--- license: apache-2.0 base_model: distilbert-base-cased tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: trainerH results: [] --- # trainerH This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.9689 - Precision: 0.8231 - Recall: 0.8151 - F1: 0.8155 - Accuracy: 0.8151 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 1.9367 | 0.14 | 30 | 1.8290 | 0.1621 | 0.2605 | 0.1694 | 0.2605 | | 1.8256 | 0.27 | 60 | 1.7350 | 0.1476 | 0.2745 | 0.1786 | 0.2745 | | 1.6271 | 0.41 | 90 | 1.5305 | 0.4700 | 0.4594 | 0.3823 | 0.4594 | | 1.3898 | 0.54 | 120 | 1.3535 | 0.5555 | 0.4790 | 0.4664 | 0.4790 | | 1.2341 | 0.68 | 150 | 1.0183 | 0.7309 | 0.7087 | 0.7041 | 0.7087 | | 1.0666 | 0.81 | 180 | 0.9651 | 0.7280 | 0.6583 | 0.6284 | 0.6583 | | 0.8155 | 0.95 | 210 | 0.8172 | 0.7889 | 0.7647 | 0.7620 | 0.7647 | | 0.6679 | 1.08 | 240 | 0.6941 | 0.7973 | 0.7843 | 0.7818 | 0.7843 | | 0.52 | 1.22 | 270 | 0.6729 | 0.8009 | 0.7927 | 0.7921 | 0.7927 | | 0.4683 | 1.35 | 300 | 0.7385 | 0.8072 | 0.7955 | 0.7962 | 0.7955 | | 0.3937 | 1.49 | 330 | 0.6951 | 0.8094 | 0.7983 | 0.7994 | 0.7983 | | 0.4883 | 1.62 | 360 | 0.6793 | 0.8099 | 0.8039 | 0.8034 | 0.8039 | | 0.4532 | 1.76 | 390 | 0.6710 | 0.8108 | 0.8067 | 0.8046 | 0.8067 | | 0.3099 | 1.89 | 420 | 0.6839 | 0.8136 | 0.8067 | 0.8055 | 0.8067 | | 0.3798 | 2.03 | 450 | 0.8117 | 0.8197 | 0.8095 | 0.8099 | 0.8095 | | 0.2304 | 2.16 | 480 | 0.7814 | 0.8299 | 0.8263 | 0.8251 | 0.8263 | | 0.1489 | 2.3 | 510 | 0.8918 | 0.8082 | 0.7955 | 0.7943 | 0.7955 | | 0.1525 | 2.43 | 540 | 0.9288 | 0.8161 | 0.8039 | 0.8048 | 0.8039 | | 0.2774 | 2.57 | 570 | 0.8478 | 0.8347 | 0.8291 | 0.8278 | 0.8291 | | 0.2452 | 2.7 | 600 | 0.8499 | 0.8342 | 0.8291 | 0.8296 | 0.8291 | | 0.1811 | 2.84 | 630 | 0.8531 | 0.8381 | 0.8347 | 0.8340 | 0.8347 | | 0.1509 | 2.97 | 660 | 0.9766 | 0.8150 | 0.7955 | 0.7967 | 0.7955 | | 0.1073 | 3.11 | 690 | 0.8532 | 0.8269 | 0.8179 | 0.8179 | 0.8179 | | 0.1273 | 3.24 | 720 | 0.9157 | 0.8315 | 0.8235 | 0.8247 | 0.8235 | | 0.0614 | 3.38 | 750 | 0.9050 | 0.8364 | 0.8291 | 0.8303 | 0.8291 | | 0.0876 | 3.51 | 780 | 0.9221 | 0.8421 | 0.8347 | 0.8352 | 0.8347 | | 0.0574 | 3.65 | 810 | 0.9416 | 0.8351 | 0.8263 | 0.8273 | 0.8263 | | 0.0783 | 3.78 | 840 | 0.9414 | 0.8377 | 0.8291 | 0.8302 | 0.8291 | | 0.0357 | 3.92 | 870 | 0.9270 | 0.8312 | 0.8207 | 0.8219 | 0.8207 | | 0.0589 | 4.05 | 900 | 0.9254 | 0.8379 | 0.8263 | 0.8275 | 0.8263 | | 0.0297 | 4.19 | 930 | 0.9402 | 0.8189 | 0.8095 | 0.8104 | 0.8095 | | 0.0324 | 4.32 | 960 | 0.9545 | 0.8303 | 0.8235 | 0.8241 | 0.8235 | | 0.0405 | 4.46 | 990 | 0.9574 | 0.8273 | 0.8207 | 0.8209 | 0.8207 | | 0.0039 | 4.59 | 1020 | 0.9553 | 0.8309 | 0.8235 | 0.8240 | 0.8235 | | 0.0052 | 4.73 | 1050 | 0.9650 | 0.8335 | 0.8263 | 0.8267 | 0.8263 | | 0.0473 | 4.86 | 1080 | 0.9678 | 0.8259 | 0.8179 | 0.8186 | 0.8179 | | 0.0417 | 5.0 | 1110 | 0.9689 | 0.8231 | 0.8151 | 0.8155 | 0.8151 | ### Framework versions - Transformers 4.39.1 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2