, | |
| "eval_steps_per_second": 0.25, | |
| "learning_rate": 0.001, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.162, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5201857806359415, | |
| "eval_f1_macro": 0.7530230371766228, | |
| "eval_f1_micro": 0.8187878039748179, | |
| "eval_loss": 0.1304706484079361, | |
| "eval_roc_auc": 0.8764409254464951, | |
| "eval_runtime": 704.2301, | |
| "eval_samples_per_second": 3.975, | |
| "eval_steps_per_second": 0.248, | |
| "learning_rate": 0.001, | |
| "step": 8576 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.1548, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5248302965344765, | |
| "eval_f1_macro": 0.788713547954132, | |
| "eval_f1_micro": 0.829077551987677, | |
| "eval_loss": 0.12419470399618149, | |
| "eval_roc_auc": 0.8945177280625883, | |
| "eval_runtime": 725.0968, | |
| "eval_samples_per_second": 3.86, | |
| "eval_steps_per_second": 0.241, | |
| "learning_rate": 0.001, | |
| "step": 9112 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 0.001, | |
| "loss": 0.1532, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5226866738120758, | |
| "eval_f1_macro": 0.782300591476402, | |
| "eval_f1_micro": 0.8292102759276879, | |
| "eval_loss": 0.12466239929199219, | |
| "eval_roc_auc": 0.8934405856125267, | |
| "eval_runtime": 737.9752, | |
| "eval_samples_per_second": 3.793, | |
| "eval_steps_per_second": 0.237, | |
| "learning_rate": 0.001, | |
| "step": 9648 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 0.001, | |
| "loss": 0.152, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5280457306180779, | |
| "eval_f1_macro": 0.7687831529578533, | |
| "eval_f1_micro": 0.8237944471505114, | |
| "eval_loss": 0.1271921843290329, | |
| "eval_roc_auc": 0.8832304052589448, | |
| "eval_runtime": 742.4217, | |
| "eval_samples_per_second": 3.77, | |
| "eval_steps_per_second": 0.236, | |
| "learning_rate": 0.001, | |
| "step": 10184 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 0.001, | |
| "loss": 0.1479, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5287602715255448, | |
| "eval_f1_macro": 0.7783155153237968, | |
| "eval_f1_micro": 0.8279668813247469, | |
| "eval_loss": 0.12385135143995285, | |
| "eval_roc_auc": 0.8833930136365329, | |
| "eval_runtime": 714.6841, | |
| "eval_samples_per_second": 3.916, | |
| "eval_steps_per_second": 0.245, | |
| "learning_rate": 0.001, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 20.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.1483, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.534119328331547, | |
| "eval_f1_macro": 0.791367242205616, | |
| "eval_f1_micro": 0.8361280949209999, | |
| "eval_loss": 0.1375582218170166, | |
| "eval_roc_auc": 0.8918987306282016, | |
| "eval_runtime": 704.0932, | |
| "eval_samples_per_second": 3.975, | |
| "eval_steps_per_second": 0.249, | |
| "learning_rate": 0.001, | |
| "step": 11256 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.1448, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5380493033226152, | |
| "eval_f1_macro": 0.7773902467356547, | |
| "eval_f1_micro": 0.8291756052712227, | |
| "eval_loss": 0.12673501670360565, | |
| "eval_roc_auc": 0.8842480463699955, | |
| "eval_runtime": 694.3206, | |
| "eval_samples_per_second": 4.031, | |
| "eval_steps_per_second": 0.252, | |
| "learning_rate": 0.001, | |
| "step": 11792 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 0.001, | |
| "loss": 0.1456, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5448374419435512, | |
| "eval_f1_macro": 0.7913781838771046, | |
| "eval_f1_micro": 0.8334247577253612, | |
| "eval_loss": 0.12168043851852417, | |
| "eval_roc_auc": 0.8883093845683582, | |
| "eval_runtime": 716.6426, | |
| "eval_samples_per_second": 3.906, | |
| "eval_steps_per_second": 0.244, | |
| "learning_rate": 0.001, | |
| "step": 12328 | |
| }, | |
| { | |
| "epoch": 23.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.1441, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5380493033226152, | |
| "eval_f1_macro": 0.7852190635254378, | |
| "eval_f1_micro": 0.8282665343094677, | |
| "eval_loss": 0.11930090188980103, | |
| "eval_roc_auc": 0.8801416627925638, | |
| "eval_runtime": 736.3569, | |
| "eval_samples_per_second": 3.801, | |
| "eval_steps_per_second": 0.238, | |
| "learning_rate": 0.001, | |
| "step": 12864 | |
| }, | |
| { | |
