{ "best_metric": 0.21624045073986053, "best_model_checkpoint": "/hpcwork/vg380347/NER/EduGBERT/checkpoint-550", "epoch": 7.446808510638298, "eval_steps": 50, "global_step": 1050, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.35, "eval_f1": 0.5815712900096993, "eval_loss": 0.3045153319835663, "eval_precision": 0.5216332212040367, "eval_recall": 0.6570718877849211, "eval_runtime": 7.1562, "eval_samples_per_second": 629.381, "eval_steps_per_second": 5.031, "step": 50 }, { "epoch": 0.71, "eval_f1": 0.6822522225880804, "eval_loss": 0.25079214572906494, "eval_precision": 0.6210286536386525, "eval_recall": 0.7568673290473408, "eval_runtime": 7.2954, "eval_samples_per_second": 617.376, "eval_steps_per_second": 4.935, "step": 100 }, { "epoch": 1.06, "eval_f1": 0.7016087182148418, "eval_loss": 0.24814821779727936, "eval_precision": 0.6308912739150724, "eval_recall": 0.7901811805961426, "eval_runtime": 7.1783, "eval_samples_per_second": 627.45, "eval_steps_per_second": 5.015, "step": 150 }, { "epoch": 1.42, "eval_f1": 0.7199271355149306, "eval_loss": 0.2445540428161621, "eval_precision": 0.6488800281458895, "eval_recall": 0.8084453535943893, "eval_runtime": 7.1384, "eval_samples_per_second": 630.95, "eval_steps_per_second": 5.043, "step": 200 }, { "epoch": 1.77, "eval_f1": 0.722252082773448, "eval_loss": 0.22964715957641602, "eval_precision": 0.6685323383084577, "eval_recall": 0.7853594389246055, "eval_runtime": 7.434, "eval_samples_per_second": 605.866, "eval_steps_per_second": 4.843, "step": 250 }, { "epoch": 2.13, "eval_f1": 0.7319960997353392, "eval_loss": 0.21758420765399933, "eval_precision": 0.6993611924407772, "eval_recall": 0.7678258328462887, "eval_runtime": 7.1469, "eval_samples_per_second": 630.207, "eval_steps_per_second": 5.037, "step": 300 }, { "epoch": 2.48, "eval_f1": 0.7406113537117905, "eval_loss": 0.22185301780700684, "eval_precision": 0.6854868797413257, "eval_recall": 0.8053769725306839, "eval_runtime": 7.1574, "eval_samples_per_second": 629.281, "eval_steps_per_second": 5.03, "step": 350 }, { "epoch": 2.84, "eval_f1": 0.7412340309866812, "eval_loss": 0.2164618819952011, "eval_precision": 0.6928353658536586, "eval_recall": 0.7969023962594973, "eval_runtime": 7.1409, "eval_samples_per_second": 630.735, "eval_steps_per_second": 5.041, "step": 400 }, { "epoch": 3.19, "eval_f1": 0.7499483221938952, "eval_loss": 0.2220638245344162, "eval_precision": 0.7096101186595384, "eval_recall": 0.7951490356516657, "eval_runtime": 7.4483, "eval_samples_per_second": 604.703, "eval_steps_per_second": 4.833, "step": 450 }, { "epoch": 3.55, "learning_rate": 4.822695035460993e-06, "loss": 0.2581, "step": 500 }, { "epoch": 3.55, "eval_f1": 0.7439247452312516, "eval_loss": 0.2487693727016449, "eval_precision": 0.6727315689981096, "eval_recall": 0.8319696084161309, "eval_runtime": 7.1497, "eval_samples_per_second": 629.957, "eval_steps_per_second": 5.035, "step": 500 }, { "epoch": 3.9, "eval_f1": 0.7555155958226711, "eval_loss": 0.21624045073986053, "eval_precision": 0.717268548916612, "eval_recall": 0.7980713033313852, "eval_runtime": 7.1536, "eval_samples_per_second": 629.612, "eval_steps_per_second": 5.032, "step": 550 }, { "epoch": 4.26, "eval_f1": 0.7588671611598112, "eval_loss": 0.23951853811740875, "eval_precision": 0.7046080641121963, "eval_recall": 0.8221800116890707, "eval_runtime": 7.0397, "eval_samples_per_second": 639.8, "eval_steps_per_second": 5.114, "step": 600 }, { "epoch": 4.61, "eval_f1": 0.7562726374711887, "eval_loss": 0.24661774933338165, "eval_precision": 0.688406665867402, "eval_recall": 0.8389830508474576, "eval_runtime": 7.1388, "eval_samples_per_second": 630.916, "eval_steps_per_second": 5.043, "step": 650 }, { "epoch": 4.96, "eval_f1": 0.7577822311289245, "eval_loss": 0.24025806784629822, "eval_precision": 0.6980063992124046, "eval_recall": 0.8287551139684395, "eval_runtime": 7.1329, "eval_samples_per_second": 631.441, "eval_steps_per_second": 5.047, "step": 700 }, { "epoch": 5.32, "eval_f1": 0.7517815517815518, "eval_loss": 0.261866956949234, "eval_precision": 0.6907355280871375, "eval_recall": 0.8246639392168322, "eval_runtime": 7.3254, "eval_samples_per_second": 614.846, "eval_steps_per_second": 4.914, "step": 750 }, { "epoch": 5.67, "eval_f1": 0.7615306467998646, "eval_loss": 0.2429821491241455, "eval_precision": 0.7097588688296932, "eval_recall": 0.8214494447691408, "eval_runtime": 7.1352, "eval_samples_per_second": 631.236, "eval_steps_per_second": 5.045, "step": 800 }, { "epoch": 6.03, "eval_f1": 0.7594460131773565, "eval_loss": 0.24021703004837036, "eval_precision": 0.7033623910336239, "eval_recall": 0.8252483927527762, "eval_runtime": 7.155, "eval_samples_per_second": 629.489, "eval_steps_per_second": 5.031, "step": 850 }, { "epoch": 6.38, "eval_f1": 0.7594716019580233, "eval_loss": 0.25845229625701904, "eval_precision": 0.70182178708638, "eval_recall": 0.8274400935125658, "eval_runtime": 7.1743, "eval_samples_per_second": 627.796, "eval_steps_per_second": 5.018, "step": 900 }, { "epoch": 6.74, "eval_f1": 0.7634940255459416, "eval_loss": 0.2463415563106537, "eval_precision": 0.7202643171806168, "eval_recall": 0.8122443015780245, "eval_runtime": 7.1315, "eval_samples_per_second": 631.568, "eval_steps_per_second": 5.048, "step": 950 }, { "epoch": 7.09, "learning_rate": 4.645390070921986e-06, "loss": 0.1517, "step": 1000 }, { "epoch": 7.09, "eval_f1": 0.7641669494401085, "eval_loss": 0.25761693716049194, "eval_precision": 0.7134710429603346, "eval_recall": 0.8226183518410286, "eval_runtime": 7.1379, "eval_samples_per_second": 630.995, "eval_steps_per_second": 5.043, "step": 1000 }, { "epoch": 7.45, "eval_f1": 0.7703476197124111, "eval_loss": 0.2536332607269287, "eval_precision": 0.7375033413525796, "eval_recall": 0.8062536528345996, "eval_runtime": 7.1375, "eval_samples_per_second": 631.035, "eval_steps_per_second": 5.044, "step": 1050 } ], "logging_steps": 500, "max_steps": 14100, "num_train_epochs": 100, "save_steps": 50, "total_flos": 6.408198647855674e+16, "trial_name": null, "trial_params": null }