|
--- |
|
license: mit |
|
base_model: mhr2004/plm-nsp-10000 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: base-nsp-10000 |
|
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. --> |
|
|
|
# base-nsp-10000 |
|
|
|
This model is a fine-tuned version of [mhr2004/plm-nsp-10000](https://huggingface.co/mhr2004/plm-nsp-10000) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8886 |
|
- Accuracy: 0.4717 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.9837 | 1.0 | 183 | 0.8747 | 0.4703 | |
|
| 0.9294 | 2.0 | 366 | 0.8611 | 0.4577 | |
|
| 0.8769 | 3.0 | 549 | 0.8751 | 0.4730 | |
|
| 0.8351 | 4.0 | 732 | 0.8768 | 0.5054 | |
|
| 0.8143 | 5.0 | 915 | 0.8789 | 0.4973 | |
|
| 0.7892 | 6.0 | 1098 | 0.8924 | 0.4802 | |
|
| 0.7748 | 7.0 | 1281 | 0.8990 | 0.5045 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
