metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_km_5_v1_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6604963384865744
bert_base_km_5_v1_mnli
This model is a fine-tuned version of Hartunka/bert_base_km_5_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7877
- Accuracy: 0.6605
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 |
|---|---|---|---|---|
| 0.9844 | 1.0 | 1534 | 0.9082 | 0.5690 |
| 0.8695 | 2.0 | 3068 | 0.8510 | 0.6127 |
| 0.7774 | 3.0 | 4602 | 0.8041 | 0.6435 |
| 0.6904 | 4.0 | 6136 | 0.7985 | 0.6588 |
| 0.6068 | 5.0 | 7670 | 0.8158 | 0.6659 |
| 0.521 | 6.0 | 9204 | 0.9025 | 0.6599 |
| 0.4345 | 7.0 | 10738 | 0.9470 | 0.6591 |
| 0.3593 | 8.0 | 12272 | 1.0820 | 0.6572 |
| 0.2939 | 9.0 | 13806 | 1.2041 | 0.6549 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1