metadata
library_name: transformers
license: apache-2.0
base_model: cl-nagoya/ruri-v3-130m
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: results_sudachi
results: []
results_sudachi
This model is a fine-tuned version of cl-nagoya/ruri-v3-130m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1707
- Precision: 0.8447
- Recall: 0.8768
- F1: 0.8605
- Accuracy: 0.9704
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 301 | 0.1252 | 0.7904 | 0.8345 | 0.8118 | 0.9675 |
| 0.1349 | 2.0 | 602 | 0.1337 | 0.7867 | 0.8295 | 0.8075 | 0.9649 |
| 0.1349 | 3.0 | 903 | 0.1582 | 0.8132 | 0.8668 | 0.8391 | 0.9659 |
| 0.0395 | 4.0 | 1204 | 0.1484 | 0.8161 | 0.8646 | 0.8397 | 0.9669 |
| 0.0186 | 5.0 | 1505 | 0.1632 | 0.8430 | 0.8574 | 0.8501 | 0.9701 |
| 0.0186 | 6.0 | 1806 | 0.1707 | 0.8447 | 0.8768 | 0.8605 | 0.9704 |
| 0.0091 | 7.0 | 2107 | 0.2057 | 0.8241 | 0.8660 | 0.8446 | 0.9689 |
| 0.0091 | 8.0 | 2408 | 0.1948 | 0.8404 | 0.8603 | 0.8503 | 0.9709 |
| 0.0065 | 9.0 | 2709 | 0.2039 | 0.8332 | 0.8553 | 0.8441 | 0.9703 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2