|
---
|
|
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: 0.0101
|
|
- Precision: 0.6420
|
|
- Recall: 0.5821
|
|
- F1: 0.6106
|
|
- Accuracy: 0.9967
|
|
|
|
## 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 | 32 | 0.1033 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| No log | 2.0 | 64 | 0.0391 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| No log | 3.0 | 96 | 0.0351 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| No log | 4.0 | 128 | 0.0321 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| No log | 5.0 | 160 | 0.0260 | 0.0 | 0.0 | 0.0 | 0.9952 |
|
|
| No log | 6.0 | 192 | 0.0188 | 0.6809 | 0.1194 | 0.2032 | 0.9955 |
|
|
| No log | 7.0 | 224 | 0.0158 | 0.6480 | 0.4328 | 0.5190 | 0.9961 |
|
|
| No log | 8.0 | 256 | 0.0143 | 0.6567 | 0.4925 | 0.5629 | 0.9964 |
|
|
| No log | 9.0 | 288 | 0.0133 | 0.6573 | 0.4366 | 0.5247 | 0.9963 |
|
|
| No log | 10.0 | 320 | 0.0127 | 0.5898 | 0.5634 | 0.5763 | 0.9964 |
|
|
| No log | 11.0 | 352 | 0.0122 | 0.6128 | 0.5373 | 0.5726 | 0.9965 |
|
|
| No log | 12.0 | 384 | 0.0119 | 0.6122 | 0.6007 | 0.6064 | 0.9965 |
|
|
| No log | 13.0 | 416 | 0.0114 | 0.6295 | 0.5261 | 0.5732 | 0.9965 |
|
|
| No log | 14.0 | 448 | 0.0112 | 0.6349 | 0.5709 | 0.6012 | 0.9967 |
|
|
| No log | 15.0 | 480 | 0.0111 | 0.6174 | 0.6082 | 0.6128 | 0.9966 |
|
|
| 0.0665 | 16.0 | 512 | 0.0108 | 0.6491 | 0.5522 | 0.5968 | 0.9967 |
|
|
| 0.0665 | 17.0 | 544 | 0.0108 | 0.6232 | 0.6418 | 0.6324 | 0.9967 |
|
|
| 0.0665 | 18.0 | 576 | 0.0106 | 0.6571 | 0.5149 | 0.5774 | 0.9967 |
|
|
| 0.0665 | 19.0 | 608 | 0.0105 | 0.6271 | 0.5522 | 0.5873 | 0.9965 |
|
|
| 0.0665 | 20.0 | 640 | 0.0105 | 0.6332 | 0.6119 | 0.6224 | 0.9967 |
|
|
| 0.0665 | 21.0 | 672 | 0.0104 | 0.6390 | 0.5746 | 0.6051 | 0.9966 |
|
|
| 0.0665 | 22.0 | 704 | 0.0104 | 0.6316 | 0.5821 | 0.6058 | 0.9966 |
|
|
| 0.0665 | 23.0 | 736 | 0.0103 | 0.6444 | 0.5410 | 0.5882 | 0.9966 |
|
|
| 0.0665 | 24.0 | 768 | 0.0103 | 0.6287 | 0.5560 | 0.5901 | 0.9966 |
|
|
| 0.0665 | 25.0 | 800 | 0.0102 | 0.6322 | 0.5709 | 0.6000 | 0.9966 |
|
|
| 0.0665 | 26.0 | 832 | 0.0102 | 0.6360 | 0.5672 | 0.5996 | 0.9966 |
|
|
| 0.0665 | 27.0 | 864 | 0.0102 | 0.6352 | 0.5784 | 0.6055 | 0.9966 |
|
|
| 0.0665 | 28.0 | 896 | 0.0102 | 0.6453 | 0.5634 | 0.6016 | 0.9967 |
|
|
| 0.0665 | 29.0 | 928 | 0.0101 | 0.6402 | 0.5709 | 0.6036 | 0.9967 |
|
|
| 0.0665 | 30.0 | 960 | 0.0101 | 0.6420 | 0.5821 | 0.6106 | 0.9967 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.41.2
|
|
- Pytorch 2.3.1+cpu
|
|
- Datasets 2.19.2
|
|
- Tokenizers 0.19.1
|
|
|
