|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
base_model: bert-base-multilingual-cased |
|
model-index: |
|
- name: comic-name-classification |
|
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. --> |
|
|
|
# comic-name-classification |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0445 |
|
- Accuracy: 0.9937 |
|
|
|
## 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: 0.000125 |
|
- 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 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 25 | 0.0311 | 0.9933 | |
|
| No log | 2.0 | 50 | 0.0330 | 0.9937 | |
|
| No log | 3.0 | 75 | 0.0330 | 0.9933 | |
|
| No log | 4.0 | 100 | 0.0350 | 0.9941 | |
|
| No log | 5.0 | 125 | 0.0358 | 0.9937 | |
|
| No log | 6.0 | 150 | 0.0363 | 0.9937 | |
|
| No log | 7.0 | 175 | 0.0379 | 0.9945 | |
|
| No log | 8.0 | 200 | 0.0356 | 0.9941 | |
|
| No log | 9.0 | 225 | 0.0352 | 0.9941 | |
|
| No log | 10.0 | 250 | 0.0376 | 0.9941 | |
|
| No log | 11.0 | 275 | 0.0374 | 0.9941 | |
|
| No log | 12.0 | 300 | 0.0387 | 0.9937 | |
|
| No log | 13.0 | 325 | 0.0384 | 0.9941 | |
|
| No log | 14.0 | 350 | 0.0392 | 0.9941 | |
|
| No log | 15.0 | 375 | 0.0392 | 0.9941 | |
|
| No log | 16.0 | 400 | 0.0394 | 0.9941 | |
|
| No log | 17.0 | 425 | 0.0412 | 0.9945 | |
|
| No log | 18.0 | 450 | 0.0404 | 0.9941 | |
|
| No log | 19.0 | 475 | 0.0410 | 0.9941 | |
|
| 0.0039 | 20.0 | 500 | 0.0414 | 0.9941 | |
|
| 0.0039 | 21.0 | 525 | 0.0425 | 0.9941 | |
|
| 0.0039 | 22.0 | 550 | 0.0416 | 0.9941 | |
|
| 0.0039 | 23.0 | 575 | 0.0431 | 0.9941 | |
|
| 0.0039 | 24.0 | 600 | 0.0439 | 0.9941 | |
|
| 0.0039 | 25.0 | 625 | 0.0443 | 0.9941 | |
|
| 0.0039 | 26.0 | 650 | 0.0440 | 0.9937 | |
|
| 0.0039 | 27.0 | 675 | 0.0435 | 0.9937 | |
|
| 0.0039 | 28.0 | 700 | 0.0428 | 0.9941 | |
|
| 0.0039 | 29.0 | 725 | 0.0424 | 0.9941 | |
|
| 0.0039 | 30.0 | 750 | 0.0431 | 0.9941 | |
|
| 0.0039 | 31.0 | 775 | 0.0438 | 0.9941 | |
|
| 0.0039 | 32.0 | 800 | 0.0419 | 0.9941 | |
|
| 0.0039 | 33.0 | 825 | 0.0419 | 0.9941 | |
|
| 0.0039 | 34.0 | 850 | 0.0416 | 0.9941 | |
|
| 0.0039 | 35.0 | 875 | 0.0419 | 0.9941 | |
|
| 0.0039 | 36.0 | 900 | 0.0430 | 0.9945 | |
|
| 0.0039 | 37.0 | 925 | 0.0431 | 0.9941 | |
|
| 0.0039 | 38.0 | 950 | 0.0439 | 0.9941 | |
|
| 0.0039 | 39.0 | 975 | 0.0445 | 0.9937 | |
|
| 0.0021 | 40.0 | 1000 | 0.0449 | 0.9937 | |
|
| 0.0021 | 41.0 | 1025 | 0.0456 | 0.9941 | |
|
| 0.0021 | 42.0 | 1050 | 0.0459 | 0.9941 | |
|
| 0.0021 | 43.0 | 1075 | 0.0446 | 0.9937 | |
|
| 0.0021 | 44.0 | 1100 | 0.0439 | 0.9941 | |
|
| 0.0021 | 45.0 | 1125 | 0.0439 | 0.9941 | |
|
| 0.0021 | 46.0 | 1150 | 0.0441 | 0.9941 | |
|
| 0.0021 | 47.0 | 1175 | 0.0443 | 0.9941 | |
|
| 0.0021 | 48.0 | 1200 | 0.0443 | 0.9937 | |
|
| 0.0021 | 49.0 | 1225 | 0.0444 | 0.9937 | |
|
| 0.0021 | 50.0 | 1250 | 0.0445 | 0.9937 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
