metadata
library_name: transformers
base_model: ai-forever/ruBert-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: my-chgk-ner-model-v1
results: []
my-chgk-ner-model-v1
This model is a fine-tuned version of ai-forever/ruBert-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3204
- Precision: 0.6308
- Recall: 0.6464
- F1: 0.6347
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: 32
- 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: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 50 | 0.2016 | 0.3892 | 0.4330 | 0.3974 |
| No log | 2.0 | 100 | 0.1674 | 0.4990 | 0.5723 | 0.5258 |
| No log | 3.0 | 150 | 0.1732 | 0.5184 | 0.6257 | 0.5621 |
| No log | 4.0 | 200 | 0.1819 | 0.5821 | 0.6373 | 0.6079 |
| No log | 5.0 | 250 | 0.2041 | 0.6160 | 0.6317 | 0.6208 |
| No log | 6.0 | 300 | 0.2197 | 0.6023 | 0.6908 | 0.6411 |
| No log | 7.0 | 350 | 0.2349 | 0.6100 | 0.6512 | 0.6281 |
| No log | 8.0 | 400 | 0.2418 | 0.6039 | 0.6490 | 0.6240 |
| No log | 9.0 | 450 | 0.2609 | 0.6456 | 0.6744 | 0.6575 |
| 0.0914 | 10.0 | 500 | 0.2792 | 0.6243 | 0.6658 | 0.6396 |
| 0.0914 | 11.0 | 550 | 0.2931 | 0.6375 | 0.6693 | 0.6515 |
| 0.0914 | 12.0 | 600 | 0.3204 | 0.6308 | 0.6464 | 0.6347 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2