|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_base_uncased_patent |
|
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_patent |
|
|
|
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9811 |
|
- Accuracy: 0.6632 |
|
- F1 Macro: 0.5701 |
|
- F1 Micro: 0.6632 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.5572 | 0.13 | 50 | 1.4884 | 0.504 | 0.3171 | 0.504 | |
|
| 1.2925 | 0.26 | 100 | 1.2877 | 0.5634 | 0.3803 | 0.5634 | |
|
| 1.253 | 0.38 | 150 | 1.2014 | 0.5974 | 0.4162 | 0.5974 | |
|
| 1.1591 | 0.51 | 200 | 1.1558 | 0.6102 | 0.4468 | 0.6102 | |
|
| 1.1756 | 0.64 | 250 | 1.1151 | 0.6244 | 0.4725 | 0.6244 | |
|
| 1.1078 | 0.77 | 300 | 1.1123 | 0.6268 | 0.4912 | 0.6268 | |
|
| 1.1463 | 0.9 | 350 | 1.0832 | 0.627 | 0.5030 | 0.627 | |
|
| 1.0328 | 1.02 | 400 | 1.0610 | 0.6432 | 0.5068 | 0.6432 | |
|
| 0.9224 | 1.15 | 450 | 1.0462 | 0.6476 | 0.5153 | 0.6476 | |
|
| 0.9902 | 1.28 | 500 | 1.0401 | 0.6448 | 0.5168 | 0.6448 | |
|
| 0.9681 | 1.41 | 550 | 1.0253 | 0.6546 | 0.5216 | 0.6546 | |
|
| 0.9657 | 1.53 | 600 | 1.0123 | 0.6564 | 0.5248 | 0.6564 | |
|
| 0.9742 | 1.66 | 650 | 1.0186 | 0.656 | 0.5263 | 0.656 | |
|
| 0.9443 | 1.79 | 700 | 1.0028 | 0.66 | 0.5279 | 0.66 | |
|
| 0.9944 | 1.92 | 750 | 1.0000 | 0.6544 | 0.5324 | 0.6544 | |
|
| 0.849 | 2.05 | 800 | 0.9939 | 0.6588 | 0.5571 | 0.6588 | |
|
| 0.8801 | 2.17 | 850 | 0.9916 | 0.6608 | 0.5618 | 0.6608 | |
|
| 0.9913 | 2.3 | 900 | 0.9912 | 0.6634 | 0.5686 | 0.6634 | |
|
| 0.923 | 2.43 | 950 | 0.9879 | 0.666 | 0.5739 | 0.666 | |
|
| 0.8935 | 2.56 | 1000 | 0.9828 | 0.6642 | 0.5695 | 0.6642 | |
|
| 0.8062 | 2.69 | 1050 | 0.9877 | 0.6598 | 0.5691 | 0.6598 | |
|
| 0.853 | 2.81 | 1100 | 0.9811 | 0.6632 | 0.5701 | 0.6632 | |
|
| 0.8978 | 2.94 | 1150 | 0.9811 | 0.6638 | 0.5709 | 0.6638 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|