metadata
license: mit
base_model: cointegrated/rubert-tiny2
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: rubert-tiny2-odonata-ner
results: []
rubert-tiny2-odonata-ner
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: 0.0048
- Precision: 0.4157
- Recall: 0.3274
- F1: 0.3663
- Accuracy: 0.9985
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 188 | 0.0144 | 0.0 | 0.0 | 0.0 | 0.9985 |
| No log | 2.0 | 376 | 0.0133 | 0.0 | 0.0 | 0.0 | 0.9985 |
| 0.0582 | 3.0 | 564 | 0.0100 | 0.0 | 0.0 | 0.0 | 0.9985 |
| 0.0582 | 4.0 | 752 | 0.0069 | 0.5 | 0.0177 | 0.0342 | 0.9985 |
| 0.0582 | 5.0 | 940 | 0.0058 | 0.6667 | 0.0177 | 0.0345 | 0.9985 |
| 0.0084 | 6.0 | 1128 | 0.0053 | 0.5 | 0.1593 | 0.2416 | 0.9985 |
| 0.0084 | 7.0 | 1316 | 0.0052 | 0.4487 | 0.3097 | 0.3665 | 0.9985 |
| 0.0057 | 8.0 | 1504 | 0.0049 | 0.4533 | 0.3009 | 0.3617 | 0.9985 |
| 0.0057 | 9.0 | 1692 | 0.0048 | 0.4302 | 0.3274 | 0.3719 | 0.9985 |
| 0.0057 | 10.0 | 1880 | 0.0048 | 0.4157 | 0.3274 | 0.3663 | 0.9985 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cpu
- Datasets 2.19.2
- Tokenizers 0.19.1