|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: bert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: bert-mrpc-analysis |
|
|
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-mrpc-analysis |
|
|
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6197 |
|
|
- Accuracy: 0.8554 |
|
|
- F1: 0.8985 |
|
|
|
|
|
## 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: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:| |
|
|
| 0.6445 | 0.2174 | 50 | 0.5860 | 0.7010 | 0.8201 | |
|
|
| 0.5425 | 0.4348 | 100 | 0.5083 | 0.7647 | 0.8509 | |
|
|
| 0.4903 | 0.6522 | 150 | 0.4756 | 0.7868 | 0.8621 | |
|
|
| 0.459 | 0.8696 | 200 | 0.4043 | 0.8309 | 0.8832 | |
|
|
| 0.3848 | 1.0870 | 250 | 0.3972 | 0.8505 | 0.8968 | |
|
|
| 0.2851 | 1.3043 | 300 | 0.4763 | 0.8235 | 0.8808 | |
|
|
| 0.2758 | 1.5217 | 350 | 0.3576 | 0.8701 | 0.9065 | |
|
|
| 0.2241 | 1.7391 | 400 | 0.4367 | 0.8456 | 0.8919 | |
|
|
| 0.2699 | 1.9565 | 450 | 0.3583 | 0.8554 | 0.8948 | |
|
|
| 0.1345 | 2.1739 | 500 | 0.4947 | 0.8578 | 0.9 | |
|
|
| 0.092 | 2.3913 | 550 | 0.5921 | 0.8505 | 0.8968 | |
|
|
| 0.0825 | 2.6087 | 600 | 0.6000 | 0.8554 | 0.8985 | |
|
|
| 0.1194 | 2.8261 | 650 | 0.6197 | 0.8554 | 0.8985 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.1 |
|
|
- Pytorch 2.8.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.1 |
|
|
|
