| { | |
| "best_metric": 0.1039666160941124, | |
| "best_model_checkpoint": "./dino-base-2023_11_27-with_custom_head/checkpoint-43952", | |
| "epoch": 90.0, | |
| "eval_steps": 500, | |
| "global_step": 48240, | |
| "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": 0.2471, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.39442658092175775, | |
| "eval_f1_macro": 0.40064106475011957, | |
| "eval_f1_micro": 0.5684482898035094, | |
| "eval_loss": 0.2136440873146057, | |
| "eval_roc_auc": 0.7020299868465498, | |
| "eval_runtime": 648.3221, | |
| "eval_samples_per_second": 4.317, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.01, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.01, | |
| "loss": 0.2208, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4090746695248303, | |
| "eval_f1_macro": 0.646218183693934, | |
| "eval_f1_micro": 0.6908665105386417, | |
| "eval_loss": 0.21994435787200928, | |
| "eval_roc_auc": 0.7944947312416977, | |
| "eval_runtime": 649.3168, | |
| "eval_samples_per_second": 4.311, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.01, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.01, | |
| "loss": 0.2181, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.43122543765630583, | |
| "eval_f1_macro": 0.5770940809584216, | |
| "eval_f1_micro": 0.6712328767123288, | |
| "eval_loss": 0.19793672859668732, | |
| "eval_roc_auc": 0.7666801441240528, | |
| "eval_runtime": 645.3042, | |
| "eval_samples_per_second": 4.337, | |
| "eval_steps_per_second": 0.271, | |
| "learning_rate": 0.01, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.01, | |
| "loss": 0.2187, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4137191854233655, | |
| "eval_f1_macro": 0.606113442290164, | |
| "eval_f1_micro": 0.7318466985527052, | |
| "eval_loss": 0.1766517609357834, | |
| "eval_roc_auc": 0.8268705246501159, | |
| "eval_runtime": 668.3118, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 0.262, | |
| "learning_rate": 0.01, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.01, | |
| "loss": 0.2128, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.43265451947123973, | |
| "eval_f1_macro": 0.5526692766303807, | |
| "eval_f1_micro": 0.7173007124613524, | |
| "eval_loss": 0.17600227892398834, | |
| "eval_roc_auc": 0.8011887560107374, | |
| "eval_runtime": 647.0188, | |
| "eval_samples_per_second": 4.326, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.01, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.01, | |
| "loss": 0.2171, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4226509467667024, | |
| "eval_f1_macro": 0.5183527283365527, | |
| "eval_f1_micro": 0.7108839135498899, | |
| "eval_loss": 0.1992170512676239, | |
| "eval_roc_auc": 0.8061565099276957, | |
| "eval_runtime": 650.6673, | |
| "eval_samples_per_second": 4.302, | |
| "eval_steps_per_second": 0.269, | |
| "learning_rate": 0.01, | |
| "step": 3216 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.01, | |
| "loss": 0.2108, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.41729188996070027, | |
| "eval_f1_macro": 0.6054999995580052, | |
| "eval_f1_micro": 0.7338740337092892, | |
| "eval_loss": 0.16948619484901428, | |
| "eval_roc_auc": 0.8232094683978447, | |
| "eval_runtime": 649.3312, | |
| "eval_samples_per_second": 4.311, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.01, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 0.01, | |
| "loss": 0.2147, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4226509467667024, | |
| "eval_f1_macro": 0.6176021212641017, | |
| "eval_f1_micro": 0.7440822902466228, | |
| "eval_loss": 0.16185873746871948, | |
| "eval_roc_auc": 0.8341874074405569, | |
| "eval_runtime": 663.7112, | |
| "eval_samples_per_second": 4.217, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.01, | |
| "step": 4288 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 0.01, | |
| "loss": 0.2112, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.43086816720257237, | |
| "eval_f1_macro": 0.6402287128969387, | |
| "eval_f1_micro": 0.7336987336987336, | |
| "eval_loss": 0.17079614102840424, | |
| "eval_roc_auc": 0.8244850070361233, | |
| "eval_runtime": 656.7931, | |
| "eval_samples_per_second": 4.262, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.01, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.01, | |
| "loss": 0.216, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.42836727402643804, | |
| "eval_f1_macro": 0.643393584513474, | |
| "eval_f1_micro": 0.7493341591824095, | |
| "eval_loss": 0.1750514954328537, | |
| "eval_roc_auc": 0.83718619371997, | |
| "eval_runtime": 657.1366, | |
| "eval_samples_per_second": 4.259, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.01, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 0.01, | |
| "loss": 0.2151, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.43372633083244017, | |
| "eval_f1_macro": 0.6292914445814428, | |
| "eval_f1_micro": 0.7241767706883986, | |
| "eval_loss": 0.17014054954051971, | |
| "eval_roc_auc": 0.8078434001509203, | |
| "eval_runtime": 662.7207, | |
| "eval_samples_per_second": 4.223, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.01, | |
| "step": 5896 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.01, | |
| "loss": 0.213, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.3565559128260093, | |
| "eval_f1_macro": 0.5371100777543761, | |
