|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: distilbert-base-uncased-finetuned-IAM |
|
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-base-uncased-finetuned-IAM |
|
|
|
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: 0.9616 |
|
- Accuracy: 0.5103 |
|
- F1: 0.4983 |
|
|
|
## 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: 10 |
|
- eval_batch_size: 10 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 1.5782 | 1.0 | 15 | 1.4989 | 0.3448 | 0.2657 | |
|
| 1.5021 | 2.0 | 30 | 1.4732 | 0.3655 | 0.2645 | |
|
| 1.4674 | 3.0 | 45 | 1.4384 | 0.3448 | 0.2525 | |
|
| 1.4277 | 4.0 | 60 | 1.4140 | 0.3517 | 0.2751 | |
|
| 1.4341 | 5.0 | 75 | 1.3905 | 0.3379 | 0.2546 | |
|
| 1.3698 | 6.0 | 90 | 1.3697 | 0.3724 | 0.2936 | |
|
| 1.4233 | 7.0 | 105 | 1.3196 | 0.3862 | 0.3073 | |
|
| 1.3112 | 8.0 | 120 | 1.3048 | 0.4552 | 0.3958 | |
|
| 1.372 | 9.0 | 135 | 1.2548 | 0.4138 | 0.3385 | |
|
| 1.3284 | 10.0 | 150 | 1.2020 | 0.4759 | 0.4287 | |
|
| 1.2412 | 11.0 | 165 | 1.1672 | 0.4966 | 0.4594 | |
|
| 1.2508 | 12.0 | 180 | 1.1453 | 0.4897 | 0.4740 | |
|
| 1.1843 | 13.0 | 195 | 1.1172 | 0.4966 | 0.4784 | |
|
| 1.1694 | 14.0 | 210 | 1.1006 | 0.4966 | 0.4785 | |
|
| 1.1438 | 15.0 | 225 | 1.0763 | 0.5034 | 0.4851 | |
|
| 1.1066 | 16.0 | 240 | 1.0603 | 0.5034 | 0.4815 | |
|
| 1.1357 | 17.0 | 255 | 1.0435 | 0.5034 | 0.4821 | |
|
| 1.0352 | 18.0 | 270 | 1.0358 | 0.5034 | 0.4803 | |
|
| 1.1355 | 19.0 | 285 | 1.0183 | 0.5103 | 0.4941 | |
|
| 1.063 | 20.0 | 300 | 1.0063 | 0.5103 | 0.4957 | |
|
| 1.0329 | 21.0 | 315 | 0.9960 | 0.5103 | 0.4989 | |
|
| 1.063 | 22.0 | 330 | 0.9867 | 0.5103 | 0.4989 | |
|
| 1.0289 | 23.0 | 345 | 0.9821 | 0.5103 | 0.4980 | |
|
| 1.0624 | 24.0 | 360 | 0.9816 | 0.5103 | 0.4942 | |
|
| 1.0404 | 25.0 | 375 | 0.9723 | 0.5103 | 0.4939 | |
|
| 0.9791 | 26.0 | 390 | 0.9693 | 0.5103 | 0.4985 | |
|
| 1.0365 | 27.0 | 405 | 0.9663 | 0.5103 | 0.4980 | |
|
| 1.0129 | 28.0 | 420 | 0.9637 | 0.5103 | 0.5002 | |
|
| 0.9844 | 29.0 | 435 | 0.9617 | 0.5103 | 0.4997 | |
|
| 1.0049 | 30.0 | 450 | 0.9616 | 0.5103 | 0.4983 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.6.1 |
|
- Tokenizers 0.11.0 |
|
|