| "epoch": 24.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.1406, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.534119328331547, | |
| "eval_f1_macro": 0.8019722412424143, | |
| "eval_f1_micro": 0.8392282958199356, | |
| "eval_loss": 0.11846613883972168, | |
| "eval_roc_auc": 0.89877394155691, | |
| "eval_runtime": 732.3109, | |
| "eval_samples_per_second": 3.822, | |
| "eval_steps_per_second": 0.239, | |
| "learning_rate": 0.001, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 25.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.1416, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5441229010360843, | |
| "eval_f1_macro": 0.7850806686320094, | |
| "eval_f1_micro": 0.8350723045945452, | |
| "eval_loss": 0.1295102834701538, | |
| "eval_roc_auc": 0.888897831813434, | |
| "eval_runtime": 736.4837, | |
| "eval_samples_per_second": 3.8, | |
| "eval_steps_per_second": 0.238, | |
| "learning_rate": 0.001, | |
| "step": 13936 | |
| }, | |
| { | |
| "epoch": 26.12, | |
| "learning_rate": 0.001, | |
| "loss": 0.1417, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5305466237942122, | |
| "eval_f1_macro": 0.7699298453614014, | |
| "eval_f1_micro": 0.8287484510532839, | |
| "eval_loss": 0.1389976292848587, | |
| "eval_roc_auc": 0.8808089652631531, | |
| "eval_runtime": 714.8246, | |
| "eval_samples_per_second": 3.916, | |
| "eval_steps_per_second": 0.245, | |
| "learning_rate": 0.001, | |
| "step": 14472 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.1452, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.142, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5441229010360843, | |
| "eval_f1_macro": 0.7857164640115839, | |
| "eval_f1_micro": 0.8328267477203647, | |
| "eval_loss": 0.12560133635997772, | |
| "eval_roc_auc": 0.888767490354217, | |
| "eval_runtime": 711.9043, | |
| "eval_samples_per_second": 3.932, | |
| "eval_steps_per_second": 0.246, | |
| "learning_rate": 0.001, | |
| "step": 15008 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 0.001, | |
| "loss": 0.14, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5359056806002144, | |
| "eval_f1_macro": 0.7758987493304471, | |
| "eval_f1_micro": 0.8291174469664172, | |
| "eval_loss": 0.12682993710041046, | |
| "eval_roc_auc": 0.8815429141058391, | |
| "eval_runtime": 725.5421, | |
| "eval_samples_per_second": 3.858, | |
| "eval_steps_per_second": 0.241, | |
| "learning_rate": 0.001, | |
| "step": 15544 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.1415, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5419792783136834, | |
| "eval_f1_macro": 0.7674795938272058, | |
| "eval_f1_micro": 0.8239833027638985, | |
| "eval_loss": 0.13736343383789062, | |
| "eval_roc_auc": 0.8722214417609943, | |
| "eval_runtime": 716.5365, | |
| "eval_samples_per_second": 3.906, | |
| "eval_steps_per_second": 0.244, | |
| "learning_rate": 0.001, | |
| "step": 16080 | |
| }, | |
| { | |
| "epoch": 30.78, | |
| "learning_rate": 0.001, | |
| "loss": 0.1414, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5405501964987496, | |
| "eval_f1_macro": 0.7795434508186554, | |
| "eval_f1_micro": 0.8309928553830993, | |
| "eval_loss": 0.12812598049640656, | |
| "eval_roc_auc": 0.8838076169713958, | |
| "eval_runtime": 695.9054, | |
| "eval_samples_per_second": 4.022, | |
| "eval_steps_per_second": 0.251, | |
| "learning_rate": 0.001, | |
| "step": 16616 | |
| }, | |
| { | |
| "epoch": 31.72, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1349, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5512683101107538, | |
| "eval_f1_macro": 0.7927055189210745, | |
| "eval_f1_micro": 0.8388680866736234, | |
| "eval_loss": 0.11437654495239258, | |
| "eval_roc_auc": 0.8891921900071421, | |
| "eval_runtime": 701.3503, | |
| "eval_samples_per_second": 3.991, | |
| "eval_steps_per_second": 0.25, | |
| "learning_rate": 0.0001, | |
| "step": 17152 | |
| }, | |
| { | |
| "epoch": 32.65, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1294, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5534119328331547, | |
| "eval_f1_macro": 0.7990834574660737, | |
| "eval_f1_micro": 0.8414029503580829, | |
| "eval_loss": 0.10969647765159607, | |
| "eval_roc_auc": 0.8914615216569188, | |
| "eval_runtime": 698.1361, | |
| "eval_samples_per_second": 4.009, | |
| "eval_steps_per_second": 0.251, | |
| "learning_rate": 0.0001, | |
