metadata
language:
- en
base_model: Hartunka/tiny_bert_km_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_km_100_v1_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6392392188771359
tiny_bert_km_100_v1_mnli
This model is a fine-tuned version of Hartunka/tiny_bert_km_100_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8203
- Accuracy: 0.6392
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0013 | 1.0 | 1534 | 0.9411 | 0.5438 |
| 0.9118 | 2.0 | 3068 | 0.8921 | 0.5829 |
| 0.8579 | 3.0 | 4602 | 0.8575 | 0.6049 |
| 0.811 | 4.0 | 6136 | 0.8428 | 0.6192 |
| 0.7625 | 5.0 | 7670 | 0.8314 | 0.6324 |
| 0.7165 | 6.0 | 9204 | 0.8438 | 0.6409 |
| 0.6721 | 7.0 | 10738 | 0.8498 | 0.6440 |
| 0.6294 | 8.0 | 12272 | 0.8689 | 0.6462 |
| 0.5874 | 9.0 | 13806 | 0.9020 | 0.6466 |
| 0.5462 | 10.0 | 15340 | 0.9526 | 0.6473 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1