| "eval_f1_micro": 0.6629161350191394, | |
| "eval_loss": 0.2409001588821411, | |
| "eval_roc_auc": 0.8034829311226885, | |
| "eval_runtime": 657.3534, | |
| "eval_samples_per_second": 4.258, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.01, | |
| "step": 6432 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 0.01, | |
| "loss": 0.2161, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4194355126831011, | |
| "eval_f1_macro": 0.6243034191518838, | |
| "eval_f1_micro": 0.7290690310322989, | |
| "eval_loss": 0.1704823523759842, | |
| "eval_roc_auc": 0.820743148916754, | |
| "eval_runtime": 665.336, | |
| "eval_samples_per_second": 4.207, | |
| "eval_steps_per_second": 0.263, | |
| "learning_rate": 0.01, | |
| "step": 6968 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.01, | |
| "loss": 0.2145, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 0.01, | |
| "loss": 0.2136, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.44265809217577706, | |
| "eval_f1_macro": 0.6215367292632343, | |
| "eval_f1_micro": 0.734259379462547, | |
| "eval_loss": 0.16933664679527283, | |
| "eval_roc_auc": 0.8177495297062425, | |
| "eval_runtime": 654.4339, | |
| "eval_samples_per_second": 4.277, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.01, | |
| "step": 7504 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 0.001, | |
| "loss": 0.1826, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4969632011432655, | |
| "eval_f1_macro": 0.7459554779815883, | |
| "eval_f1_micro": 0.7967720076387605, | |
| "eval_loss": 0.13880470395088196, | |
| "eval_roc_auc": 0.8648126874646008, | |
| "eval_runtime": 668.3546, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 0.262, | |
| "learning_rate": 0.001, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.1731, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5155412647374062, | |
| "eval_f1_macro": 0.7385190479208986, | |
| "eval_f1_micro": 0.8016270337922403, | |
| "eval_loss": 0.14762958884239197, | |
| "eval_roc_auc": 0.8631052728177114, | |
| "eval_runtime": 657.5159, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.001, | |
| "step": 8576 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.1649, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5023222579492675, | |
| "eval_f1_macro": 0.7692855132157861, | |
| "eval_f1_micro": 0.813318908522659, | |
| "eval_loss": 0.1351146697998047, | |
| "eval_roc_auc": 0.8811667807242409, | |
| "eval_runtime": 655.4487, | |
| "eval_samples_per_second": 4.27, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.001, | |
| "step": 9112 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 0.001, | |
| "loss": 0.1624, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5212575919971418, | |
| "eval_f1_macro": 0.7714136364578609, | |
| "eval_f1_micro": 0.8185593067340675, | |
| "eval_loss": 0.13848340511322021, | |
| "eval_roc_auc": 0.8837626029149266, | |
| "eval_runtime": 662.3967, | |
| "eval_samples_per_second": 4.226, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.001, | |
| "step": 9648 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 0.001, | |
| "loss": 0.1576, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5205430510896749, | |
| "eval_f1_macro": 0.7631806100991755, | |
| "eval_f1_micro": 0.8175969609705288, | |
| "eval_loss": 0.13018544018268585, | |
| "eval_roc_auc": 0.8779148602729905, | |
| "eval_runtime": 679.9157, | |
| "eval_samples_per_second": 4.117, | |
| "eval_steps_per_second": 0.257, | |
| "learning_rate": 0.001, | |
| "step": 10184 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 0.001, | |
| "loss": 0.1544, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5319757056091461, | |
| "eval_f1_macro": 0.7721701876863485, | |
| "eval_f1_micro": 0.8229907814143413, | |
| "eval_loss": 0.12343110144138336, | |
| "eval_roc_auc": 0.8780568409783432, | |
| "eval_runtime": 658.9399, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.001, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 20.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.1542, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.525902107895677, | |
| "eval_f1_macro": 0.7754587726434372, | |
| "eval_f1_micro": 0.8267645466032855, | |
| "eval_loss": 0.13044790923595428, | |
| "eval_roc_auc": 0.8884477411328827, | |
| "eval_runtime": 659.4337, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.001, | |
| "step": 11256 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.1525, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5376920328688818, | |
| "eval_f1_macro": 0.76461964189607, | |
| "eval_f1_micro": 0.8176823176823177, | |
| "eval_loss": 0.12196117639541626, | |
| "eval_roc_auc": 0.8724977198539325, | |
| "eval_runtime": 674.7285, | |
| "eval_samples_per_second": 4.148, | |
| "eval_steps_per_second": 0.259, | |
| "learning_rate": 0.001, | |
| "step": 11792 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 0.001, | |
| "loss": 0.1505, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5255448374419436, | |
| "eval_f1_macro": 0.7872363331907107, | |
| "eval_f1_micro": 0.8264049955396968, | |
| "eval_loss": 0.13109837472438812, | |
| "eval_roc_auc": 0.891814004155335, | |
| "eval_runtime": 658.8901, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.001, | |
| "step": 12328 | |
| }, | |
| { | |
| "epoch": 23.32, | |
| "learning_rate": 0.001, | |
