|
---
|
|
license: apache-2.0
|
|
base_model: asapp/sew-d-tiny-100k-ft-ls100h
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
- precision
|
|
- recall
|
|
- f1
|
|
model-index:
|
|
- name: sewd-classifier
|
|
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. -->
|
|
|
|
# sewd-classifier
|
|
|
|
This model is a fine-tuned version of [asapp/sew-d-tiny-100k-ft-ls100h](https://huggingface.co/asapp/sew-d-tiny-100k-ft-ls100h) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 3.0550
|
|
- Accuracy: 0.2615
|
|
- Precision: 0.1852
|
|
- Recall: 0.2615
|
|
- F1: 0.1884
|
|
- Binary: 0.4790
|
|
|
|
## 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: 3e-05
|
|
- train_batch_size: 32
|
|
- eval_batch_size: 32
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 4
|
|
- total_train_batch_size: 128
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- num_epochs: 10
|
|
- mixed_precision_training: Native AMP
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Binary |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
|
|
| No log | 0.96 | 50 | 4.3136 | 0.0189 | 0.0016 | 0.0189 | 0.0027 | 0.1941 |
|
|
| 4.4253 | 1.91 | 100 | 4.0292 | 0.0889 | 0.0382 | 0.0889 | 0.0339 | 0.3261 |
|
|
| 4.2369 | 2.87 | 150 | 3.7609 | 0.1267 | 0.0875 | 0.1267 | 0.0706 | 0.3763 |
|
|
| 4.0004 | 3.83 | 200 | 3.5568 | 0.1563 | 0.0681 | 0.1563 | 0.0827 | 0.3992 |
|
|
| 3.7262 | 4.78 | 250 | 3.4164 | 0.1725 | 0.0858 | 0.1725 | 0.0932 | 0.4151 |
|
|
| 3.6489 | 5.74 | 300 | 3.2817 | 0.2156 | 0.1380 | 0.2156 | 0.1327 | 0.4453 |
|
|
| 3.5178 | 6.7 | 350 | 3.1920 | 0.2102 | 0.1752 | 0.2102 | 0.1384 | 0.4423 |
|
|
| 3.4228 | 7.66 | 400 | 3.1191 | 0.2264 | 0.1794 | 0.2264 | 0.1543 | 0.4553 |
|
|
| 3.2967 | 8.61 | 450 | 3.0710 | 0.2507 | 0.1804 | 0.2507 | 0.1807 | 0.4714 |
|
|
| 3.3135 | 9.57 | 500 | 3.0550 | 0.2615 | 0.1852 | 0.2615 | 0.1884 | 0.4790 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.38.2
|
|
- Pytorch 2.3.0
|
|
- Datasets 2.19.1
|
|
- Tokenizers 0.15.1
|
|
|
