|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilroberta_base_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. --> |
|
|
|
# distilroberta_base_patent |
|
|
|
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0022 |
|
- Accuracy: 0.6596 |
|
- F1 Macro: 0.5725 |
|
- F1 Micro: 0.6596 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.5474 | 0.13 | 50 | 1.4682 | 0.4644 | 0.3007 | 0.4644 | |
|
| 1.2975 | 0.26 | 100 | 1.2702 | 0.5514 | 0.3857 | 0.5514 | |
|
| 1.277 | 0.38 | 150 | 1.1989 | 0.588 | 0.4213 | 0.588 | |
|
| 1.1483 | 0.51 | 200 | 1.1509 | 0.6018 | 0.4433 | 0.6018 | |
|
| 1.1909 | 0.64 | 250 | 1.1209 | 0.618 | 0.4785 | 0.618 | |
|
| 1.1243 | 0.77 | 300 | 1.1128 | 0.622 | 0.4930 | 0.622 | |
|
| 1.1353 | 0.9 | 350 | 1.1134 | 0.609 | 0.4930 | 0.609 | |
|
| 1.0636 | 1.02 | 400 | 1.0676 | 0.64 | 0.5189 | 0.64 | |
|
| 0.9667 | 1.15 | 450 | 1.0703 | 0.6404 | 0.5193 | 0.6404 | |
|
| 1.0063 | 1.28 | 500 | 1.0495 | 0.6386 | 0.5128 | 0.6386 | |
|
| 0.9521 | 1.41 | 550 | 1.0469 | 0.6432 | 0.5185 | 0.6432 | |
|
| 0.998 | 1.53 | 600 | 1.0359 | 0.6486 | 0.5357 | 0.6486 | |
|
| 1.0188 | 1.66 | 650 | 1.0530 | 0.6418 | 0.5395 | 0.6418 | |
|
| 0.9617 | 1.79 | 700 | 1.0214 | 0.6526 | 0.5307 | 0.6526 | |
|
| 1.0234 | 1.92 | 750 | 1.0148 | 0.6514 | 0.5495 | 0.6514 | |
|
| 0.8914 | 2.05 | 800 | 1.0132 | 0.6544 | 0.5603 | 0.6544 | |
|
| 0.9269 | 2.17 | 850 | 1.0110 | 0.6562 | 0.5647 | 0.6562 | |
|
| 1.0351 | 2.3 | 900 | 1.0124 | 0.6528 | 0.5717 | 0.6528 | |
|
| 0.9582 | 2.43 | 950 | 1.0150 | 0.6524 | 0.5552 | 0.6524 | |
|
| 0.8959 | 2.56 | 1000 | 1.0069 | 0.659 | 0.5741 | 0.659 | |
|
| 0.8342 | 2.69 | 1050 | 1.0031 | 0.6596 | 0.5794 | 0.6596 | |
|
| 0.883 | 2.81 | 1100 | 1.0042 | 0.6594 | 0.5767 | 0.6594 | |
|
| 0.9377 | 2.94 | 1150 | 1.0022 | 0.6596 | 0.5725 | 0.6596 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|