| "loss": 0.1515, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5316184351554126, | |
| "eval_f1_macro": 0.7629977302664256, | |
| "eval_f1_micro": 0.8188446438586652, | |
| "eval_loss": 0.12468679994344711, | |
| "eval_roc_auc": 0.8736890703040258, | |
| "eval_runtime": 649.926, | |
| "eval_samples_per_second": 4.307, | |
| "eval_steps_per_second": 0.269, | |
| "learning_rate": 0.001, | |
| "step": 12864 | |
| }, | |
| { | |
| "epoch": 24.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.1471, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5226866738120758, | |
| "eval_f1_macro": 0.7726394339166129, | |
| "eval_f1_micro": 0.8258118937157316, | |
| "eval_loss": 0.1264602392911911, | |
| "eval_roc_auc": 0.8875076814616129, | |
| "eval_runtime": 661.9223, | |
| "eval_samples_per_second": 4.229, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.001, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 25.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.1475, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5330475169703466, | |
| "eval_f1_macro": 0.7834057788273457, | |
| "eval_f1_micro": 0.8301059554256485, | |
| "eval_loss": 0.12767212092876434, | |
| "eval_roc_auc": 0.8867279830614062, | |
| "eval_runtime": 654.8587, | |
| "eval_samples_per_second": 4.274, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.001, | |
| "step": 13936 | |
| }, | |
| { | |
| "epoch": 26.12, | |
| "learning_rate": 0.001, | |
| "loss": 0.1484, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5398356555912825, | |
| "eval_f1_macro": 0.7661233818608114, | |
| "eval_f1_micro": 0.8218290555693994, | |
| "eval_loss": 0.12360195070505142, | |
| "eval_roc_auc": 0.8754121833739898, | |
| "eval_runtime": 658.0747, | |
| "eval_samples_per_second": 4.253, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.001, | |
| "step": 14472 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "learning_rate": 0.001, | |
| "loss": 0.1475, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 0.001, | |
| "loss": 0.1472, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5401929260450161, | |
| "eval_f1_macro": 0.7728524137767288, | |
| "eval_f1_micro": 0.8228913409388442, | |
| "eval_loss": 0.1256585270166397, | |
| "eval_roc_auc": 0.8757945197904818, | |
| "eval_runtime": 655.1438, | |
| "eval_samples_per_second": 4.272, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.001, | |
| "step": 15008 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1379, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5451947123972848, | |
| "eval_f1_macro": 0.7891009081675242, | |
| "eval_f1_micro": 0.8352094482376824, | |
| "eval_loss": 0.11994459480047226, | |
| "eval_roc_auc": 0.8865305601939816, | |
| "eval_runtime": 657.6068, | |
| "eval_samples_per_second": 4.256, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.0001, | |
| "step": 15544 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1349, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5487674169346195, | |
| "eval_f1_macro": 0.7943922901606704, | |
| "eval_f1_micro": 0.841315916787615, | |
| "eval_loss": 0.11564121395349503, | |
| "eval_roc_auc": 0.895138845939546, | |
| "eval_runtime": 659.4245, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 16080 | |
| }, | |
| { | |
| "epoch": 30.78, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1326, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5498392282958199, | |
| "eval_f1_macro": 0.7983364672353336, | |
| "eval_f1_micro": 0.84037558685446, | |
| "eval_loss": 0.11515345424413681, | |
| "eval_roc_auc": 0.8960665621862288, | |
| "eval_runtime": 652.6109, | |
| "eval_samples_per_second": 4.289, | |
| "eval_steps_per_second": 0.268, | |
| "learning_rate": 0.0001, | |
| "step": 16616 | |
| }, | |
| { | |
| "epoch": 31.72, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1321, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5509110396570204, | |
| "eval_f1_macro": 0.7911364775051637, | |
| "eval_f1_micro": 0.8385913426265589, | |
| "eval_loss": 0.11371538788080215, | |
| "eval_roc_auc": 0.89024940896342, | |
| "eval_runtime": 663.8067, | |
| "eval_samples_per_second": 4.217, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 17152 | |
| }, | |
| { | |
| "epoch": 32.65, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1294, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5512683101107538, | |
| "eval_f1_macro": 0.7924466456431516, | |
| "eval_f1_micro": 0.8406133545115768, | |
| "eval_loss": 0.11363548040390015, | |
| "eval_roc_auc": 0.891620070857568, | |
| "eval_runtime": 641.5792, | |
| "eval_samples_per_second": 4.363, | |
| "eval_steps_per_second": 0.273, | |
| "learning_rate": 0.0001, | |
| "step": 17688 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1297, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.5551982851018221, | |
| "eval_f1_macro": 0.7994952163993189, | |
| "eval_f1_micro": 0.8438879816125325, | |
| "eval_loss": 0.1100151389837265, | |
| "eval_roc_auc": 0.8965325171836247, | |
| "eval_runtime": 666.5011, | |
| "eval_samples_per_second": 4.2, | |
| "eval_steps_per_second": 0.263, | |
| "learning_rate": 0.0001, | |
| "step": 18224 | |
| }, | |
| { | |
| "epoch": 34.51, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1296, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5569846373704894, | |
| "eval_f1_macro": 0.7958547104209327, | |
