--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: V10-distilbert-text-classification-model results: [] --- # V10-distilbert-text-classification-model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2088 - Accuracy: 0.9546 - F1: 0.8213 - Precision: 0.8192 - Recall: 0.8243 ## 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: 16 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 4 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | 1.5687 | 0.11 | 50 | 2.1779 | 0.1200 | 0.0687 | 0.0913 | 0.0550 | | 1.1872 | 0.22 | 100 | 1.1610 | 0.6475 | 0.4010 | 0.4470 | 0.3901 | | 0.6574 | 0.33 | 150 | 0.9675 | 0.6300 | 0.3389 | 0.4603 | 0.3683 | | 0.548 | 0.44 | 200 | 0.6524 | 0.8165 | 0.5001 | 0.4898 | 0.5117 | | 0.3506 | 0.55 | 250 | 0.6884 | 0.7985 | 0.5037 | 0.6467 | 0.5073 | | 0.3233 | 0.66 | 300 | 0.5294 | 0.8553 | 0.5177 | 0.5012 | 0.5353 | | 0.3211 | 0.76 | 350 | 0.5028 | 0.8553 | 0.5989 | 0.5974 | 0.6058 | | 0.2611 | 0.87 | 400 | 0.7703 | 0.8387 | 0.6148 | 0.5917 | 0.6521 | | 0.3259 | 0.98 | 450 | 0.6041 | 0.8335 | 0.6121 | 0.5925 | 0.6442 | | 0.2196 | 1.09 | 500 | 0.5109 | 0.8737 | 0.6300 | 0.6026 | 0.6665 | | 0.1712 | 1.2 | 550 | 0.6030 | 0.8488 | 0.6231 | 0.7507 | 0.6528 | | 0.175 | 1.31 | 600 | 0.5176 | 0.8783 | 0.6549 | 0.7620 | 0.6752 | | 0.257 | 1.42 | 650 | 0.3901 | 0.8873 | 0.6462 | 0.7626 | 0.6783 | | 0.1759 | 1.53 | 700 | 0.4053 | 0.8955 | 0.6774 | 0.7709 | 0.6947 | | 0.1309 | 1.64 | 750 | 0.3624 | 0.9251 | 0.7857 | 0.7883 | 0.7927 | | 0.2394 | 1.75 | 800 | 0.3332 | 0.9171 | 0.7749 | 0.7751 | 0.7848 | | 0.165 | 1.86 | 850 | 0.6878 | 0.8510 | 0.6446 | 0.6970 | 0.6394 | | 0.1421 | 1.97 | 900 | 0.3987 | 0.8718 | 0.6345 | 0.7590 | 0.6170 | | 0.1361 | 2.07 | 950 | 0.3393 | 0.9253 | 0.7738 | 0.7734 | 0.7872 | | 0.1292 | 2.18 | 1000 | 0.3194 | 0.9300 | 0.8017 | 0.8128 | 0.7930 | | 0.0754 | 2.29 | 1050 | 0.3485 | 0.9245 | 0.7871 | 0.7842 | 0.8006 | | 0.1345 | 2.4 | 1100 | 0.2564 | 0.9387 | 0.8022 | 0.7974 | 0.8104 | | 0.0593 | 2.51 | 1150 | 0.2132 | 0.9541 | 0.8159 | 0.8222 | 0.8109 | | 0.1019 | 2.62 | 1200 | 0.2234 | 0.9472 | 0.8070 | 0.8044 | 0.8127 | | 0.0735 | 2.73 | 1250 | 0.2183 | 0.9535 | 0.8155 | 0.8250 | 0.8072 | | 0.113 | 2.84 | 1300 | 0.2716 | 0.9128 | 0.7208 | 0.8006 | 0.7118 | | 0.0838 | 2.95 | 1350 | 0.2957 | 0.9330 | 0.7999 | 0.7929 | 0.8128 | | 0.0797 | 3.06 | 1400 | 0.2758 | 0.9437 | 0.8075 | 0.8117 | 0.8058 | | 0.0612 | 3.17 | 1450 | 0.2450 | 0.9139 | 0.7200 | 0.7983 | 0.7140 | | 0.0492 | 3.28 | 1500 | 0.2501 | 0.9480 | 0.8089 | 0.8089 | 0.8118 | | 0.0294 | 3.38 | 1550 | 0.2745 | 0.9374 | 0.8035 | 0.8011 | 0.8084 | | 0.0248 | 3.49 | 1600 | 0.2561 | 0.9434 | 0.8099 | 0.8073 | 0.8144 | | 0.0621 | 3.6 | 1650 | 0.2312 | 0.9491 | 0.8135 | 0.8190 | 0.8094 | | 0.0541 | 3.71 | 1700 | 0.2512 | 0.9472 | 0.8140 | 0.8177 | 0.8119 | | 0.0509 | 3.82 | 1750 | 0.2195 | 0.9516 | 0.8145 | 0.8173 | 0.8125 | | 0.0452 | 3.93 | 1800 | 0.2418 | 0.9480 | 0.8140 | 0.8175 | 0.8120 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2