| "step": 17688 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1281, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.5519828510182208, | |
| "eval_f1_macro": 0.7981650632699254, | |
| "eval_f1_micro": 0.8424912902634313, | |
| "eval_loss": 0.11602061241865158, | |
| "eval_roc_auc": 0.8925180364347453, | |
| "eval_runtime": 712.6765, | |
| "eval_samples_per_second": 3.927, | |
| "eval_steps_per_second": 0.246, | |
| "learning_rate": 0.0001, | |
| "step": 18224 | |
| }, | |
| { | |
| "epoch": 34.51, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1274, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5576991782779565, | |
| "eval_f1_macro": 0.7999145597601702, | |
| "eval_f1_micro": 0.8441375939390237, | |
| "eval_loss": 0.12442068755626678, | |
| "eval_roc_auc": 0.893549294756116, | |
| "eval_runtime": 707.8053, | |
| "eval_samples_per_second": 3.954, | |
| "eval_steps_per_second": 0.247, | |
| "learning_rate": 0.0001, | |
| "step": 18760 | |
| }, | |
| { | |
| "epoch": 35.45, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1243, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.555912826009289, | |
| "eval_f1_macro": 0.7991433380498747, | |
| "eval_f1_micro": 0.8434315360385399, | |
| "eval_loss": 0.10998840630054474, | |
| "eval_roc_auc": 0.889847418195485, | |
| "eval_runtime": 712.761, | |
| "eval_samples_per_second": 3.927, | |
| "eval_steps_per_second": 0.246, | |
| "learning_rate": 0.0001, | |
| "step": 19296 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1231, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.564130046445159, | |
| "eval_f1_macro": 0.8086403056854424, | |
| "eval_f1_micro": 0.8485288775880857, | |
| "eval_loss": 0.10725793987512589, | |
| "eval_roc_auc": 0.8988640009924486, | |
| "eval_runtime": 714.0011, | |
| "eval_samples_per_second": 3.92, | |
| "eval_steps_per_second": 0.245, | |
| "learning_rate": 0.0001, | |
| "step": 19832 | |
| }, | |
| { | |
| "epoch": 37.31, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1245, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5602000714540908, | |
| "eval_f1_macro": 0.8053806942991502, | |
| "eval_f1_micro": 0.8455705566857777, | |
| "eval_loss": 0.1091923713684082, | |
| "eval_roc_auc": 0.8915942447938312, | |
| "eval_runtime": 713.3543, | |
| "eval_samples_per_second": 3.924, | |
| "eval_steps_per_second": 0.245, | |
| "learning_rate": 0.0001, | |
| "step": 20368 | |
| }, | |
| { | |
| "epoch": 38.25, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1197, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5623436941764915, | |
| "eval_f1_macro": 0.8111886307990975, | |
| "eval_f1_micro": 0.8482584066530071, | |
| "eval_loss": 0.10690516978502274, | |
| "eval_roc_auc": 0.9001525872337657, | |
| "eval_runtime": 742.3723, | |
| "eval_samples_per_second": 3.77, | |
| "eval_steps_per_second": 0.236, | |
| "learning_rate": 0.0001, | |
| "step": 20904 | |
| }, | |
| { | |
| "epoch": 39.18, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1242, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5637727759914255, | |
| "eval_f1_macro": 0.8080882298039329, | |
| "eval_f1_micro": 0.8468215158924205, | |
| "eval_loss": 0.10654206573963165, | |
| "eval_roc_auc": 0.8949146236875923, | |
| "eval_runtime": 748.0644, | |
| "eval_samples_per_second": 3.742, | |
| "eval_steps_per_second": 0.234, | |
| "learning_rate": 0.0001, | |
| "step": 21440 | |
| }, | |
| { | |
| "epoch": 40.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1167, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5591282600928903, | |
| "eval_f1_macro": 0.8043452814541342, | |
| "eval_f1_micro": 0.8462199312714777, | |
| "eval_loss": 0.10834041237831116, | |
| "eval_roc_auc": 0.8933701178832314, | |
| "eval_runtime": 743.3565, | |
| "eval_samples_per_second": 3.765, | |
| "eval_steps_per_second": 0.235, | |
| "learning_rate": 0.0001, | |
| "step": 21976 | |
| }, | |
| { | |
| "epoch": 41.04, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1201, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 41.98, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1179, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5691318327974276, | |
| "eval_f1_macro": 0.8089823958516517, | |
| "eval_f1_micro": 0.8505242623750304, | |
| "eval_loss": 0.10719550400972366, | |
| "eval_roc_auc": 0.8978175825326844, | |
| "eval_runtime": 698.4214, | |