| "eval_f1_micro": 0.8430563978168587, | |
| "eval_loss": 0.11022897809743881, | |
| "eval_roc_auc": 0.8952561397957243, | |
| "eval_runtime": 651.2057, | |
| "eval_samples_per_second": 4.298, | |
| "eval_steps_per_second": 0.269, | |
| "learning_rate": 0.0001, | |
| "step": 18760 | |
| }, | |
| { | |
| "epoch": 35.45, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1276, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5584137191854234, | |
| "eval_f1_macro": 0.7954026209465306, | |
| "eval_f1_micro": 0.8428501708150318, | |
| "eval_loss": 0.11038191616535187, | |
| "eval_roc_auc": 0.8933002510838177, | |
| "eval_runtime": 659.4359, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 19296 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1264, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.5644873168988924, | |
| "eval_f1_macro": 0.8073166114826349, | |
| "eval_f1_micro": 0.8467775842392937, | |
| "eval_loss": 0.11108729988336563, | |
| "eval_roc_auc": 0.9003547734565809, | |
| "eval_runtime": 649.1518, | |
| "eval_samples_per_second": 4.312, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.0001, | |
| "step": 19832 | |
| }, | |
| { | |
| "epoch": 37.31, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1279, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5662736691675598, | |
| "eval_f1_macro": 0.8059718169069215, | |
| "eval_f1_micro": 0.8457475869604808, | |
| "eval_loss": 0.11050034314393997, | |
| "eval_roc_auc": 0.8964483289954395, | |
| "eval_runtime": 661.6908, | |
| "eval_samples_per_second": 4.23, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 20368 | |
| }, | |
| { | |
| "epoch": 38.25, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1231, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5623436941764915, | |
| "eval_f1_macro": 0.810452280144873, | |
| "eval_f1_micro": 0.8481141692150868, | |
| "eval_loss": 0.1114969253540039, | |
| "eval_roc_auc": 0.9016441984475202, | |
| "eval_runtime": 645.0365, | |
| "eval_samples_per_second": 4.339, | |
| "eval_steps_per_second": 0.271, | |
| "learning_rate": 0.0001, | |
| "step": 20904 | |
| }, | |
| { | |
| "epoch": 39.18, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1276, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.564844587352626, | |
| "eval_f1_macro": 0.7998757908744976, | |
| "eval_f1_micro": 0.8442948914040991, | |
| "eval_loss": 0.10886894911527634, | |
| "eval_roc_auc": 0.8932229387863774, | |
| "eval_runtime": 664.3024, | |
| "eval_samples_per_second": 4.213, | |
| "eval_steps_per_second": 0.263, | |
| "learning_rate": 0.0001, | |
| "step": 21440 | |
| }, | |
| { | |
| "epoch": 40.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.121, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5627009646302251, | |
| "eval_f1_macro": 0.8014681171854418, | |
| "eval_f1_micro": 0.8454512239678481, | |
| "eval_loss": 0.10981705039739609, | |
| "eval_roc_auc": 0.8953198348828445, | |
| "eval_runtime": 652.9462, | |
| "eval_samples_per_second": 4.287, | |
| "eval_steps_per_second": 0.268, | |
| "learning_rate": 0.0001, | |
| "step": 21976 | |
| }, | |
| { | |
| "epoch": 41.04, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1241, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 41.98, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1229, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5619864237227581, | |
| "eval_f1_macro": 0.8009464266100834, | |
| "eval_f1_micro": 0.8459390554813646, | |
| "eval_loss": 0.10872387140989304, | |
| "eval_roc_auc": 0.8965747458488879, | |
| "eval_runtime": 655.0026, | |
| "eval_samples_per_second": 4.273, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.0001, | |
| "step": 22512 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1227, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5687745623436942, | |
| "eval_f1_macro": 0.8067169938735436, | |
| "eval_f1_micro": 0.8468292682926829, | |
| "eval_loss": 0.10882638394832611, | |
| "eval_roc_auc": 0.8956753719148074, | |
| "eval_runtime": 660.8489, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 23048 | |
| }, | |
| { | |
| "epoch": 43.84, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1221, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5673454805287603, | |
| "eval_f1_macro": 0.8065744332804647, | |
| "eval_f1_micro": 0.8476346632659257, | |
| "eval_loss": 0.10762665420770645, | |
| "eval_roc_auc": 0.897394560379003, | |
| "eval_runtime": 657.9808, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.0001, | |
| "step": 23584 | |
| }, | |
| { | |
| "epoch": 44.78, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1191, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5698463737048947, | |
| "eval_f1_macro": 0.817339787108748, | |
| "eval_f1_micro": 0.8507955568898229, | |
| "eval_loss": 0.10689569264650345, | |
| "eval_roc_auc": 0.9027498177813545, | |
| "eval_runtime": 671.4032, | |
| "eval_samples_per_second": 4.169, | |
| "eval_steps_per_second": 0.261, | |
| "learning_rate": 0.0001, | |
| "step": 24120 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1212, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.563415505537692, | |
| "eval_f1_macro": 0.8173548628519673, | |
| "eval_f1_micro": 0.8508932256352808, | |
| "eval_loss": 0.10721632838249207, | |
| "eval_roc_auc": 0.9086343215547117, | |
