metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
my_awesome_model
This model is a fine-tuned version of AIRI-Institute/gena-lm-bigbird-base-t2t on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6717
- Accuracy: 0.7949
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6885 | 1.0 | 10 | 0.6923 | 0.4615 |
| 0.6785 | 2.0 | 20 | 0.6819 | 0.5385 |
| 0.6589 | 3.0 | 30 | 0.6930 | 0.5128 |
| 0.6021 | 4.0 | 40 | 0.7762 | 0.5128 |
| 0.5021 | 5.0 | 50 | 0.5179 | 0.7949 |
| 0.3407 | 6.0 | 60 | 0.4931 | 0.7436 |
| 0.2148 | 7.0 | 70 | 0.5146 | 0.8462 |
| 0.1577 | 8.0 | 80 | 0.5509 | 0.7949 |
| 0.167 | 9.0 | 90 | 0.5763 | 0.8462 |
| 0.0903 | 10.0 | 100 | 0.6717 | 0.7949 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3