|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: mrm8488/electra-small-finetuned-squadv2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: electra_combined_top |
|
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. --> |
|
|
|
# electra_combined_top |
|
|
|
This model is a fine-tuned version of [mrm8488/electra-small-finetuned-squadv2](https://huggingface.co/mrm8488/electra-small-finetuned-squadv2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4985 |
|
- Accuracy: 0.7115 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- 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: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.0557 | 1.0 | 624 | 1.0444 | 0.5032 | |
|
| 1.0119 | 2.0 | 1248 | 0.9122 | 0.6154 | |
|
| 0.827 | 3.0 | 1872 | 1.0536 | 0.6410 | |
|
| 0.7281 | 4.0 | 2496 | 1.1990 | 0.6667 | |
|
| 0.5995 | 5.0 | 3120 | 1.0404 | 0.6795 | |
|
| 0.5339 | 6.0 | 3744 | 1.3688 | 0.6955 | |
|
| 0.4599 | 7.0 | 4368 | 1.4182 | 0.7083 | |
|
| 0.388 | 8.0 | 4992 | 1.4727 | 0.7147 | |
|
| 0.3418 | 9.0 | 5616 | 1.5407 | 0.7051 | |
|
| 0.2794 | 10.0 | 6240 | 1.4985 | 0.7115 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
