| { | |
| "best_metric": 0.3534505903118732, | |
| "best_model_checkpoint": "esm2_t12_35M_qlora_binding_sites_2023-09-30_06-27-21/checkpoint-10578", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 10578, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003700117150420716, | |
| "loss": 0.4265, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0003695766709151845, | |
| "loss": 0.2446, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00036885235529645174, | |
| "loss": 0.1964, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00036783990382720894, | |
| "loss": 0.1714, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000366540903911771, | |
| "loss": 0.1556, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00036495739222857005, | |
| "loss": 0.1454, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00036309185153688393, | |
| "loss": 0.1387, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003609472067841633, | |
| "loss": 0.133, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003585268205200591, | |
| "loss": 0.1289, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003558344876243421, | |
| "loss": 0.1228, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003528744293569798, | |
| "loss": 0.1208, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00034965128673969907, | |
| "loss": 0.1167, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003461701132794125, | |
| "loss": 0.1131, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003424363670449164, | |
| "loss": 0.1113, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00033845590210928363, | |
| "loss": 0.1088, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00033423495937136847, | |
| "loss": 0.1081, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00032978015677081454, | |
| "loss": 0.1054, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00032509847891190683, | |
| "loss": 0.1029, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003201972661125376, | |
| "loss": 0.102, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003150842028954544, | |
| "loss": 0.0999, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003097673059398367, | |
| "loss": 0.098, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00030425491151208934, | |
| "loss": 0.0972, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00029855566239556173, | |
| "loss": 0.0968, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002926784943396845, | |
| "loss": 0.0947, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00028663262204976965, | |
| "loss": 0.0933, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00028042752473944106, | |
| "loss": 0.094, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9297529150299436, | |
| "eval_auc": 0.8167222019799886, | |
| "eval_f1": 0.3440490710592986, | |
| "eval_loss": 0.6011912822723389, | |
| "eval_mcc": 0.3730152153022164, | |
| "eval_precision": 0.22835223718675476, | |
| "eval_recall": 0.697386656717114, | |
| "eval_runtime": 3756.1015, | |
| "eval_samples_per_second": 144.201, | |
| "eval_steps_per_second": 0.687, | |
| "step": 5289 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00027407293126834736, | |
| "loss": 0.0924, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00026757880488845914, | |
| "loss": 0.0912, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00026095532762286633, | |
| "loss": 0.0902, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002542128843015694, | |
| "loss": 0.09, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00024739655239955165, | |
| "loss": 0.0901, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00024048348750604134, | |
| "loss": 0.0889, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00023344905030678293, | |
| "loss": 0.0872, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00022633877364566408, | |
| "loss": 0.0873, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0002191638055966375, | |
| "loss": 0.0866, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00021193539566211078, | |
| "loss": 0.0864, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00020466487713505563, | |
| "loss": 0.085, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.000197363649329743, | |
| "loss": 0.086, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00019004315970896487, | |
| "loss": 0.0847, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00018271488593576474, | |
| "loss": 0.0836, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0001753903178778174, | |
| "loss": 0.0844, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00016808093959267418, | |
| "loss": 0.0828, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00016079821132211663, | |
| "loss": 0.0848, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00015355355152385142, | |
| "loss": 0.0826, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00014635831896871702, | |
| "loss": 0.0826, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00013922379493147316, | |
| "loss": 0.0833, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0001321611655030941, | |
| "loss": 0.0816, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00012518150405229972, | |
| "loss": 0.0817, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001182957538638206, | |
| "loss": 0.0827, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011151471098062111, | |
| "loss": 0.0807, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010484900727697857, | |
| "loss": 0.0818, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.830909378896018e-05, | |
| "loss": 0.0811, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9345128329975654, | |
| "eval_auc": 0.8095464647248594, | |
| "eval_f1": 0.3534505903118732, | |
| "eval_loss": 0.646632730960846, | |
| "eval_mcc": 0.37724366807619925, | |
| "eval_precision": 0.23907868925380343, | |
| "eval_recall": 0.6776094956043187, | |
| "eval_runtime": 3741.5855, | |
| "eval_samples_per_second": 144.761, | |
| "eval_steps_per_second": 0.69, | |
| "step": 10578 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 15867, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 8.013035409672134e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |