metadata
language:
- en
base_model: Hartunka/tiny_bert_km_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_km_50_v1_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5054151624548736
tiny_bert_km_50_v1_rte
This model is a fine-tuned version of Hartunka/tiny_bert_km_50_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6951
- Accuracy: 0.5054
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 |
|---|---|---|---|---|
| 0.6977 | 1.0 | 10 | 0.6951 | 0.5054 |
| 0.684 | 2.0 | 20 | 0.7016 | 0.4946 |
| 0.6682 | 3.0 | 30 | 0.7009 | 0.5018 |
| 0.6498 | 4.0 | 40 | 0.7172 | 0.4874 |
| 0.6256 | 5.0 | 50 | 0.7284 | 0.5126 |
| 0.5891 | 6.0 | 60 | 0.7591 | 0.5054 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1