|
|
--- |
|
|
license: mit |
|
|
base_model: microsoft/mdeberta-v3-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- f1 |
|
|
model-index: |
|
|
- name: Model |
|
|
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. --> |
|
|
|
|
|
# Model |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.5484 |
|
|
- F1: 0.7866 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 8 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
|
| 0.8731 | 1.0 | 1469 | 0.9043 | 0.6580 | |
|
|
| 0.5627 | 2.0 | 2938 | 0.7961 | 0.7249 | |
|
|
| 0.3709 | 3.0 | 4407 | 0.7498 | 0.7616 | |
|
|
| 0.2306 | 4.0 | 5876 | 1.0133 | 0.7449 | |
|
|
| 0.1605 | 5.0 | 7345 | 0.9206 | 0.7930 | |
|
|
| 0.0903 | 6.0 | 8814 | 1.1841 | 0.7797 | |
|
|
| 0.0506 | 7.0 | 10283 | 1.4182 | 0.7864 | |
|
|
| 0.027 | 8.0 | 11752 | 1.5484 | 0.7866 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.2 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.19.2 |
|
|
- Tokenizers 0.19.1 |
|
|
|