| "eval_runtime": 661.9534, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 24656 | |
| }, | |
| { | |
| "epoch": 46.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1198, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5687745623436942, | |
| "eval_f1_macro": 0.8090465345914333, | |
| "eval_f1_micro": 0.849293563579278, | |
| "eval_loss": 0.10663535445928574, | |
| "eval_roc_auc": 0.900130416633457, | |
| "eval_runtime": 673.8512, | |
| "eval_samples_per_second": 4.154, | |
| "eval_steps_per_second": 0.26, | |
| "learning_rate": 0.0001, | |
| "step": 25192 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1201, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5652018578063595, | |
| "eval_f1_macro": 0.8082582901487069, | |
| "eval_f1_micro": 0.8484811957569913, | |
| "eval_loss": 0.10762892663478851, | |
| "eval_roc_auc": 0.9002407000277199, | |
| "eval_runtime": 662.4725, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 25728 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1189, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5687745623436942, | |
| "eval_f1_macro": 0.8152048365492516, | |
| "eval_f1_micro": 0.8507597141312836, | |
| "eval_loss": 0.10654111951589584, | |
| "eval_roc_auc": 0.9026532861685821, | |
| "eval_runtime": 679.062, | |
| "eval_samples_per_second": 4.122, | |
| "eval_steps_per_second": 0.258, | |
| "learning_rate": 0.0001, | |
| "step": 26264 | |
| }, | |
| { | |
| "epoch": 49.44, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1176, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.563415505537692, | |
| "eval_f1_macro": 0.8033757987633436, | |
| "eval_f1_micro": 0.8462940461725396, | |
| "eval_loss": 0.10730718821287155, | |
| "eval_roc_auc": 0.8965096424048645, | |
| "eval_runtime": 643.0995, | |
| "eval_samples_per_second": 4.352, | |
| "eval_steps_per_second": 0.272, | |
| "learning_rate": 0.0001, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 50.37, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1202, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5727045373347625, | |
| "eval_f1_macro": 0.8102272806912906, | |
| "eval_f1_micro": 0.8480676328502416, | |
| "eval_loss": 0.10732194036245346, | |
| "eval_roc_auc": 0.8994002578253693, | |
| "eval_runtime": 645.0782, | |
| "eval_samples_per_second": 4.339, | |
| "eval_steps_per_second": 0.271, | |
| "learning_rate": 0.0001, | |
| "step": 27336 | |
| }, | |
| { | |
| "epoch": 51.31, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1167, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.571632725973562, | |
| "eval_f1_macro": 0.8179079350328715, | |
| "eval_f1_micro": 0.8521687462863933, | |
| "eval_loss": 0.10600127279758453, | |
| "eval_roc_auc": 0.9068707918898985, | |
| "eval_runtime": 661.3351, | |
| "eval_samples_per_second": 4.232, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 27872 | |
| }, | |
| { | |
| "epoch": 52.24, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1192, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5712754555198285, | |
| "eval_f1_macro": 0.8127939311574505, | |
| "eval_f1_micro": 0.8507093268940539, | |
| "eval_loss": 0.10628383606672287, | |
| "eval_roc_auc": 0.9009869922949931, | |
| "eval_runtime": 649.2151, | |
| "eval_samples_per_second": 4.311, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.0001, | |
| "step": 28408 | |
| }, | |
| { | |
| "epoch": 53.17, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1156, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5719899964272954, | |
| "eval_f1_macro": 0.8113280265904282, | |
| "eval_f1_micro": 0.8493415488703637, | |
| "eval_loss": 0.10670817643404007, | |
| "eval_roc_auc": 0.9000055427080821, | |
| "eval_runtime": 659.1604, | |
| "eval_samples_per_second": 4.246, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 28944 | |
| }, | |
| { | |
| "epoch": 54.1, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1193, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5727045373347625, | |
| "eval_f1_macro": 0.8116343899877551, | |
| "eval_f1_micro": 0.8490052609300356, | |
| "eval_loss": 0.10690104961395264, | |
| "eval_roc_auc": 0.8994929994035434, | |
| "eval_runtime": 663.4912, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 29480 | |
| }, | |
| { | |
| "epoch": 55.04, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1161, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.116, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5744908896034298, | |
| "eval_f1_macro": 0.818624257330544, | |
| "eval_f1_micro": 0.8542707589816796, | |
| "eval_loss": 0.10558204352855682, | |
| "eval_roc_auc": 0.9077319963356549, | |
| "eval_runtime": 659.0048, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.0001, | |
| "step": 30016 | |
| }, | |
| { | |
| "epoch": 56.9, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1147, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5730618077884959, | |
| "eval_f1_macro": 0.8113712664273885, | |
| "eval_f1_micro": 0.8505116959064327, | |
| "eval_loss": 0.10627623647451401, | |
| "eval_roc_auc": 0.8980389880708319, | |
| "eval_runtime": 669.8276, | |
| "eval_samples_per_second": 4.179, | |
| "eval_steps_per_second": 0.261, | |
| "learning_rate": 0.0001, | |
| "step": 30552 | |
| }, | |
| { | |
| "epoch": 57.84, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1139, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5705609146123616, | |
