metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
base_model: cointegrated/rubert-tiny2
model-index:
- name: greenery_finder_model_v2
results: []
greenery_finder_model_v2
This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1768
- F1: 0.9700
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.1936 | 1.0 | 896 | 0.2916 | 0.9500 |
| 0.3054 | 2.0 | 1792 | 0.1344 | 0.9700 |
| 0.1174 | 3.0 | 2688 | 0.1948 | 0.9700 |
| 0.0417 | 4.0 | 3584 | 0.1929 | 0.9700 |
| 0.1048 | 5.0 | 4480 | 0.1768 | 0.9700 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.1.0.dev20230523+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3