|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: best_model-sst-2-16-13 |
|
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. --> |
|
|
|
# best_model-sst-2-16-13 |
|
|
|
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: 0.6710 |
|
- Accuracy: 0.7188 |
|
|
|
## 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 |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 1 | 0.6895 | 0.5312 | |
|
| No log | 2.0 | 2 | 0.6895 | 0.5312 | |
|
| No log | 3.0 | 3 | 0.6894 | 0.5312 | |
|
| No log | 4.0 | 4 | 0.6894 | 0.5312 | |
|
| No log | 5.0 | 5 | 0.6894 | 0.5312 | |
|
| No log | 6.0 | 6 | 0.6893 | 0.5312 | |
|
| No log | 7.0 | 7 | 0.6893 | 0.5312 | |
|
| No log | 8.0 | 8 | 0.6892 | 0.5312 | |
|
| No log | 9.0 | 9 | 0.6891 | 0.5312 | |
|
| 0.7006 | 10.0 | 10 | 0.6890 | 0.5312 | |
|
| 0.7006 | 11.0 | 11 | 0.6889 | 0.5312 | |
|
| 0.7006 | 12.0 | 12 | 0.6888 | 0.5312 | |
|
| 0.7006 | 13.0 | 13 | 0.6887 | 0.5312 | |
|
| 0.7006 | 14.0 | 14 | 0.6886 | 0.5312 | |
|
| 0.7006 | 15.0 | 15 | 0.6884 | 0.5312 | |
|
| 0.7006 | 16.0 | 16 | 0.6883 | 0.5312 | |
|
| 0.7006 | 17.0 | 17 | 0.6881 | 0.5312 | |
|
| 0.7006 | 18.0 | 18 | 0.6879 | 0.5312 | |
|
| 0.7006 | 19.0 | 19 | 0.6877 | 0.5312 | |
|
| 0.6992 | 20.0 | 20 | 0.6875 | 0.5312 | |
|
| 0.6992 | 21.0 | 21 | 0.6872 | 0.5312 | |
|
| 0.6992 | 22.0 | 22 | 0.6870 | 0.5312 | |
|
| 0.6992 | 23.0 | 23 | 0.6867 | 0.5 | |
|
| 0.6992 | 24.0 | 24 | 0.6864 | 0.5 | |
|
| 0.6992 | 25.0 | 25 | 0.6861 | 0.5 | |
|
| 0.6992 | 26.0 | 26 | 0.6857 | 0.5 | |
|
| 0.6992 | 27.0 | 27 | 0.6854 | 0.5 | |
|
| 0.6992 | 28.0 | 28 | 0.6850 | 0.5 | |
|
| 0.6992 | 29.0 | 29 | 0.6846 | 0.5 | |
|
| 0.68 | 30.0 | 30 | 0.6842 | 0.5 | |
|
| 0.68 | 31.0 | 31 | 0.6838 | 0.5 | |
|
| 0.68 | 32.0 | 32 | 0.6833 | 0.5 | |
|
| 0.68 | 33.0 | 33 | 0.6829 | 0.5 | |
|
| 0.68 | 34.0 | 34 | 0.6824 | 0.5 | |
|
| 0.68 | 35.0 | 35 | 0.6819 | 0.5 | |
|
| 0.68 | 36.0 | 36 | 0.6814 | 0.5312 | |
|
| 0.68 | 37.0 | 37 | 0.6808 | 0.5625 | |
|
| 0.68 | 38.0 | 38 | 0.6802 | 0.5625 | |
|
| 0.68 | 39.0 | 39 | 0.6796 | 0.5938 | |
|
| 0.6655 | 40.0 | 40 | 0.6789 | 0.5938 | |
|
| 0.6655 | 41.0 | 41 | 0.6783 | 0.5938 | |
|
| 0.6655 | 42.0 | 42 | 0.6776 | 0.5938 | |
|
| 0.6655 | 43.0 | 43 | 0.6769 | 0.6562 | |
|
| 0.6655 | 44.0 | 44 | 0.6762 | 0.7188 | |
|
| 0.6655 | 45.0 | 45 | 0.6754 | 0.7188 | |
|
| 0.6655 | 46.0 | 46 | 0.6746 | 0.7188 | |
|
| 0.6655 | 47.0 | 47 | 0.6737 | 0.75 | |
|
| 0.6655 | 48.0 | 48 | 0.6728 | 0.75 | |
|
| 0.6655 | 49.0 | 49 | 0.6719 | 0.75 | |
|
| 0.6452 | 50.0 | 50 | 0.6710 | 0.7188 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.13.3 |
|
|
