|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: distilbert-base-uncased |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: multilabel_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. --> |
|
|
|
# multilabel_classification |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2810 |
|
- F1 Micro: 0.8770 |
|
- F1 Macro: 0.7787 |
|
- F1 Weighted: 0.8672 |
|
- Precision: 0.8702 |
|
- Recall: 0.8770 |
|
- Accuracy: 0.8770 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted | Precision | Recall | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------:|:------:|:--------:| |
|
| No log | 1.0 | 406 | 0.2865 | 0.8643 | 0.7287 | 0.8438 | 0.8620 | 0.8643 | 0.8643 | |
|
| 0.2729 | 2.0 | 812 | 0.2924 | 0.8737 | 0.7671 | 0.8616 | 0.8671 | 0.8737 | 0.8737 | |
|
| 0.216 | 3.0 | 1218 | 0.2810 | 0.8770 | 0.7787 | 0.8672 | 0.8702 | 0.8770 | 0.8770 | |
|
| 0.1868 | 4.0 | 1624 | 0.2813 | 0.8787 | 0.7802 | 0.8685 | 0.8725 | 0.8787 | 0.8787 | |
|
| 0.1728 | 5.0 | 2030 | 0.2944 | 0.8748 | 0.7794 | 0.8664 | 0.8673 | 0.8748 | 0.8748 | |
|
| 0.1728 | 6.0 | 2436 | 0.2937 | 0.8825 | 0.7967 | 0.8760 | 0.8762 | 0.8825 | 0.8825 | |
|
| 0.155 | 7.0 | 2842 | 0.3007 | 0.8848 | 0.8039 | 0.8795 | 0.8789 | 0.8848 | 0.8848 | |
|
| 0.151 | 8.0 | 3248 | 0.3007 | 0.8875 | 0.8070 | 0.8818 | 0.8819 | 0.8875 | 0.8875 | |
|
| 0.1359 | 9.0 | 3654 | 0.3031 | 0.8870 | 0.8077 | 0.8818 | 0.8814 | 0.8870 | 0.8870 | |
|
| 0.1359 | 10.0 | 4060 | 0.3035 | 0.8881 | 0.8086 | 0.8826 | 0.8826 | 0.8881 | 0.8881 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.1 |
