metadata
library_name: transformers
license: mit
base_model: sergeyzh/rubert-mini-sts
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- precision
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of sergeyzh/rubert-mini-sts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2971
- Accuracy: 0.9341
- Recall: 0.8385
- Precision: 0.4891
- F1: 0.6178
- Roc Auc: 0.9580
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.4671 | 1.0 | 634 | 0.3607 | 0.9262 | 0.7453 | 0.4511 | 0.5621 | 0.9394 |
| 0.3636 | 2.0 | 1268 | 0.2971 | 0.9341 | 0.8385 | 0.4891 | 0.6178 | 0.9580 |
| 0.2249 | 3.0 | 1902 | 0.4273 | 0.9594 | 0.7019 | 0.6726 | 0.6869 | 0.9521 |
| 0.0178 | 4.0 | 2536 | 0.6423 | 0.9657 | 0.6398 | 0.7803 | 0.7031 | 0.9507 |
| 0.0123 | 5.0 | 3170 | 0.5578 | 0.9558 | 0.7516 | 0.6269 | 0.6836 | 0.9500 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0