sber-full-test / README.md
ruselkomp's picture
update model card README.md
e051a3d
---
tags:
- generated_from_trainer
model-index:
- name: sber-full-test
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. -->
# sber-full-test
This model is a fine-tuned version of [sberbank-ai/sbert_large_nlu_ru](https://huggingface.co/sberbank-ai/sbert_large_nlu_ru) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4148
## 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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.0779 | 1.0 | 9046 | 1.3850 |
| 0.7429 | 2.0 | 18092 | 1.1795 |
| 0.446 | 3.0 | 27138 | 1.4148 |
### Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.2.2.dev0
- Tokenizers 0.12.1