|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: distilbert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: distilbert-text-classifier |
|
|
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-text-classifier |
|
|
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2758 |
|
|
- Accuracy: 0.9174 |
|
|
|
|
|
## 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: 64 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 40 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 0.3169 | 1.0 | 632 | 0.2758 | 0.9174 | |
|
|
| 0.1195 | 2.0 | 1264 | 0.2899 | 0.9218 | |
|
|
| 0.092 | 3.0 | 1896 | 0.3103 | 0.9274 | |
|
|
| 0.0951 | 4.0 | 2528 | 0.3161 | 0.9335 | |
|
|
| 0.0435 | 5.0 | 3160 | 0.3640 | 0.9336 | |
|
|
| 0.0294 | 6.0 | 3792 | 0.4195 | 0.9310 | |
|
|
| 0.0444 | 7.0 | 4424 | 0.4745 | 0.9286 | |
|
|
| 0.001 | 8.0 | 5056 | 0.4672 | 0.9355 | |
|
|
| 0.0577 | 9.0 | 5688 | 0.5112 | 0.9282 | |
|
|
| 0.0003 | 10.0 | 6320 | 0.4807 | 0.9362 | |
|
|
| 0.0135 | 11.0 | 6952 | 0.5246 | 0.9319 | |
|
|
| 0.0026 | 12.0 | 7584 | 0.5371 | 0.9345 | |
|
|
| 0.0012 | 13.0 | 8216 | 0.5445 | 0.9351 | |
|
|
| 0.0023 | 14.0 | 8848 | 0.5788 | 0.9335 | |
|
|
| 0.0006 | 15.0 | 9480 | 0.5707 | 0.9335 | |
|
|
| 0.0018 | 16.0 | 10112 | 0.5424 | 0.9375 | |
|
|
| 0.0034 | 17.0 | 10744 | 0.5418 | 0.9345 | |
|
|
| 0.0004 | 18.0 | 11376 | 0.5673 | 0.9389 | |
|
|
| 0.0001 | 19.0 | 12008 | 0.5738 | 0.9349 | |
|
|
| 0.01 | 20.0 | 12640 | 0.5651 | 0.9389 | |
|
|
| 0.0011 | 21.0 | 13272 | 0.6153 | 0.9339 | |
|
|
| 0.0224 | 22.0 | 13904 | 0.6216 | 0.9356 | |
|
|
| 0.0001 | 23.0 | 14536 | 0.5976 | 0.9353 | |
|
|
| 0.0417 | 24.0 | 15168 | 0.6134 | 0.9329 | |
|
|
| 0.0 | 25.0 | 15800 | 0.5920 | 0.9377 | |
|
|
| 0.0 | 26.0 | 16432 | 0.6247 | 0.9377 | |
|
|
| 0.0 | 27.0 | 17064 | 0.6435 | 0.9372 | |
|
|
| 0.0 | 28.0 | 17696 | 0.7084 | 0.9320 | |
|
|
| 0.0 | 29.0 | 18328 | 0.7095 | 0.9343 | |
|
|
| 0.0 | 30.0 | 18960 | 0.6708 | 0.9362 | |
|
|
| 0.0 | 31.0 | 19592 | 0.6704 | 0.9384 | |
|
|
| 0.0 | 32.0 | 20224 | 0.6665 | 0.9383 | |
|
|
| 0.0 | 33.0 | 20856 | 0.6910 | 0.9388 | |
|
|
| 0.0 | 34.0 | 21488 | 0.6861 | 0.9375 | |
|
|
| 0.0 | 35.0 | 22120 | 0.6714 | 0.9386 | |
|
|
| 0.0 | 36.0 | 22752 | 0.6914 | 0.9397 | |
|
|
| 0.0 | 37.0 | 23384 | 0.6756 | 0.9390 | |
|
|
| 0.0 | 38.0 | 24016 | 0.6780 | 0.9390 | |
|
|
| 0.0 | 39.0 | 24648 | 0.6751 | 0.9394 | |
|
|
| 0.0 | 40.0 | 25280 | 0.6756 | 0.9395 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Tokenizers 0.21.0 |
|
|
|
