|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: sentiment_analysis_model |
|
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_model |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7543 |
|
- Accuracy: 0.8483 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | 150 | 0.4045 | 0.8317 | |
|
| No log | 2.0 | 300 | 0.4403 | 0.83 | |
|
| No log | 3.0 | 450 | 0.5234 | 0.8325 | |
|
| 0.3116 | 4.0 | 600 | 0.5604 | 0.8367 | |
|
| 0.3116 | 5.0 | 750 | 0.6089 | 0.8425 | |
|
| 0.3116 | 6.0 | 900 | 0.6792 | 0.85 | |
|
| 0.0814 | 7.0 | 1050 | 0.7147 | 0.8508 | |
|
| 0.0814 | 8.0 | 1200 | 0.7421 | 0.8517 | |
|
| 0.0814 | 9.0 | 1350 | 0.7794 | 0.845 | |
|
| 0.0302 | 10.0 | 1500 | 0.7543 | 0.8483 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.13.3 |
|
|
