--- library_name: transformers license: apache-2.0 base_model: google-bert/bert-base-uncased tags: - generated_from_trainer model-index: - name: bert-seq-class-values-no-context results: [] --- # bert-seq-class-values-no-context This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3514 - Subset Accuracy: 0.2902 - F1 Macro: 0.3370 - F1 Micro: 0.3898 - Precision Macro: 0.3762 - Recall Macro: 0.3140 - Roc Auc: 0.7933 ## 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: 4 - eval_batch_size: 4 - seed: 2025 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Subset Accuracy | F1 Macro | F1 Micro | Precision Macro | Recall Macro | Roc Auc | |:-------------:|:-------:|:-----:|:---------------:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------:| | 0.4274 | 0.5002 | 767 | 0.2090 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6092 | | 0.1875 | 1.0 | 1534 | 0.1773 | 0.0816 | 0.0680 | 0.1479 | 0.2599 | 0.0476 | 0.7795 | | 0.1682 | 1.5002 | 2301 | 0.1681 | 0.1630 | 0.1275 | 0.2611 | 0.2788 | 0.1014 | 0.8039 | | 0.161 | 2.0 | 3068 | 0.1631 | 0.2076 | 0.1940 | 0.3133 | 0.4626 | 0.1538 | 0.8256 | | 0.1379 | 2.5002 | 3835 | 0.1674 | 0.2572 | 0.2415 | 0.3613 | 0.4434 | 0.1922 | 0.8235 | | 0.1323 | 3.0 | 4602 | 0.1634 | 0.2604 | 0.2566 | 0.3641 | 0.4828 | 0.1999 | 0.8349 | | 0.1032 | 3.5002 | 5369 | 0.1855 | 0.2953 | 0.2878 | 0.3803 | 0.3958 | 0.2422 | 0.8211 | | 0.0961 | 4.0 | 6136 | 0.1858 | 0.3151 | 0.3092 | 0.4045 | 0.4284 | 0.2670 | 0.8231 | | 0.0737 | 4.5002 | 6903 | 0.2082 | 0.3121 | 0.3140 | 0.3941 | 0.3975 | 0.2748 | 0.8120 | | 0.0651 | 5.0 | 7670 | 0.2108 | 0.3082 | 0.2990 | 0.3935 | 0.4146 | 0.2605 | 0.8106 | | 0.0541 | 5.5002 | 8437 | 0.2241 | 0.2995 | 0.3174 | 0.3851 | 0.3851 | 0.2861 | 0.8055 | | 0.0465 | 6.0 | 9204 | 0.2386 | 0.3039 | 0.3123 | 0.3871 | 0.3757 | 0.2779 | 0.8026 | | 0.0399 | 6.5002 | 9971 | 0.2458 | 0.3020 | 0.3240 | 0.3894 | 0.3745 | 0.2979 | 0.8032 | | 0.0345 | 7.0 | 10738 | 0.2539 | 0.3078 | 0.3288 | 0.4012 | 0.3615 | 0.3105 | 0.8039 | | 0.0251 | 7.5002 | 11505 | 0.2663 | 0.2951 | 0.3301 | 0.3912 | 0.3619 | 0.3140 | 0.7993 | | 0.0254 | 8.0 | 12272 | 0.2737 | 0.2944 | 0.3322 | 0.3920 | 0.3709 | 0.3109 | 0.7998 | | 0.0189 | 8.5002 | 13039 | 0.2791 | 0.2844 | 0.3388 | 0.3984 | 0.3574 | 0.3310 | 0.8029 | | 0.0195 | 9.0 | 13806 | 0.2838 | 0.2913 | 0.3273 | 0.3896 | 0.3615 | 0.3064 | 0.7989 | | 0.014 | 9.5002 | 14573 | 0.3037 | 0.2925 | 0.3336 | 0.3987 | 0.3680 | 0.3201 | 0.7971 | | 0.0139 | 10.0 | 15340 | 0.3015 | 0.2903 | 0.3401 | 0.3979 | 0.3648 | 0.3239 | 0.7950 | | 0.0101 | 10.5002 | 16107 | 0.3192 | 0.2846 | 0.3428 | 0.4032 | 0.3598 | 0.3409 | 0.7934 | | 0.0103 | 11.0 | 16874 | 0.3257 | 0.2866 | 0.3376 | 0.3989 | 0.3566 | 0.3274 | 0.7928 | | 0.0073 | 11.5002 | 17641 | 0.3275 | 0.3004 | 0.3334 | 0.4008 | 0.3828 | 0.3077 | 0.7941 | | 0.0074 | 12.0 | 18408 | 0.3378 | 0.2868 | 0.3361 | 0.3999 | 0.3646 | 0.3217 | 0.7911 | | 0.0056 | 12.5002 | 19175 | 0.3424 | 0.3010 | 0.3419 | 0.4036 | 0.3733 | 0.3215 | 0.7926 | | 0.0052 | 13.0 | 19942 | 0.3514 | 0.2902 | 0.3370 | 0.3898 | 0.3762 | 0.3140 | 0.7933 | ### Framework versions - Transformers 4.53.2 - Pytorch 2.6.0+cu124 - Datasets 2.14.4 - Tokenizers 0.21.2