| "eval_f1_macro": 0.8074486566040442, | |
| "eval_f1_micro": 0.8488632919066383, | |
| "eval_loss": 0.10657747834920883, | |
| "eval_roc_auc": 0.898615796069772, | |
| "eval_runtime": 654.902, | |
| "eval_samples_per_second": 4.274, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.0001, | |
| "step": 31088 | |
| }, | |
| { | |
| "epoch": 58.77, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1143, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5727045373347625, | |
| "eval_f1_macro": 0.8065194300593265, | |
| "eval_f1_micro": 0.8490646517579673, | |
| "eval_loss": 0.10738535225391388, | |
| "eval_roc_auc": 0.8971341466029096, | |
| "eval_runtime": 661.8186, | |
| "eval_samples_per_second": 4.229, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 31624 | |
| }, | |
| { | |
| "epoch": 59.7, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1148, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5694891032511611, | |
| "eval_f1_macro": 0.8079607267977419, | |
| "eval_f1_micro": 0.8498935199269851, | |
| "eval_loss": 0.10777446627616882, | |
| "eval_roc_auc": 0.8980542827803957, | |
| "eval_runtime": 663.1043, | |
| "eval_samples_per_second": 4.221, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 32160 | |
| }, | |
| { | |
| "epoch": 60.63, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1143, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.572347266881029, | |
| "eval_f1_macro": 0.8159017507862669, | |
| "eval_f1_micro": 0.8512052195976559, | |
| "eval_loss": 0.10536229610443115, | |
| "eval_roc_auc": 0.9010383439575261, | |
| "eval_runtime": 660.7796, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 32696 | |
| }, | |
| { | |
| "epoch": 61.57, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1133, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.5737763486959628, | |
| "eval_f1_macro": 0.808341771577789, | |
| "eval_f1_micro": 0.8495672315006705, | |
| "eval_loss": 0.10581369698047638, | |
| "eval_roc_auc": 0.8973203339377094, | |
| "eval_runtime": 655.4703, | |
| "eval_samples_per_second": 4.27, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.0001, | |
| "step": 33232 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1134, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.5680600214362272, | |
| "eval_f1_macro": 0.8087952156757714, | |
| "eval_f1_micro": 0.847873368777187, | |
| "eval_loss": 0.1063385158777237, | |
| "eval_roc_auc": 0.899139005299654, | |
| "eval_runtime": 659.92, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 0.0001, | |
| "step": 33768 | |
| }, | |
| { | |
| "epoch": 63.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1123, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.5702036441586281, | |
| "eval_f1_macro": 0.8121242156828758, | |
| "eval_f1_micro": 0.8503755754785559, | |
| "eval_loss": 0.10543316602706909, | |
| "eval_roc_auc": 0.8997137007632394, | |
| "eval_runtime": 647.0637, | |
| "eval_samples_per_second": 4.326, | |
| "eval_steps_per_second": 0.27, | |
| "learning_rate": 0.0001, | |
| "step": 34304 | |
| }, | |
| { | |
| "epoch": 64.37, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1141, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.5730618077884959, | |
| "eval_f1_macro": 0.8099395952334975, | |
| "eval_f1_micro": 0.8494330240737371, | |
| "eval_loss": 0.10500979423522949, | |
| "eval_roc_auc": 0.8988602109578501, | |
| "eval_runtime": 649.7608, | |
| "eval_samples_per_second": 4.308, | |
| "eval_steps_per_second": 0.269, | |
| "learning_rate": 0.0001, | |
| "step": 34840 | |
| }, | |
| { | |
| "epoch": 65.3, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1104, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.5762772418720972, | |
| "eval_f1_macro": 0.8132610218333434, | |
| "eval_f1_micro": 0.8506980430409072, | |
| "eval_loss": 0.10500740259885788, | |
| "eval_roc_auc": 0.8978957335797464, | |
| "eval_runtime": 652.9454, | |
| "eval_samples_per_second": 4.287, | |
| "eval_steps_per_second": 0.268, | |
| "learning_rate": 0.0001, | |
| "step": 35376 | |
| }, | |
| { | |
| "epoch": 66.23, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1124, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.5669882100750268, | |
| "eval_f1_macro": 0.8163481281680508, | |
| "eval_f1_micro": 0.8512857399748246, | |
| "eval_loss": 0.10600199550390244, | |
| "eval_roc_auc": 0.9035619176711028, | |
| "eval_runtime": 657.7451, | |
| "eval_samples_per_second": 4.255, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.0001, | |
| "step": 35912 | |
| }, | |
| { | |
| "epoch": 67.16, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1111, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.5680600214362272, | |
| "eval_f1_macro": 0.8156635542444352, | |
| "eval_f1_micro": 0.8511868899867453, | |
| "eval_loss": 0.10536548495292664, | |
| "eval_roc_auc": 0.9018856620506218, | |
| "eval_runtime": 656.6156, | |
| "eval_samples_per_second": 4.263, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.0001, | |
| "step": 36448 | |
| }, | |
| { | |
| "epoch": 68.1, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1097, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.5673454805287603, | |
| "eval_f1_macro": 0.8109923908741982, | |
| "eval_f1_micro": 0.8500871237156763, | |
| "eval_loss": 0.1056470051407814, | |
| "eval_roc_auc": 0.9021192764421861, | |
