|
--- |
|
license: apache-2.0 |
|
base_model: bert-large-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: cs605-nlp-assignment-2-bert-large-uncased-v2 |
|
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. --> |
|
|
|
# cs605-nlp-assignment-2-bert-large-uncased-v2 |
|
|
|
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4797 |
|
- Accuracy: 0.7861 |
|
|
|
## 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: 1.3166642758879955e-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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5698 | 1.0 | 746 | 0.4877 | 0.7533 | |
|
| 0.4247 | 2.0 | 1492 | 0.5234 | 0.7777 | |
|
| 0.1575 | 3.0 | 2238 | 0.6654 | 0.7741 | |
|
| 0.1178 | 4.0 | 2984 | 1.0942 | 0.7764 | |
|
| 0.044 | 5.0 | 3730 | 1.2965 | 0.7824 | |
|
| 0.0345 | 6.0 | 4476 | 1.1750 | 0.7861 | |
|
| 0.0164 | 7.0 | 5222 | 1.4659 | 0.7828 | |
|
| 0.0136 | 8.0 | 5968 | 1.4372 | 0.7848 | |
|
| 0.0059 | 9.0 | 6714 | 1.5201 | 0.7871 | |
|
| 0.0081 | 10.0 | 7460 | 1.4797 | 0.7861 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
