| { | |
| "best_metric": 0.8244957371594926, | |
| "best_model_checkpoint": "./my_unified_model_classification_only_value/checkpoint-1200", | |
| "epoch": 1.8154311649016641, | |
| "eval_steps": 200, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07564296520423601, | |
| "grad_norm": 53.5, | |
| "learning_rate": 3.7878787878787882e-06, | |
| "loss": 0.898, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15128593040847202, | |
| "grad_norm": 35.25, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.686, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22692889561270801, | |
| "grad_norm": 80.5, | |
| "learning_rate": 9.848739495798321e-06, | |
| "loss": 0.6538, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.30257186081694404, | |
| "grad_norm": 16.5, | |
| "learning_rate": 9.42857142857143e-06, | |
| "loss": 0.5964, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.30257186081694404, | |
| "eval_accuracy": 0.7317742851732626, | |
| "eval_auc": 0.8013802237782263, | |
| "eval_f1": 0.7138094757046166, | |
| "eval_false_negatives": 1426, | |
| "eval_false_positives": 1407, | |
| "eval_loss": 0.5440672636032104, | |
| "eval_precision": 0.7151821862348178, | |
| "eval_recall": 0.7124420246017342, | |
| "eval_runtime": 372.1925, | |
| "eval_samples_per_second": 28.378, | |
| "eval_specificity": 0.7488845261467071, | |
| "eval_steps_per_second": 0.223, | |
| "eval_true_negatives": 4196, | |
| "eval_true_positives": 3533, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.30257186081694404, | |
| "step": 200, | |
| "train_accuracy": 0.754, | |
| "train_auc": 0.8275891870163803, | |
| "train_f1": 0.7399577167019028, | |
| "train_false_negatives": 115, | |
| "train_false_positives": 131, | |
| "train_loss": 0.5138152837753296, | |
| "train_precision": 0.7276507276507277, | |
| "train_recall": 0.7526881720430108, | |
| "train_runtime": 35.2326, | |
| "train_samples_per_second": 28.383, | |
| "train_specificity": 0.7551401869158878, | |
| "train_steps_per_second": 0.227, | |
| "train_true_negatives": 404, | |
| "train_true_positives": 350 | |
| }, | |
| { | |
| "epoch": 0.37821482602118, | |
| "grad_norm": 59.5, | |
| "learning_rate": 9.008403361344538e-06, | |
| "loss": 0.5647, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.45385779122541603, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 8.588235294117647e-06, | |
| "loss": 0.528, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.529500756429652, | |
| "grad_norm": 22.625, | |
| "learning_rate": 8.168067226890757e-06, | |
| "loss": 0.5223, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6051437216338881, | |
| "grad_norm": 15.9375, | |
| "learning_rate": 7.747899159663867e-06, | |
| "loss": 0.4929, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6051437216338881, | |
| "eval_accuracy": 0.7788297670895664, | |
| "eval_auc": 0.8526692031898765, | |
| "eval_f1": 0.7375870590878454, | |
| "eval_false_negatives": 1676, | |
| "eval_false_positives": 660, | |
| "eval_loss": 0.48032745718955994, | |
| "eval_precision": 0.8326147603347704, | |
| "eval_recall": 0.6620286348054043, | |
| "eval_runtime": 372.0488, | |
| "eval_samples_per_second": 28.389, | |
| "eval_specificity": 0.882205961092272, | |
| "eval_steps_per_second": 0.223, | |
| "eval_true_negatives": 4943, | |
| "eval_true_positives": 3283, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6051437216338881, | |
| "step": 400, | |
| "train_accuracy": 0.795, | |
| "train_auc": 0.8693421116328606, | |
| "train_f1": 0.7484662576687117, | |
| "train_false_negatives": 149, | |
| "train_false_positives": 56, | |
| "train_loss": 0.45130425691604614, | |
| "train_precision": 0.8448753462603878, | |
| "train_recall": 0.6718061674008811, | |
| "train_runtime": 35.2264, | |
| "train_samples_per_second": 28.388, | |
| "train_specificity": 0.8974358974358975, | |
