|
---
|
|
license: mit
|
|
base_model: cointegrated/rubert-tiny2
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- precision
|
|
- recall
|
|
- f1
|
|
- accuracy
|
|
model-index:
|
|
- name: rubert-tiny2-odonata-extended-305-1-ner
|
|
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. -->
|
|
|
|
# rubert-tiny2-odonata-extended-305-1-ner
|
|
|
|
This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the None dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.0181
|
|
- Precision: 0.7075
|
|
- Recall: 0.2799
|
|
- F1: 0.4011
|
|
- Accuracy: 0.9963
|
|
|
|
## 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: 30
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
|
| No log | 1.0 | 213 | 0.0343 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| No log | 2.0 | 426 | 0.0219 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| 0.045 | 3.0 | 639 | 0.0151 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| 0.045 | 4.0 | 852 | 0.0121 | 0.7727 | 0.1269 | 0.2179 | 0.9957 |
|
|
| 0.0065 | 5.0 | 1065 | 0.0127 | 0.6296 | 0.1269 | 0.2112 | 0.9957 |
|
|
| 0.0065 | 6.0 | 1278 | 0.0116 | 0.6667 | 0.2463 | 0.3597 | 0.9962 |
|
|
| 0.0065 | 7.0 | 1491 | 0.0107 | 0.6696 | 0.2873 | 0.4021 | 0.9964 |
|
|
| 0.0047 | 8.0 | 1704 | 0.0115 | 0.7158 | 0.2537 | 0.3747 | 0.9963 |
|
|
| 0.0047 | 9.0 | 1917 | 0.0117 | 0.7327 | 0.2761 | 0.4011 | 0.9963 |
|
|
| 0.0037 | 10.0 | 2130 | 0.0115 | 0.675 | 0.3022 | 0.4175 | 0.9964 |
|
|
| 0.0037 | 11.0 | 2343 | 0.0128 | 0.6990 | 0.2687 | 0.3881 | 0.9963 |
|
|
| 0.0032 | 12.0 | 2556 | 0.0136 | 0.6931 | 0.2612 | 0.3794 | 0.9963 |
|
|
| 0.0032 | 13.0 | 2769 | 0.0136 | 0.7 | 0.2873 | 0.4074 | 0.9963 |
|
|
| 0.0032 | 14.0 | 2982 | 0.0132 | 0.6774 | 0.3134 | 0.4286 | 0.9964 |
|
|
| 0.0026 | 15.0 | 3195 | 0.0137 | 0.6942 | 0.3134 | 0.4319 | 0.9963 |
|
|
| 0.0026 | 16.0 | 3408 | 0.0140 | 0.7193 | 0.3060 | 0.4293 | 0.9964 |
|
|
| 0.0022 | 17.0 | 3621 | 0.0144 | 0.6991 | 0.2948 | 0.4147 | 0.9964 |
|
|
| 0.0022 | 18.0 | 3834 | 0.0157 | 0.7156 | 0.2910 | 0.4138 | 0.9964 |
|
|
| 0.0019 | 19.0 | 4047 | 0.0166 | 0.6923 | 0.2351 | 0.3510 | 0.9962 |
|
|
| 0.0019 | 20.0 | 4260 | 0.0163 | 0.72 | 0.2687 | 0.3913 | 0.9963 |
|
|
| 0.0019 | 21.0 | 4473 | 0.0159 | 0.6957 | 0.2985 | 0.4178 | 0.9963 |
|
|
| 0.0017 | 22.0 | 4686 | 0.0165 | 0.6696 | 0.2873 | 0.4021 | 0.9962 |
|
|
| 0.0017 | 23.0 | 4899 | 0.0174 | 0.6952 | 0.2724 | 0.3914 | 0.9963 |
|
|
| 0.0015 | 24.0 | 5112 | 0.0180 | 0.6882 | 0.2388 | 0.3546 | 0.9961 |
|
|
| 0.0015 | 25.0 | 5325 | 0.0184 | 0.6915 | 0.2425 | 0.3591 | 0.9962 |
|
|
| 0.0014 | 26.0 | 5538 | 0.0183 | 0.7041 | 0.2575 | 0.3770 | 0.9962 |
|
|
| 0.0014 | 27.0 | 5751 | 0.0177 | 0.7009 | 0.2799 | 0.4000 | 0.9963 |
|
|
| 0.0014 | 28.0 | 5964 | 0.0180 | 0.7075 | 0.2799 | 0.4011 | 0.9963 |
|
|
| 0.0013 | 29.0 | 6177 | 0.0178 | 0.6991 | 0.2948 | 0.4147 | 0.9963 |
|
|
| 0.0013 | 30.0 | 6390 | 0.0181 | 0.7075 | 0.2799 | 0.4011 | 0.9963 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.41.2
|
|
- Pytorch 2.3.1+cpu
|
|
- Datasets 2.19.2
|
|
- Tokenizers 0.19.1
|
|
|
