|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: office-character |
|
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. --> |
|
|
|
# office-character |
|
|
|
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: 2.5873 |
|
- Accuracy: 0.1544 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2.5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.6964 | 0.16 | 60 | 2.6756 | 0.0834 | |
|
| 2.6947 | 0.31 | 120 | 2.6670 | 0.0947 | |
|
| 2.6716 | 0.47 | 180 | 2.6428 | 0.1139 | |
|
| 2.6315 | 0.63 | 240 | 2.6252 | 0.1268 | |
|
| 2.6113 | 0.79 | 300 | 2.6205 | 0.1310 | |
|
| 2.5936 | 0.94 | 360 | 2.6137 | 0.1293 | |
|
| 2.5298 | 1.1 | 420 | 2.6065 | 0.1381 | |
|
| 2.4691 | 1.26 | 480 | 2.6097 | 0.1452 | |
|
| 2.4645 | 1.42 | 540 | 2.6015 | 0.1519 | |
|
| 2.4404 | 1.57 | 600 | 2.5912 | 0.1414 | |
|
| 2.4435 | 1.73 | 660 | 2.5890 | 0.1464 | |
|
| 2.4425 | 1.89 | 720 | 2.5928 | 0.1514 | |
|
| 2.4038 | 2.05 | 780 | 2.5880 | 0.1481 | |
|
| 2.2601 | 2.2 | 840 | 2.5941 | 0.1423 | |
|
| 2.2858 | 2.36 | 900 | 2.5873 | 0.1544 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|