|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: answerdotai/ModernBERT-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: Assignment4_Distilled_ModernBERT |
|
|
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. --> |
|
|
|
|
|
# Assignment4_Distilled_ModernBERT |
|
|
|
|
|
This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2589 |
|
|
- Accuracy: 0.9681 |
|
|
|
|
|
## 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: 6e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 8 |
|
|
- 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: cosine |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
|
| 7.8963 | 0.2096 | 100 | 2.9564 | 0.7577 | |
|
|
| 1.6375 | 0.4193 | 200 | 1.0919 | 0.8806 | |
|
|
| 0.8239 | 0.6289 | 300 | 0.6403 | 0.9335 | |
|
|
| 0.5738 | 0.8386 | 400 | 0.5019 | 0.9448 | |
|
|
| 0.3915 | 1.0482 | 500 | 0.4918 | 0.9452 | |
|
|
| 0.1938 | 1.2579 | 600 | 0.4370 | 0.9548 | |
|
|
| 0.2045 | 1.4675 | 700 | 0.4937 | 0.9435 | |
|
|
| 0.1874 | 1.6771 | 800 | 0.4477 | 0.9568 | |
|
|
| 0.1804 | 1.8868 | 900 | 0.4118 | 0.9581 | |
|
|
| 0.1237 | 2.0964 | 1000 | 0.3573 | 0.9616 | |
|
|
| 0.076 | 2.3061 | 1100 | 0.3772 | 0.9574 | |
|
|
| 0.0834 | 2.5157 | 1200 | 0.3337 | 0.9652 | |
|
|
| 0.0713 | 2.7254 | 1300 | 0.3032 | 0.9658 | |
|
|
| 0.0514 | 2.9350 | 1400 | 0.3009 | 0.9661 | |
|
|
| 0.0448 | 3.1447 | 1500 | 0.2892 | 0.9661 | |
|
|
| 0.0425 | 3.3543 | 1600 | 0.2864 | 0.9671 | |
|
|
| 0.0341 | 3.5639 | 1700 | 0.2859 | 0.9642 | |
|
|
| 0.0389 | 3.7736 | 1800 | 0.2763 | 0.9677 | |
|
|
| 0.0409 | 3.9832 | 1900 | 0.2682 | 0.9668 | |
|
|
| 0.0266 | 4.1929 | 2000 | 0.2624 | 0.9674 | |
|
|
| 0.0265 | 4.4025 | 2100 | 0.2610 | 0.9684 | |
|
|
| 0.0267 | 4.6122 | 2200 | 0.2592 | 0.9684 | |
|
|
| 0.027 | 4.8218 | 2300 | 0.2589 | 0.9681 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.0 |
|
|
- Pytorch 2.8.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.1 |
|
|
|