| "eval_samples_per_second": 4.008, | |
| "eval_steps_per_second": 0.251, | |
| "learning_rate": 0.0001, | |
| "step": 22512 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1186, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5612718828152912, | |
| "eval_f1_macro": 0.8071782588939219, | |
| "eval_f1_micro": 0.8482877132686878, | |
| "eval_loss": 0.11790523678064346, | |
| "eval_roc_auc": 0.8944810701797377, | |
| "eval_runtime": 695.4681, | |
| "eval_samples_per_second": 4.025, | |
| "eval_steps_per_second": 0.252, | |
| "learning_rate": 0.0001, | |
| "step": 23048 | |
| }, | |
| { | |
| "epoch": 43.84, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1174, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5655591282600929, | |
| "eval_f1_macro": 0.808033951861079, | |
| "eval_f1_micro": 0.8477235124701268, | |
| "eval_loss": 0.10680884122848511, | |
| "eval_roc_auc": 0.8946411623084602, | |
| "eval_runtime": 698.3846, | |
| "eval_samples_per_second": 4.008, | |
| "eval_steps_per_second": 0.251, | |
| "learning_rate": 0.0001, | |
| "step": 23584 | |
| }, | |
| { | |
| "epoch": 44.78, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1153, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.571632725973562, | |
| "eval_f1_macro": 0.8193083754252073, | |
| "eval_f1_micro": 0.85338323172572, | |
| "eval_loss": 0.10468064993619919, | |
| "eval_roc_auc": 0.9025354227051225, | |
| "eval_runtime": 732.8049, | |
| "eval_samples_per_second": 3.82, | |
| "eval_steps_per_second": 0.239, | |
| "learning_rate": 0.0001, | |
| "step": 24120 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1167, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5666309396212933, | |
| "eval_f1_macro": 0.822920967846307, | |
| "eval_f1_micro": 0.8535311572700296, | |
| "eval_loss": 0.10616234689950943, | |
| "eval_roc_auc": 0.9080353429554627, | |
| "eval_runtime": 730.6388, | |
| "eval_samples_per_second": 3.831, | |
| "eval_steps_per_second": 0.24, | |
| "learning_rate": 0.0001, | |
| "step": 24656 | |
| }, | |
| { | |
| "epoch": 46.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1162, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5694891032511611, | |
| "eval_f1_macro": 0.8179688260529804, | |
| "eval_f1_micro": 0.8521570528356762, | |
| "eval_loss": 0.10597173124551773, | |
| "eval_roc_auc": 0.9006400086530192, | |
| "eval_runtime": 707.3305, | |
| "eval_samples_per_second": 3.957, | |
| "eval_steps_per_second": 0.247, | |
| "learning_rate": 0.0001, | |
| "step": 25192 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1145, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5744908896034298, | |
| "eval_f1_macro": 0.8153624729345684, | |
| "eval_f1_micro": 0.8529072240111792, | |
| "eval_loss": 0.10410725325345993, | |
| "eval_roc_auc": 0.9002018263609444, | |
| "eval_runtime": 693.6803, | |
| "eval_samples_per_second": 4.035, | |
| "eval_steps_per_second": 0.252, | |
| "learning_rate": 0.0001, | |
| "step": 25728 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1143, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5652018578063595, | |
| "eval_f1_macro": 0.8181584192698232, | |
| "eval_f1_micro": 0.8542054951001022, | |
| "eval_loss": 0.10334235429763794, | |
| "eval_roc_auc": 0.9042645729162101, | |
| "eval_runtime": 700.9047, | |
| "eval_samples_per_second": 3.993, | |
| "eval_steps_per_second": 0.25, | |
| "learning_rate": 0.0001, | |
| "step": 26264 | |
| }, | |
| { | |
| "epoch": 49.44, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1129, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5719899964272954, | |
| "eval_f1_macro": 0.8102121985255263, | |
| "eval_f1_micro": 0.850807689945335, | |
| "eval_loss": 0.10544609278440475, | |
| "eval_roc_auc": 0.8956334123918851, | |
| "eval_runtime": 741.7594, | |
| "eval_samples_per_second": 3.773, | |
| "eval_steps_per_second": 0.236, | |
| "learning_rate": 0.0001, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0001, | |
| "step": 26800, | |
| "total_flos": 1.1878568451307192e+20, | |
| "train_loss": 0.15577314120620045, | |
| "train_runtime": 143618.003, | |
| "train_samples_per_second": 2.983, | |
| "train_steps_per_second": 0.187 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 26800, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 1.1878568451307192e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |