|
---
|
|
license: mit
|
|
base_model: roberta-base
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
model-index:
|
|
- name: cs605-nlp-assignment-2-roberta-base
|
|
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-roberta-base
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 1.1088
|
|
- Accuracy: 0.7023
|
|
|
|
## 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: 3.2723062543456794e-05
|
|
- train_batch_size: 64
|
|
- 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 | 187 | 0.5811 | 0.6614 |
|
|
| No log | 2.0 | 374 | 0.5568 | 0.6889 |
|
|
| 0.5401 | 3.0 | 561 | 0.5805 | 0.6933 |
|
|
| 0.5401 | 4.0 | 748 | 0.6222 | 0.6996 |
|
|
| 0.5401 | 5.0 | 935 | 0.7495 | 0.7026 |
|
|
| 0.3002 | 6.0 | 1122 | 0.8180 | 0.7047 |
|
|
| 0.3002 | 7.0 | 1309 | 0.9720 | 0.6976 |
|
|
| 0.3002 | 8.0 | 1496 | 0.9912 | 0.6986 |
|
|
| 0.1454 | 9.0 | 1683 | 1.0774 | 0.6983 |
|
|
| 0.1454 | 10.0 | 1870 | 1.1088 | 0.7023 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.41.2
|
|
- Pytorch 2.1.0+cu121
|
|
- Datasets 2.19.1
|
|
- Tokenizers 0.19.1
|
|
|
