metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_km_100_v2_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6645646867371847
bert_base_km_100_v2_mnli
This model is a fine-tuned version of Hartunka/bert_base_km_100_v2 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7707
- Accuracy: 0.6646
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use 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 | Accuracy |
|---|---|---|---|---|
| 0.9919 | 1.0 | 1534 | 0.9109 | 0.5674 |
| 0.8775 | 2.0 | 3068 | 0.8532 | 0.6129 |
| 0.7872 | 3.0 | 4602 | 0.7985 | 0.6460 |
| 0.7081 | 4.0 | 6136 | 0.7868 | 0.6558 |
| 0.6356 | 5.0 | 7670 | 0.7994 | 0.6590 |
| 0.5597 | 6.0 | 9204 | 0.8493 | 0.6656 |
| 0.481 | 7.0 | 10738 | 0.9019 | 0.6660 |
| 0.4057 | 8.0 | 12272 | 0.9966 | 0.6587 |
| 0.3381 | 9.0 | 13806 | 1.1030 | 0.6597 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1