| { | |
| "best_metric": 0.771723286444866, | |
| "best_model_checkpoint": "./tokcl_models/EMBO_bert-base-cased_NER-task/checkpoint-2000", | |
| "epoch": 3.9318479685452163, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0004934469200524247, | |
| "loss": 1.0092, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00048689384010484925, | |
| "loss": 0.4881, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0004803407601572739, | |
| "loss": 0.3663, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0004737876802096986, | |
| "loss": 0.3384, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00046723460026212323, | |
| "loss": 0.3115, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00046068152031454785, | |
| "loss": 0.2999, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0004541284403669725, | |
| "loss": 0.271, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0004475753604193971, | |
| "loss": 0.2692, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00044102228047182177, | |
| "loss": 0.2574, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0004344692005242464, | |
| "loss": 0.2485, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00042791612057667107, | |
| "loss": 0.2467, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0004213630406290957, | |
| "loss": 0.2528, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0004148099606815203, | |
| "loss": 0.2472, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00040825688073394494, | |
| "loss": 0.241, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0004017038007863696, | |
| "loss": 0.2363, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00039515072083879424, | |
| "loss": 0.2104, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0003885976408912189, | |
| "loss": 0.1935, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00038204456094364353, | |
| "loss": 0.1939, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00037549148099606816, | |
| "loss": 0.1924, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0003689384010484928, | |
| "loss": 0.1938, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy_score": 0.9050444524751189, | |
| "eval_f1": 0.7458701475198578, | |
| "eval_loss": 0.2917892336845398, | |
| "eval_precision": 0.7596363560104018, | |
| "eval_recall": 0.7325940033370975, | |
| "eval_runtime": 111.3074, | |
| "eval_samples_per_second": 123.99, | |
| "eval_steps_per_second": 0.97, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00036238532110091746, | |
| "loss": 0.1825, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0003558322411533421, | |
| "loss": 0.1898, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0003492791612057667, | |
| "loss": 0.1858, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0003427260812581914, | |
| "loss": 0.182, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.000336173001310616, | |
| "loss": 0.1853, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0003296199213630406, | |
| "loss": 0.1869, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0003230668414154653, | |
| "loss": 0.1771, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0003165137614678899, | |
| "loss": 0.1759, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00030996068152031454, | |
| "loss": 0.1705, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00030340760157273916, | |
| "loss": 0.1786, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00029685452162516384, | |
| "loss": 0.1589, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00029030144167758846, | |
| "loss": 0.1364, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00028374836173001314, | |
| "loss": 0.1319, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.00027719528178243776, | |
| "loss": 0.1283, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0002706422018348624, | |
| "loss": 0.1266, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.000264089121887287, | |
| "loss": 0.1359, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002575360419397117, | |
| "loss": 0.1271, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0002509829619921363, | |
| "loss": 0.1328, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.000244429882044561, | |
| "loss": 0.1328, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002378768020969856, | |
| "loss": 0.138, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy_score": 0.9121489075478695, | |
| "eval_f1": 0.771723286444866, | |
| "eval_loss": 0.2743813991546631, | |
| "eval_precision": 0.751326535173136, | |
| "eval_recall": 0.7932583890920736, | |
| "eval_runtime": 111.6996, | |
| "eval_samples_per_second": 123.555, | |
| "eval_steps_per_second": 0.967, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00023132372214941022, | |
| "loss": 0.1305, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00022477064220183487, | |
| "loss": 0.1243, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.00021821756225425952, | |
| "loss": 0.1265, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00021166448230668415, | |
| "loss": 0.133, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.00020511140235910877, | |
| "loss": 0.1298, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00019855832241153344, | |
| "loss": 0.123, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.00019200524246395807, | |
| "loss": 0.0871, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.0001854521625163827, | |
| "loss": 0.086, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00017889908256880736, | |
| "loss": 0.0928, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.000172346002621232, | |
| "loss": 0.083, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.0001657929226736566, | |
| "loss": 0.0918, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.00015923984272608129, | |
| "loss": 0.0849, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.0001526867627785059, | |
| "loss": 0.0863, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00014613368283093053, | |
| "loss": 0.0865, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00013958060288335518, | |
| "loss": 0.0827, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00013302752293577983, | |
| "loss": 0.083, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.00012647444298820445, | |
| "loss": 0.0849, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.0001199213630406291, | |
| "loss": 0.0813, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00011336828309305374, | |
| "loss": 0.0873, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00010681520314547838, | |
| "loss": 0.0808, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_accuracy_score": 0.909553294853392, | |
| "eval_f1": 0.7627703980346628, | |
| "eval_loss": 0.3164892792701721, | |
| "eval_precision": 0.7620479900951458, | |
| "eval_recall": 0.7634941769335782, | |
| "eval_runtime": 111.6078, | |
| "eval_samples_per_second": 123.656, | |
| "eval_steps_per_second": 0.968, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 3815, | |
| "num_train_epochs": 5, | |
| "total_flos": 3.419886505231602e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |