|
|
--- |
|
|
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_plus |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# bert-seq-class-values-no-context_plus |
|
|
|
|
|
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: 0.3789 |
|
|
- Subset Accuracy: 0.2907 |
|
|
- F1 Macro: 0.3225 |
|
|
- F1 Micro: 0.3837 |
|
|
- Precision Macro: 0.3470 |
|
|
- Recall Macro: 0.3052 |
|
|
- Roc Auc: 0.7784 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 2025 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- 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: 25 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------:| |
|
|
| 0.3261 | 1.0 | 767 | 0.1848 | 0.0358 | 0.0273 | 0.0682 | 0.1322 | 0.0165 | 0.7523 | |
|
|
| 0.1653 | 2.0 | 1534 | 0.1687 | 0.2000 | 0.1740 | 0.3048 | 0.3058 | 0.1429 | 0.8180 | |
|
|
| 0.1422 | 3.0 | 2301 | 0.1700 | 0.2427 | 0.2509 | 0.3398 | 0.4408 | 0.1957 | 0.8239 | |
|
|
| 0.1091 | 4.0 | 3068 | 0.1864 | 0.3055 | 0.2801 | 0.3921 | 0.4249 | 0.2469 | 0.8166 | |
|
|
| 0.0806 | 5.0 | 3835 | 0.2045 | 0.3021 | 0.2926 | 0.3841 | 0.3993 | 0.2540 | 0.8079 | |
|
|
| 0.0542 | 6.0 | 4602 | 0.2328 | 0.2992 | 0.2961 | 0.3785 | 0.3630 | 0.2644 | 0.7991 | |
|
|
| 0.0434 | 7.0 | 5369 | 0.2475 | 0.2842 | 0.3076 | 0.3845 | 0.3510 | 0.2955 | 0.7982 | |
|
|
| 0.0311 | 8.0 | 6136 | 0.2661 | 0.2919 | 0.3236 | 0.3904 | 0.3442 | 0.3168 | 0.7920 | |
|
|
| 0.025 | 9.0 | 6903 | 0.2812 | 0.2844 | 0.3201 | 0.3858 | 0.3441 | 0.3085 | 0.7878 | |
|
|
| 0.0186 | 10.0 | 7670 | 0.3123 | 0.2826 | 0.3246 | 0.3879 | 0.3432 | 0.3220 | 0.7827 | |
|
|
| 0.0152 | 11.0 | 8437 | 0.3156 | 0.2689 | 0.3217 | 0.3774 | 0.3374 | 0.3157 | 0.7828 | |
|
|
| 0.0109 | 12.0 | 9204 | 0.3380 | 0.2856 | 0.3127 | 0.3800 | 0.3410 | 0.2994 | 0.7785 | |
|
|
| 0.0095 | 13.0 | 9971 | 0.3636 | 0.2684 | 0.3187 | 0.3783 | 0.3385 | 0.3140 | 0.7699 | |
|
|
| 0.0063 | 14.0 | 10738 | 0.3684 | 0.2835 | 0.3206 | 0.3807 | 0.3478 | 0.3049 | 0.7755 | |
|
|
| 0.0054 | 15.0 | 11505 | 0.3789 | 0.2907 | 0.3225 | 0.3837 | 0.3470 | 0.3052 | 0.7784 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.2 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 2.14.4 |
|
|
- Tokenizers 0.21.2 |
|
|
|
