|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert-base-uncased-cosmos-mcqa |
|
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. --> |
|
|
|
# bert-base-uncased-cosmos-mcqa |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0302 |
|
- Accuracy: 0.5940 |
|
|
|
## 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: 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.9652 | 1.0 | 1579 | 0.9947 | 0.5926 | |
|
| 0.6377 | 2.0 | 3158 | 1.0135 | 0.6178 | |
|
| 0.3396 | 3.0 | 4737 | 1.3263 | 0.6010 | |
|
| 0.1965 | 4.0 | 6316 | 1.8585 | 0.5916 | |
|
| 0.1211 | 5.0 | 7895 | 2.0302 | 0.5940 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.6.dev0 |
|
- Tokenizers 0.13.3 |
|
|
