|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_distilbert-base-uncased-15-epoch |
|
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. --> |
|
|
|
# distilbert_distilbert-base-uncased-15-epoch |
|
|
|
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.3248 |
|
- Accuracy: 0.4133 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 1.3078 | 1.0 | 2857 | 1.3426 | 0.3356 | |
|
| 1.1327 | 2.0 | 5714 | 1.4079 | 0.3560 | |
|
| 0.911 | 3.0 | 8571 | 1.5413 | 0.3789 | |
|
| 0.7139 | 4.0 | 11428 | 1.7088 | 0.3942 | |
|
| 0.548 | 5.0 | 14285 | 1.9117 | 0.3902 | |
|
| 0.4389 | 6.0 | 17142 | 2.1179 | 0.3971 | |
|
| 0.3422 | 7.0 | 19999 | 2.5687 | 0.4002 | |
|
| 0.2707 | 8.0 | 22856 | 2.6006 | 0.4019 | |
|
| 0.2258 | 9.0 | 25713 | 2.8582 | 0.4069 | |
|
| 0.1817 | 10.0 | 28570 | 3.2135 | 0.4031 | |
|
| 0.1506 | 11.0 | 31427 | 3.2640 | 0.4074 | |
|
| 0.1285 | 12.0 | 34284 | 3.6061 | 0.4086 | |
|
| 0.1067 | 13.0 | 37141 | 3.7931 | 0.4141 | |
|
| 0.088 | 14.0 | 39998 | 4.1130 | 0.4129 | |
|
| 0.0772 | 15.0 | 42855 | 4.3248 | 0.4133 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.0 |
|
|
