metadata
base_model: mika5883/RuReCl8
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: RuReCl8
results: []
RuReCl8
This model is a fine-tuned version of mika5883/RuReCl8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1825
- Bleu: 61.2481
- Gen Len: 16.234
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: 3.83229e-05
- train_batch_size: 128
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 20 | 0.1898 | 61.0474 | 16.2296 |
| No log | 2.0 | 40 | 0.1825 | 61.2481 | 16.234 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2