| "train_steps_per_second": 0.227, | |
| "train_true_negatives": 490, | |
| "train_true_positives": 305 | |
| }, | |
| { | |
| "epoch": 0.680786686838124, | |
| "grad_norm": 17.375, | |
| "learning_rate": 7.327731092436975e-06, | |
| "loss": 0.4769, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.75642965204236, | |
| "grad_norm": 41.0, | |
| "learning_rate": 6.907563025210084e-06, | |
| "loss": 0.4651, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8320726172465961, | |
| "grad_norm": 19.875, | |
| "learning_rate": 6.487394957983194e-06, | |
| "loss": 0.4485, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9077155824508321, | |
| "grad_norm": 58.0, | |
| "learning_rate": 6.067226890756302e-06, | |
| "loss": 0.4357, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9077155824508321, | |
| "eval_accuracy": 0.7956826358644196, | |
| "eval_auc": 0.8850468901209803, | |
| "eval_f1": 0.7943978658536586, | |
| "eval_false_negatives": 790, | |
| "eval_false_positives": 1368, | |
| "eval_loss": 0.4417967200279236, | |
| "eval_precision": 0.7529348022394798, | |
| "eval_recall": 0.8406936882435975, | |
| "eval_runtime": 371.6055, | |
| "eval_samples_per_second": 28.423, | |
| "eval_specificity": 0.7558450829912546, | |
| "eval_steps_per_second": 0.223, | |
| "eval_true_negatives": 4235, | |
| "eval_true_positives": 4169, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9077155824508321, | |
| "step": 600, | |
| "train_accuracy": 0.847, | |
| "train_auc": 0.9328790111985132, | |
| "train_f1": 0.8452982810920121, | |
| "train_false_negatives": 64, | |
| "train_false_positives": 89, | |
| "train_loss": 0.34708184003829956, | |
| "train_precision": 0.8244575936883629, | |
| "train_recall": 0.8672199170124482, | |
| "train_runtime": 35.1806, | |
| "train_samples_per_second": 28.425, | |
| "train_specificity": 0.8281853281853282, | |
| "train_steps_per_second": 0.227, | |
| "train_true_negatives": 429, | |
| "train_true_positives": 418 | |
| }, | |
| { | |
| "epoch": 0.983358547655068, | |
| "grad_norm": 18.25, | |
| "learning_rate": 5.6470588235294125e-06, | |
| "loss": 0.4242, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.059001512859304, | |
| "grad_norm": 17.75, | |
| "learning_rate": 5.226890756302522e-06, | |
| "loss": 0.3567, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.13464447806354, | |
| "grad_norm": 24.0, | |
| "learning_rate": 4.80672268907563e-06, | |
| "loss": 0.318, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.2102874432677762, | |
| "grad_norm": 30.25, | |
| "learning_rate": 4.38655462184874e-06, | |
| "loss": 0.3148, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2102874432677762, | |
| "eval_accuracy": 0.825979928043931, | |
| "eval_auc": 0.9069594483438117, | |
| "eval_f1": 0.8147924224103185, | |
| "eval_false_negatives": 916, | |
| "eval_false_positives": 922, | |
| "eval_loss": 0.39389899373054504, | |
| "eval_precision": 0.8143001007049345, | |
| "eval_recall": 0.8152853397862472, | |
| "eval_runtime": 371.6744, | |
| "eval_samples_per_second": 28.417, | |
| "eval_specificity": 0.8354452971622345, | |
| "eval_steps_per_second": 0.223, | |
| "eval_true_negatives": 4681, | |
| "eval_true_positives": 4043, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2102874432677762, | |
| "step": 800, | |
| "train_accuracy": 0.906, | |
| "train_auc": 0.9618160544261452, | |
| "train_f1": 0.8993576017130621, | |
| "train_false_negatives": 44, | |
| "train_false_positives": 50, | |
| "train_loss": 0.2517271935939789, | |
| "train_precision": 0.8936170212765957, | |
| "train_recall": 0.9051724137931034, | |
| "train_runtime": 35.2079, | |
| "train_samples_per_second": 28.403, | |
| "train_specificity": 0.9067164179104478, | |
| "train_steps_per_second": 0.227, | |
| "train_true_negatives": 486, | |
| "train_true_positives": 420 | |
| }, | |
| { | |
| "epoch": 1.2859304084720122, | |