| "eval_runtime": 657.5814, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 0.0001, | |
| "step": 36984 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1106, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 69.96, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1096, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.5673454805287603, | |
| "eval_f1_macro": 0.8119494369118779, | |
| "eval_f1_micro": 0.8500514558992676, | |
| "eval_loss": 0.1059202253818512, | |
| "eval_roc_auc": 0.8997405001477684, | |
| "eval_runtime": 661.9686, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 0.0001, | |
| "step": 37520 | |
| }, | |
| { | |
| "epoch": 70.9, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1097, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.5737763486959628, | |
| "eval_f1_macro": 0.8171777200998823, | |
| "eval_f1_micro": 0.8517297200071947, | |
| "eval_loss": 0.10546696186065674, | |
| "eval_roc_auc": 0.9037381432590107, | |
| "eval_runtime": 654.6273, | |
| "eval_samples_per_second": 4.276, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 0.0001, | |
| "step": 38056 | |
| }, | |
| { | |
| "epoch": 71.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1084, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.5630582350839586, | |
| "eval_f1_macro": 0.8063147670569071, | |
| "eval_f1_micro": 0.84692696594993, | |
| "eval_loss": 0.10735420882701874, | |
| "eval_roc_auc": 0.8960515366190057, | |
| "eval_runtime": 658.0374, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 1e-05, | |
| "step": 38592 | |
| }, | |
| { | |
| "epoch": 72.76, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1091, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.5734190782422294, | |
| "eval_f1_macro": 0.8171103344103756, | |
| "eval_f1_micro": 0.8525143029208069, | |
| "eval_loss": 0.10438621789216995, | |
| "eval_roc_auc": 0.9027705800247602, | |
| "eval_runtime": 664.8235, | |
| "eval_samples_per_second": 4.21, | |
| "eval_steps_per_second": 0.263, | |
| "learning_rate": 1e-05, | |
| "step": 39128 | |
| }, | |
| { | |
| "epoch": 73.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1051, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.571632725973562, | |
| "eval_f1_macro": 0.8187356068324974, | |
| "eval_f1_micro": 0.8532934131736527, | |
| "eval_loss": 0.10408420860767365, | |
| "eval_roc_auc": 0.9050291111780234, | |
| "eval_runtime": 673.5967, | |
| "eval_samples_per_second": 4.155, | |
| "eval_steps_per_second": 0.26, | |
| "learning_rate": 1e-05, | |
| "step": 39664 | |
| }, | |
| { | |
| "epoch": 74.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1069, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.5698463737048947, | |
| "eval_f1_macro": 0.8154818599661411, | |
| "eval_f1_micro": 0.8505788712011578, | |
| "eval_loss": 0.10555566847324371, | |
| "eval_roc_auc": 0.9012750442052373, | |
| "eval_runtime": 657.1771, | |
| "eval_samples_per_second": 4.259, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 1e-05, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 75.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1079, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.572347266881029, | |
| "eval_f1_macro": 0.8153806167901401, | |
| "eval_f1_micro": 0.8517114840883114, | |
| "eval_loss": 0.10429207235574722, | |
| "eval_roc_auc": 0.9026594578808756, | |
| "eval_runtime": 664.6613, | |
| "eval_samples_per_second": 4.211, | |
| "eval_steps_per_second": 0.263, | |
| "learning_rate": 1e-05, | |
| "step": 40736 | |
| }, | |
| { | |
| "epoch": 76.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1072, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.5780635941407646, | |
| "eval_f1_macro": 0.8187874152985335, | |
| "eval_f1_micro": 0.853607002716571, | |
| "eval_loss": 0.10398340970277786, | |
| "eval_roc_auc": 0.9026235354990767, | |
| "eval_runtime": 664.3977, | |
| "eval_samples_per_second": 4.213, | |
| "eval_steps_per_second": 0.263, | |
| "learning_rate": 1e-05, | |
| "step": 41272 | |
| }, | |
| { | |
| "epoch": 77.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.105, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.5712754555198285, | |
| "eval_f1_macro": 0.8150330415154026, | |
| "eval_f1_micro": 0.8514409743156879, | |
| "eval_loss": 0.10431113094091415, | |
| "eval_roc_auc": 0.9018006351128146, | |
| "eval_runtime": 660.4258, | |
| "eval_samples_per_second": 4.238, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 1e-05, | |
| "step": 41808 | |
| }, | |
| { | |
| "epoch": 78.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1061, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.5734190782422294, | |
| "eval_f1_macro": 0.8180685346674, | |
| "eval_f1_micro": 0.8525934861278649, | |
| "eval_loss": 0.10427288711071014, | |
| "eval_roc_auc": 0.9023377306953573, | |
| "eval_runtime": 662.4252, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 1e-05, | |
| "step": 42344 | |
| }, | |
| { | |
| "epoch": 79.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1045, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.5719899964272954, | |
| "eval_f1_macro": 0.8176554657248621, | |
| "eval_f1_micro": 0.8512023142288917, | |
| "eval_loss": 0.10507169365882874, | |
| "eval_roc_auc": 0.9017990921847413, | |
| "eval_runtime": 662.5216, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 1e-05, | |
| "step": 42880 | |
