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_qnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QNLI
type: glue
args: qnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6146805784367564
tiny_bert_rand_50_v1_qnli
This model is a fine-tuned version of Hartunka/tiny_bert_rand_50_v1 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6506
- Accuracy: 0.6147
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 |
|---|---|---|---|---|
| 0.6648 | 1.0 | 410 | 0.6506 | 0.6147 |
| 0.6346 | 2.0 | 820 | 0.6588 | 0.6143 |
| 0.5929 | 3.0 | 1230 | 0.6646 | 0.6145 |
| 0.5346 | 4.0 | 1640 | 0.7260 | 0.6057 |
| 0.4633 | 5.0 | 2050 | 0.7665 | 0.6021 |
| 0.3949 | 6.0 | 2460 | 0.9755 | 0.5938 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1