| "grad_norm": 21.375, | |
| "learning_rate": 3.966386554621849e-06, | |
| "loss": 0.3124, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.361573373676248, | |
| "grad_norm": 17.25, | |
| "learning_rate": 3.5462184873949586e-06, | |
| "loss": 0.3127, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4372163388804842, | |
| "grad_norm": 21.5, | |
| "learning_rate": 3.1260504201680676e-06, | |
| "loss": 0.3088, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.5128593040847202, | |
| "grad_norm": 22.25, | |
| "learning_rate": 2.7058823529411766e-06, | |
| "loss": 0.301, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5128593040847202, | |
| "eval_accuracy": 0.8364893012686991, | |
| "eval_auc": 0.9148794341693984, | |
| "eval_f1": 0.8227081408479622, | |
| "eval_false_negatives": 952, | |
| "eval_false_positives": 775, | |
| "eval_loss": 0.36996448040008545, | |
| "eval_precision": 0.8379339188624007, | |
| "eval_recall": 0.8080258116555757, | |
| "eval_runtime": 370.6939, | |
| "eval_samples_per_second": 28.493, | |
| "eval_specificity": 0.8616812421916831, | |
| "eval_steps_per_second": 0.224, | |
| "eval_true_negatives": 4828, | |
| "eval_true_positives": 4007, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5128593040847202, | |
| "step": 1000, | |
| "train_accuracy": 0.885, | |
| "train_auc": 0.9480568101736178, | |
| "train_f1": 0.8788198103266597, | |
| "train_false_negatives": 67, | |
| "train_false_positives": 48, | |
| "train_loss": 0.2890710234642029, | |
| "train_precision": 0.896774193548387, | |
| "train_recall": 0.8615702479338843, | |
| "train_runtime": 35.1213, | |
| "train_samples_per_second": 28.473, | |
| "train_specificity": 0.9069767441860465, | |
| "train_steps_per_second": 0.228, | |
| "train_true_negatives": 468, | |
| "train_true_positives": 417 | |
| }, | |
| { | |
| "epoch": 1.588502269288956, | |
| "grad_norm": 30.875, | |
| "learning_rate": 2.285714285714286e-06, | |
| "loss": 0.2952, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.6641452344931922, | |
| "grad_norm": 31.25, | |
| "learning_rate": 1.8655462184873952e-06, | |
| "loss": 0.2759, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.7397881996974283, | |
| "grad_norm": 32.25, | |
| "learning_rate": 1.4453781512605044e-06, | |
| "loss": 0.2856, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.8154311649016641, | |
| "grad_norm": 27.125, | |
| "learning_rate": 1.0252100840336135e-06, | |
| "loss": 0.2962, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8154311649016641, | |
| "eval_accuracy": 0.8401817837530771, | |
| "eval_auc": 0.9181502131506554, | |
| "eval_f1": 0.8244957371594926, | |
| "eval_false_negatives": 994, | |
| "eval_false_positives": 694, | |
| "eval_loss": 0.3659172058105469, | |
| "eval_precision": 0.8510409959218717, | |
| "eval_recall": 0.7995563621697923, | |
| "eval_runtime": 371.7873, | |
| "eval_samples_per_second": 28.409, | |
| "eval_specificity": 0.8761377833303587, | |
| "eval_steps_per_second": 0.223, | |
| "eval_true_negatives": 4909, | |
| "eval_true_positives": 3965, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8154311649016641, | |
| "step": 1200, | |
| "train_accuracy": 0.908, | |
| "train_auc": 0.9683581113009341, | |
| "train_f1": 0.8956916099773242, | |
| "train_false_negatives": 56, | |
| "train_false_positives": 36, | |
| "train_loss": 0.23525048792362213, | |
| "train_precision": 0.9164733178654292, | |
| "train_recall": 0.8758314855875832, | |
| "train_runtime": 35.2492, | |
| "train_samples_per_second": 28.369, | |
| "train_specificity": 0.9344262295081968, | |
| "train_steps_per_second": 0.227, | |
| "train_true_negatives": 513, | |
| "train_true_positives": 395 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1322, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.577793841952973e+18, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |