metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_5_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_km_5_v2_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6934499593165175
tiny_bert_km_5_v2_mnli
This model is a fine-tuned version of Hartunka/tiny_bert_km_5_v2 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7252
- Accuracy: 0.6934
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 |
|---|---|---|---|---|
| 0.9851 | 1.0 | 1534 | 0.8962 | 0.5840 |
| 0.8564 | 2.0 | 3068 | 0.8021 | 0.6428 |
| 0.7776 | 3.0 | 4602 | 0.7621 | 0.6653 |
| 0.7255 | 4.0 | 6136 | 0.7469 | 0.6748 |
| 0.6815 | 5.0 | 7670 | 0.7374 | 0.6852 |
| 0.6403 | 6.0 | 9204 | 0.7440 | 0.6904 |
| 0.6029 | 7.0 | 10738 | 0.7365 | 0.6919 |
| 0.5657 | 8.0 | 12272 | 0.7683 | 0.6909 |
| 0.5311 | 9.0 | 13806 | 0.8053 | 0.6910 |
| 0.4934 | 10.0 | 15340 | 0.8146 | 0.6928 |
| 0.4595 | 11.0 | 16874 | 0.8573 | 0.6912 |
| 0.4278 | 12.0 | 18408 | 0.8758 | 0.6904 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1