|
--- |
|
license: mit |
|
base_model: microsoft/mdeberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mdeberta-v3-base-on-custom-kural-500 |
|
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. --> |
|
|
|
# mdeberta-v3-base-on-custom-kural-500 |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4313 |
|
- Accuracy: 0.8133 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 22 | 0.5663 | 0.74 | |
|
| No log | 2.0 | 44 | 0.5780 | 0.74 | |
|
| No log | 3.0 | 66 | 0.5738 | 0.74 | |
|
| No log | 4.0 | 88 | 0.5953 | 0.74 | |
|
| No log | 5.0 | 110 | 0.5955 | 0.74 | |
|
| No log | 6.0 | 132 | 0.5311 | 0.74 | |
|
| No log | 7.0 | 154 | 0.5937 | 0.74 | |
|
| No log | 8.0 | 176 | 0.4819 | 0.84 | |
|
| No log | 9.0 | 198 | 0.4305 | 0.8333 | |
|
| No log | 10.0 | 220 | 0.4313 | 0.8133 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
