|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: answerdotai/ModernBERT-large |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: modernbert-large-docx |
|
|
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. --> |
|
|
|
|
|
# modernbert-large-docx |
|
|
|
|
|
This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5145 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 148 |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.5541 | 0.1686 | 100 | 0.5688 | |
|
|
| 0.5465 | 0.3373 | 200 | 0.5476 | |
|
|
| 0.5054 | 0.5059 | 300 | 0.5369 | |
|
|
| 0.5113 | 0.6745 | 400 | 0.5335 | |
|
|
| 0.5281 | 0.8432 | 500 | 0.5354 | |
|
|
| 0.5441 | 1.0118 | 600 | 0.5312 | |
|
|
| 0.4983 | 1.1804 | 700 | 0.5269 | |
|
|
| 0.5151 | 1.3491 | 800 | 0.5257 | |
|
|
| 0.5247 | 1.5177 | 900 | 0.5258 | |
|
|
| 0.5212 | 1.6863 | 1000 | 0.5343 | |
|
|
| 0.5243 | 1.8550 | 1100 | 0.5190 | |
|
|
| 0.5007 | 2.0236 | 1200 | 0.5206 | |
|
|
| 0.4971 | 2.1922 | 1300 | 0.5260 | |
|
|
| 0.504 | 2.3609 | 1400 | 0.5264 | |
|
|
| 0.5152 | 2.5295 | 1500 | 0.5229 | |
|
|
| 0.5269 | 2.6981 | 1600 | 0.5264 | |
|
|
| 0.5202 | 2.8668 | 1700 | 0.5282 | |
|
|
| 0.5117 | 3.0354 | 1800 | 0.5179 | |
|
|
| 0.5163 | 3.2040 | 1900 | 0.5168 | |
|
|
| 0.4929 | 3.3727 | 2000 | 0.5165 | |
|
|
| 0.5017 | 3.5413 | 2100 | 0.5151 | |
|
|
| 0.5031 | 3.7099 | 2200 | 0.5155 | |
|
|
| 0.52 | 3.8786 | 2300 | 0.5155 | |
|
|
| 0.5055 | 4.0472 | 2400 | 0.5143 | |
|
|
| 0.4968 | 4.2159 | 2500 | 0.5138 | |
|
|
| 0.4868 | 4.3845 | 2600 | 0.5147 | |
|
|
| 0.4888 | 4.5531 | 2700 | 0.5145 | |
|
|
| 0.4994 | 4.7218 | 2800 | 0.5145 | |
|
|
| 0.4911 | 4.8904 | 2900 | 0.5145 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.0.dev0 |
|
|
- Pytorch 2.4.1+cu121 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