| }, | |
| { | |
| "epoch": 80.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1062, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.5694891032511611, | |
| "eval_f1_macro": 0.8157488543073257, | |
| "eval_f1_micro": 0.8500577402297453, | |
| "eval_loss": 0.10686225444078445, | |
| "eval_roc_auc": 0.8984886750378719, | |
| "eval_runtime": 655.8239, | |
| "eval_samples_per_second": 4.268, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 1e-05, | |
| "step": 43416 | |
| }, | |
| { | |
| "epoch": 81.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1057, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.5734190782422294, | |
| "eval_f1_macro": 0.8184447896335341, | |
| "eval_f1_micro": 0.8530242056579975, | |
| "eval_loss": 0.1039666160941124, | |
| "eval_roc_auc": 0.9039006170654286, | |
| "eval_runtime": 659.9314, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 1e-05, | |
| "step": 43952 | |
| }, | |
| { | |
| "epoch": 82.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1073, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.5712754555198285, | |
| "eval_f1_macro": 0.8151349204991644, | |
| "eval_f1_micro": 0.8503600634688149, | |
| "eval_loss": 0.10477207601070404, | |
| "eval_roc_auc": 0.8973831902752079, | |
| "eval_runtime": 660.9853, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 1e-05, | |
| "step": 44488 | |
| }, | |
| { | |
| "epoch": 83.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1053, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 83.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1059, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.5741336191496963, | |
| "eval_f1_macro": 0.8177615611039802, | |
| "eval_f1_micro": 0.8525637163342773, | |
| "eval_loss": 0.1043851226568222, | |
| "eval_roc_auc": 0.9026457060993854, | |
| "eval_runtime": 661.1385, | |
| "eval_samples_per_second": 4.234, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 1e-05, | |
| "step": 45024 | |
| }, | |
| { | |
| "epoch": 84.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1054, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.5702036441586281, | |
| "eval_f1_macro": 0.8148620661290662, | |
| "eval_f1_micro": 0.8505413415593056, | |
| "eval_loss": 0.10626183450222015, | |
| "eval_roc_auc": 0.9002829286929828, | |
| "eval_runtime": 667.6418, | |
| "eval_samples_per_second": 4.192, | |
| "eval_steps_per_second": 0.262, | |
| "learning_rate": 1e-05, | |
| "step": 45560 | |
| }, | |
| { | |
| "epoch": 85.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1046, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.5727045373347625, | |
| "eval_f1_macro": 0.8160800717420196, | |
| "eval_f1_micro": 0.8525306469231703, | |
| "eval_loss": 0.10432148724794388, | |
| "eval_roc_auc": 0.9003534996708482, | |
| "eval_runtime": 656.1196, | |
| "eval_samples_per_second": 4.266, | |
| "eval_steps_per_second": 0.267, | |
| "learning_rate": 1e-05, | |
| "step": 46096 | |
| }, | |
| { | |
| "epoch": 86.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.105, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.5719899964272954, | |
| "eval_f1_macro": 0.8185429098530308, | |
| "eval_f1_micro": 0.8532148646214804, | |
| "eval_loss": 0.10474765300750732, | |
| "eval_roc_auc": 0.904161869591144, | |
| "eval_runtime": 662.4652, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.264, | |
| "learning_rate": 1e-05, | |
| "step": 46632 | |
| }, | |
| { | |
| "epoch": 87.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1029, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.5759199714183637, | |
| "eval_f1_macro": 0.8155503181233792, | |
| "eval_f1_micro": 0.8518207954000958, | |
| "eval_loss": 0.10432733595371246, | |
| "eval_roc_auc": 0.9041143079632091, | |
| "eval_runtime": 659.661, | |
| "eval_samples_per_second": 4.243, | |
| "eval_steps_per_second": 0.265, | |
| "learning_rate": 1e-05, | |
| "step": 47168 | |
| }, | |
| { | |
| "epoch": 88.62, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1059, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.5787781350482315, | |
| "eval_f1_macro": 0.8178092875894164, | |
| "eval_f1_micro": 0.8538892570946557, | |
| "eval_loss": 0.10400809347629547, | |
| "eval_roc_auc": 0.9033957884012571, | |
| "eval_runtime": 659.0133, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 0.266, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 47704 | |
| }, | |
| { | |
| "epoch": 89.55, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1047, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.5694891032511611, | |
| "eval_f1_macro": 0.8136056007290207, | |
| "eval_f1_micro": 0.8504655833485485, | |
| "eval_loss": 0.10469033569097519, | |
| "eval_roc_auc": 0.8982986976684738, | |
| "eval_runtime": 653.5683, | |
| "eval_samples_per_second": 4.283, | |
| "eval_steps_per_second": 0.268, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 48240 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 48240, | |
| "total_flos": 6.13340503159962e+19, | |
| "train_loss": 0.13765035268679188, | |
| "train_runtime": 238196.7751, | |
| "train_samples_per_second": 3.237, | |
| "train_steps_per_second": 0.203 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 48240, | |
| "num_train_epochs": 90, | |
| "save_steps": 500, | |
| "total_flos": 6.13340503159962e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |