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_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5270758122743683
tiny_bert_km_100_v1_rte
This model is a fine-tuned version of Hartunka/tiny_bert_km_100_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6949
- Accuracy: 0.5271
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 |
|---|---|---|---|---|
| 0.699 | 1.0 | 10 | 0.6959 | 0.5271 |
| 0.6852 | 2.0 | 20 | 0.7013 | 0.4982 |
| 0.6713 | 3.0 | 30 | 0.6949 | 0.5271 |
| 0.6531 | 4.0 | 40 | 0.7031 | 0.5451 |
| 0.6265 | 5.0 | 50 | 0.7080 | 0.5235 |
| 0.5887 | 6.0 | 60 | 0.7480 | 0.5162 |
| 0.5347 | 7.0 | 70 | 0.7833 | 0.5343 |
| 0.457 | 8.0 | 80 | 0.8417 | 0.5307 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1