metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: qard
results: []
qard
This model is a fine-tuned version of kaisar-barlybay-sse/kaz_legal_bert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3614
- Accuracy: 0.4391
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: 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 126 | 1.5970 | 0.4271 |
| No log | 2.0 | 252 | 1.3113 | 0.4571 |
| No log | 3.0 | 378 | 1.4418 | 0.4391 |
| 0.838 | 4.0 | 504 | 1.8296 | 0.4491 |
| 0.838 | 5.0 | 630 | 2.2183 | 0.4411 |
| 0.838 | 6.0 | 756 | 1.9106 | 0.4351 |
| 0.838 | 7.0 | 882 | 2.4839 | 0.4451 |
| 0.4281 | 8.0 | 1008 | 3.0046 | 0.4411 |
| 0.4281 | 9.0 | 1134 | 3.2039 | 0.4431 |
| 0.4281 | 10.0 | 1260 | 3.3614 | 0.4391 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3