|
--- |
|
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: 0.9614 |
|
- Accuracy: 0.5103 |
|
- F1: 0.4923 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 1.4993 | 1.0 | 15 | 1.4646 | 0.3379 | 0.1707 | |
|
| 1.4661 | 2.0 | 30 | 1.4345 | 0.3379 | 0.1827 | |
|
| 1.4397 | 3.0 | 45 | 1.3804 | 0.3793 | 0.2763 | |
|
| 1.3817 | 4.0 | 60 | 1.3284 | 0.3931 | 0.2855 | |
|
| 1.3375 | 5.0 | 75 | 1.2819 | 0.4207 | 0.3629 | |
|
| 1.3073 | 6.0 | 90 | 1.2493 | 0.4621 | 0.4363 | |
|
| 1.3085 | 7.0 | 105 | 1.2250 | 0.4828 | 0.4577 | |
|
| 1.2545 | 8.0 | 120 | 1.2133 | 0.4966 | 0.4758 | |
|
| 1.29 | 9.0 | 135 | 1.1806 | 0.5034 | 0.4776 | |
|
| 1.2587 | 10.0 | 150 | 1.1522 | 0.5034 | 0.4764 | |
|
| 1.2009 | 11.0 | 165 | 1.1269 | 0.4966 | 0.4760 | |
|
| 1.2258 | 12.0 | 180 | 1.1133 | 0.4966 | 0.4734 | |
|
| 1.1466 | 13.0 | 195 | 1.0942 | 0.5034 | 0.4699 | |
|
| 1.1569 | 14.0 | 210 | 1.0735 | 0.5034 | 0.4793 | |
|
| 1.1194 | 15.0 | 225 | 1.0616 | 0.5034 | 0.4832 | |
|
| 1.0909 | 16.0 | 240 | 1.0529 | 0.5034 | 0.4560 | |
|
| 1.153 | 17.0 | 255 | 1.0334 | 0.5034 | 0.4822 | |
|
| 1.0086 | 18.0 | 270 | 1.0246 | 0.5034 | 0.4765 | |
|
| 1.1102 | 19.0 | 285 | 1.0111 | 0.5103 | 0.4920 | |
|
| 1.0967 | 20.0 | 300 | 1.0024 | 0.5103 | 0.4952 | |
|
| 1.0265 | 21.0 | 315 | 0.9922 | 0.5103 | 0.4937 | |
|
| 1.0377 | 22.0 | 330 | 0.9848 | 0.5103 | 0.4908 | |
|
| 1.0156 | 23.0 | 345 | 0.9794 | 0.5103 | 0.4972 | |
|
| 1.0807 | 24.0 | 360 | 0.9796 | 0.5103 | 0.4928 | |
|
| 1.051 | 25.0 | 375 | 0.9726 | 0.5103 | 0.4831 | |
|
| 0.9827 | 26.0 | 390 | 0.9675 | 0.5103 | 0.4972 | |
|
| 1.0228 | 27.0 | 405 | 0.9646 | 0.5103 | 0.4951 | |
|
| 1.0013 | 28.0 | 420 | 0.9627 | 0.5103 | 0.4950 | |
|
| 0.9963 | 29.0 | 435 | 0.9617 | 0.5103 | 0.4938 | |
|
| 0.9897 | 30.0 | 450 | 0.9614 | 0.5103 | 0.4923 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.6.1 |
|
- Tokenizers 0.11.0 |
|
|
