| { | |
| "best_metric": 0.2273811250925064, | |
| "best_model_checkpoint": "/content/dnrti_secbert/checkpoint-2500", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 6570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8477929984779303e-05, | |
| "loss": 0.6137, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.8841643897996357, | |
| "eval_f1": 0.5633311532592108, | |
| "eval_loss": 0.37306320667266846, | |
| "eval_precision": 0.5347682119205298, | |
| "eval_recall": 0.5951174573929064, | |
| "eval_runtime": 1.4634, | |
| "eval_samples_per_second": 451.693, | |
| "eval_steps_per_second": 56.718, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.69558599695586e-05, | |
| "loss": 0.2993, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.9130806010928961, | |
| "eval_f1": 0.6674354243542435, | |
| "eval_loss": 0.28528016805648804, | |
| "eval_precision": 0.6683602771362587, | |
| "eval_recall": 0.6665131275909719, | |
| "eval_runtime": 1.4759, | |
| "eval_samples_per_second": 447.863, | |
| "eval_steps_per_second": 56.237, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.54337899543379e-05, | |
| "loss": 0.2157, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.9211634790528234, | |
| "eval_f1": 0.6970899470899472, | |
| "eval_loss": 0.262411504983902, | |
| "eval_precision": 0.6684989429175475, | |
| "eval_recall": 0.7282358360202672, | |
| "eval_runtime": 2.0477, | |
| "eval_samples_per_second": 322.8, | |
| "eval_steps_per_second": 40.533, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.39117199391172e-05, | |
| "loss": 0.152, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.9308401639344263, | |
| "eval_f1": 0.725438596491228, | |
| "eval_loss": 0.24139739573001862, | |
| "eval_precision": 0.6923398911678527, | |
| "eval_recall": 0.7618608935974206, | |
| "eval_runtime": 1.5039, | |
| "eval_samples_per_second": 439.515, | |
| "eval_steps_per_second": 55.189, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.2389649923896501e-05, | |
| "loss": 0.1047, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_accuracy": 0.9389230418943534, | |
| "eval_f1": 0.7587601078167115, | |
| "eval_loss": 0.2273811250925064, | |
| "eval_precision": 0.7404647084612013, | |
| "eval_recall": 0.7779824965453708, | |
| "eval_runtime": 1.5152, | |
| "eval_samples_per_second": 436.244, | |
| "eval_steps_per_second": 54.778, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.08675799086758e-05, | |
| "loss": 0.0725, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_accuracy": 0.9370446265938069, | |
| "eval_f1": 0.7596660808435852, | |
| "eval_loss": 0.2562768757343292, | |
| "eval_precision": 0.7261654766904662, | |
| "eval_recall": 0.7964071856287425, | |
| "eval_runtime": 1.5216, | |
| "eval_samples_per_second": 434.416, | |
| "eval_steps_per_second": 54.548, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 9.3455098934551e-06, | |
| "loss": 0.0589, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_accuracy": 0.9411429872495446, | |
| "eval_f1": 0.774738714698688, | |
| "eval_loss": 0.26153579354286194, | |
| "eval_precision": 0.7489251934651763, | |
| "eval_recall": 0.8023952095808383, | |
| "eval_runtime": 1.9808, | |
| "eval_samples_per_second": 333.701, | |
| "eval_steps_per_second": 41.902, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 7.823439878234399e-06, | |
| "loss": 0.0442, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_accuracy": 0.9433629326047359, | |
| "eval_f1": 0.779336450679136, | |
| "eval_loss": 0.2637869119644165, | |
| "eval_precision": 0.7543103448275862, | |
| "eval_recall": 0.8060801473975127, | |
| "eval_runtime": 1.5001, | |
| "eval_samples_per_second": 440.626, | |
| "eval_steps_per_second": 55.328, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 6.301369863013699e-06, | |
| "loss": 0.0344, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_accuracy": 0.9447859744990893, | |
| "eval_f1": 0.785506598076493, | |
| "eval_loss": 0.26708078384399414, | |
| "eval_precision": 0.7634782608695653, | |
| "eval_recall": 0.8088438507600184, | |
| "eval_runtime": 1.9259, | |
| "eval_samples_per_second": 343.219, | |
| "eval_steps_per_second": 43.097, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 4.779299847792998e-06, | |
| "loss": 0.0282, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_accuracy": 0.9438752276867031, | |
| "eval_f1": 0.7838860449588249, | |
| "eval_loss": 0.28605297207832336, | |
| "eval_precision": 0.7583979328165374, | |
| "eval_recall": 0.8111469368954399, | |
| "eval_runtime": 1.5173, | |
| "eval_samples_per_second": 435.655, | |
| "eval_steps_per_second": 54.704, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 3.2572298325722984e-06, | |
| "loss": 0.0226, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "eval_accuracy": 0.9455828779599271, | |
| "eval_f1": 0.7887766554433222, | |
| "eval_loss": 0.2849014401435852, | |
| "eval_precision": 0.7692644483362522, | |
| "eval_recall": 0.8093044679871028, | |
| "eval_runtime": 1.5171, | |
| "eval_samples_per_second": 435.699, | |
| "eval_steps_per_second": 54.71, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.7351598173515982e-06, | |
| "loss": 0.0207, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_accuracy": 0.9456397996357013, | |
| "eval_f1": 0.7904804270462633, | |
| "eval_loss": 0.29320821166038513, | |
| "eval_precision": 0.7643010752688172, | |
| "eval_recall": 0.8185168125287886, | |
| "eval_runtime": 1.5264, | |
| "eval_samples_per_second": 433.036, | |
| "eval_steps_per_second": 54.375, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 2.1308980213089802e-07, | |
| "loss": 0.0181, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_accuracy": 0.9459244080145719, | |
| "eval_f1": 0.7908117752007137, | |
| "eval_loss": 0.29524117708206177, | |
| "eval_precision": 0.7665369649805448, | |
| "eval_recall": 0.8166743436204514, | |
| "eval_runtime": 1.5318, | |
| "eval_samples_per_second": 431.505, | |
| "eval_steps_per_second": 54.183, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 6570, | |
| "total_flos": 665046616558140.0, | |
| "train_loss": 0.12845844870470066, | |
| "train_runtime": 531.3663, | |
| "train_samples_per_second": 98.802, | |
| "train_steps_per_second": 12.364 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6570, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 665046616558140.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |