|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased-finetuned-sst-2-english |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3782 |
|
- F1: 0.9100 |
|
- Accuracy: 0.9231 |
|
|
|
## 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 |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| 1.2718 | 0.11 | 100 | 0.5156 | 0.7112 | 0.7683 | |
|
| 0.4449 | 0.22 | 200 | 0.4094 | 0.7815 | 0.8252 | |
|
| 0.4407 | 0.32 | 300 | 0.3970 | 0.7928 | 0.8311 | |
|
| 0.4038 | 0.43 | 400 | 0.3991 | 0.8117 | 0.8379 | |
|
| 0.3772 | 0.54 | 500 | 0.3750 | 0.8191 | 0.8514 | |
|
| 0.3692 | 0.65 | 600 | 0.3737 | 0.8245 | 0.8547 | |
|
| 0.3738 | 0.76 | 700 | 0.3595 | 0.8194 | 0.8590 | |
|
| 0.3685 | 0.87 | 800 | 0.3409 | 0.8305 | 0.8631 | |
|
| 0.3286 | 0.97 | 900 | 0.3504 | 0.8372 | 0.8696 | |
|
| 0.3202 | 1.08 | 1000 | 0.3590 | 0.8344 | 0.8671 | |
|
| 0.2702 | 1.19 | 1100 | 0.3706 | 0.8473 | 0.8701 | |
|
| 0.2564 | 1.3 | 1200 | 0.3850 | 0.8449 | 0.8663 | |
|
| 0.2742 | 1.41 | 1300 | 0.3205 | 0.8558 | 0.8828 | |
|
| 0.2371 | 1.52 | 1400 | 0.3324 | 0.8646 | 0.8877 | |
|
| 0.2459 | 1.62 | 1500 | 0.3327 | 0.8602 | 0.8863 | |
|
| 0.2388 | 1.73 | 1600 | 0.3498 | 0.8679 | 0.8893 | |
|
| 0.2327 | 1.84 | 1700 | 0.3387 | 0.8735 | 0.8915 | |
|
| 0.244 | 1.95 | 1800 | 0.3381 | 0.8767 | 0.8953 | |
|
| 0.2096 | 2.06 | 1900 | 0.3312 | 0.8831 | 0.9034 | |
|
| 0.1719 | 2.16 | 2000 | 0.3358 | 0.8854 | 0.9039 | |
|
| 0.1507 | 2.27 | 2100 | 0.3580 | 0.8811 | 0.9020 | |
|
| 0.1704 | 2.38 | 2200 | 0.3440 | 0.8711 | 0.8861 | |
|
| 0.1526 | 2.49 | 2300 | 0.3728 | 0.8920 | 0.9093 | |
|
| 0.1913 | 2.6 | 2400 | 0.3450 | 0.8838 | 0.9034 | |
|
| 0.1313 | 2.71 | 2500 | 0.3746 | 0.8937 | 0.9104 | |
|
| 0.1719 | 2.81 | 2600 | 0.3204 | 0.8925 | 0.9093 | |
|
| 0.1719 | 2.92 | 2700 | 0.3073 | 0.8967 | 0.9145 | |
|
| 0.139 | 3.03 | 2800 | 0.3435 | 0.9035 | 0.9191 | |
|
| 0.1035 | 3.14 | 2900 | 0.3613 | 0.8959 | 0.9104 | |
|
| 0.1112 | 3.25 | 3000 | 0.3500 | 0.9038 | 0.9185 | |
|
| 0.1134 | 3.35 | 3100 | 0.3263 | 0.9065 | 0.9210 | |
|
| 0.1177 | 3.46 | 3200 | 0.3370 | 0.9050 | 0.9194 | |
|
| 0.1022 | 3.57 | 3300 | 0.3668 | 0.9038 | 0.9194 | |
|
| 0.1036 | 3.68 | 3400 | 0.3655 | 0.9034 | 0.9194 | |
|
| 0.1165 | 3.79 | 3500 | 0.3422 | 0.9069 | 0.9215 | |
|
| 0.1056 | 3.9 | 3600 | 0.3874 | 0.9082 | 0.9218 | |
|
| 0.1006 | 4.0 | 3700 | 0.3852 | 0.8943 | 0.9074 | |
|
| 0.0774 | 4.11 | 3800 | 0.3722 | 0.9086 | 0.9226 | |
|
| 0.0755 | 4.22 | 3900 | 0.3772 | 0.9087 | 0.9229 | |
|
| 0.0762 | 4.33 | 4000 | 0.3917 | 0.9059 | 0.9212 | |
|
| 0.0891 | 4.44 | 4100 | 0.3657 | 0.9078 | 0.9231 | |
|
| 0.0767 | 4.55 | 4200 | 0.3678 | 0.9101 | 0.9242 | |
|
| 0.0755 | 4.65 | 4300 | 0.3850 | 0.9095 | 0.9231 | |
|
| 0.0765 | 4.76 | 4400 | 0.3846 | 0.9084 | 0.9234 | |
|
| 0.1069 | 4.87 | 4500 | 0.3706 | 0.9109 | 0.9250 | |
|
| 0.0884 | 4.98 | 4600 | 0.3583 | 0.9067 | 0.9204 | |
|
| 0.0751 | 5.09 | 4700 | 0.3770 | 0.9087 | 0.9231 | |
|
| 0.0708 | 5.19 | 4800 | 0.3782 | 0.9100 | 0.9231 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
