metadata
language:
- en
base_model: Hartunka/tiny_bert_rand_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_rand_50_v1_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.5633802816901409
tiny_bert_rand_50_v1_wnli
This model is a fine-tuned version of Hartunka/tiny_bert_rand_50_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6924
- Accuracy: 0.5634
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 |
|---|---|---|---|---|
| 0.6996 | 1.0 | 3 | 0.6930 | 0.5352 |
| 0.6965 | 2.0 | 6 | 0.6924 | 0.5634 |
| 0.6961 | 3.0 | 9 | 0.7065 | 0.3662 |
| 0.6933 | 4.0 | 12 | 0.7048 | 0.3521 |
| 0.6941 | 5.0 | 15 | 0.7031 | 0.4507 |
| 0.6911 | 6.0 | 18 | 0.7073 | 0.3944 |
| 0.6905 | 7.0 | 21 | 0.7102 | 0.4085 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1