|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: BERT_finetune_sentiment |
|
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. --> |
|
|
|
# BERT_finetune_sentiment |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8911 |
|
|
|
## 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: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.3369 | 1.0 | 625 | 0.2635 | |
|
| 0.1885 | 2.0 | 1250 | 0.4271 | |
|
| 0.1329 | 3.0 | 1875 | 0.5429 | |
|
| 0.0545 | 4.0 | 2500 | 0.5134 | |
|
| 0.0313 | 5.0 | 3125 | 0.6778 | |
|
| 0.0275 | 6.0 | 3750 | 0.7123 | |
|
| 0.0276 | 7.0 | 4375 | 0.6549 | |
|
| 0.021 | 8.0 | 5000 | 0.6959 | |
|
| 0.0153 | 9.0 | 5625 | 0.7736 | |
|
| 0.0083 | 10.0 | 6250 | 0.7828 | |
|
| 0.0111 | 11.0 | 6875 | 0.8629 | |
|
| 0.0046 | 12.0 | 7500 | 0.8794 | |
|
| 0.0091 | 13.0 | 8125 | 0.7696 | |
|
| 0.0064 | 14.0 | 8750 | 0.8840 | |
|
| 0.0035 | 15.0 | 9375 | 0.9002 | |
|
| 0.0014 | 16.0 | 10000 | 0.9629 | |
|
| 0.0049 | 17.0 | 10625 | 1.0240 | |
|
| 0.0051 | 18.0 | 11250 | 0.9016 | |
|
| 0.0021 | 19.0 | 11875 | 0.9011 | |
|
| 0.0012 | 20.0 | 12500 | 0.8911 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
