|
--- |
|
license: apache-2.0 |
|
base_model: LiYuan/amazon-review-sentiment-analysis |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: FineTuned_NewAmazonReview |
|
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. --> |
|
|
|
# FineTuned_NewAmazonReview |
|
|
|
This model is a fine-tuned version of [LiYuan/amazon-review-sentiment-analysis](https://huggingface.co/LiYuan/amazon-review-sentiment-analysis) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9763 |
|
- Accuracy: 0.67 |
|
## 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: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.5281 | 0.1 | 500 | 1.4426 | |
|
| 1.3849 | 0.2 | 1000 | 1.3289 | |
|
| 1.2785 | 0.3 | 1500 | 1.2364 | |
|
| 1.2415 | 0.4 | 2000 | 1.2403 | |
|
| 1.2113 | 0.5 | 2500 | 1.1924 | |
|
| 1.1661 | 0.6 | 3000 | 1.2096 | |
|
| 1.1283 | 0.7 | 3500 | 1.1103 | |
|
| 1.1176 | 0.8 | 4000 | 1.0909 | |
|
| 1.1048 | 0.9 | 4500 | 1.0933 | |
|
| 1.0746 | 1.0 | 5000 | 1.0432 | |
|
| 0.9869 | 1.1 | 5500 | 1.1254 | |
|
| 0.9895 | 1.2 | 6000 | 1.0309 | |
|
| 0.987 | 1.3 | 6500 | 1.0326 | |
|
| 0.9618 | 1.4 | 7000 | 1.0184 | |
|
| 0.9626 | 1.5 | 7500 | 1.0095 | |
|
| 0.964 | 1.6 | 8000 | 1.0016 | |
|
| 0.9484 | 1.7 | 8500 | 0.9964 | |
|
| 0.9395 | 1.8 | 9000 | 0.9933 | |
|
| 0.9247 | 1.9 | 9500 | 0.9849 | |
|
| 0.9402 | 2.0 | 10000 | 0.9763 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|