|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: distilbert-base-multilingual-cased |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: multilabel_lora_distilbert_classifier_tuned_ru |
|
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_lora_distilbert_classifier_tuned_ru |
|
|
|
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3658 |
|
- Accuracy: 0.7845 |
|
- F1: 0.7857 |
|
- Precision: 0.7997 |
|
- Recall: 0.7845 |
|
|
|
## 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: 4.993596574084884e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.0622 | 1.0 | 727 | 0.9090 | 0.6025 | 0.5923 | 0.6149 | 0.6025 | |
|
| 0.9449 | 2.0 | 1454 | 0.7451 | 0.6891 | 0.6855 | 0.6950 | 0.6891 | |
|
| 0.7018 | 3.0 | 2181 | 0.6176 | 0.7359 | 0.7354 | 0.7377 | 0.7359 | |
|
| 0.6192 | 4.0 | 2908 | 0.5854 | 0.7758 | 0.7751 | 0.7805 | 0.7758 | |
|
| 0.4921 | 5.0 | 3635 | 0.5727 | 0.8061 | 0.8050 | 0.8202 | 0.8061 | |
|
| 0.4091 | 6.0 | 4362 | 0.5019 | 0.8294 | 0.8293 | 0.8301 | 0.8294 | |
|
| 0.3273 | 7.0 | 5089 | 0.4864 | 0.8404 | 0.8403 | 0.8409 | 0.8404 | |
|
| 0.3473 | 8.0 | 5816 | 0.4828 | 0.8514 | 0.8512 | 0.8557 | 0.8514 | |
|
| 0.2821 | 9.0 | 6543 | 0.4679 | 0.8597 | 0.8597 | 0.8597 | 0.8597 | |
|
| 0.2599 | 10.0 | 7270 | 0.4874 | 0.8803 | 0.8799 | 0.8823 | 0.8803 | |
|
| 0.2717 | 11.0 | 7997 | 0.4551 | 0.8831 | 0.8829 | 0.8832 | 0.8831 | |
|
| 0.2211 | 12.0 | 8724 | 0.4602 | 0.8858 | 0.8856 | 0.8859 | 0.8858 | |
|
| 0.2207 | 13.0 | 9451 | 0.5086 | 0.8845 | 0.8837 | 0.8862 | 0.8845 | |
|
| 0.2166 | 14.0 | 10178 | 0.4795 | 0.8941 | 0.8936 | 0.8952 | 0.8941 | |
|
| 0.1782 | 15.0 | 10905 | 0.4650 | 0.8955 | 0.8951 | 0.8959 | 0.8955 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
