|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Sentiment_Analysis_in_Social_Media_SonatafyAI_BERT_v1 |
|
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. --> |
|
|
|
# Sentiment_Analysis_in_Social_Media_SonatafyAI_BERT_v1 |
|
|
|
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: 1.0893 |
|
- Accuracy: 0.8495 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5082 | 1.0 | 687 | 0.4134 | 0.8481 | |
|
| 0.3337 | 2.0 | 1374 | 0.4205 | 0.8499 | |
|
| 0.1865 | 3.0 | 2061 | 0.5330 | 0.8477 | |
|
| 0.1099 | 4.0 | 2748 | 0.8024 | 0.8299 | |
|
| 0.1007 | 5.0 | 3435 | 0.7997 | 0.8455 | |
|
| 0.0393 | 6.0 | 4122 | 0.8675 | 0.8419 | |
|
| 0.0368 | 7.0 | 4809 | 0.9558 | 0.8455 | |
|
| 0.0308 | 8.0 | 5496 | 1.0125 | 0.8401 | |
|
| 0.0157 | 9.0 | 6183 | 1.0818 | 0.8423 | |
|
| 0.0156 | 10.0 | 6870 | 1.0893 | 0.8495 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
