metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_10_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_rand_10_v1_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.516245487364621
tiny_bert_rand_10_v1_rte
This model is a fine-tuned version of Hartunka/tiny_bert_rand_10_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6918
- Accuracy: 0.5162
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7007 | 1.0 | 10 | 0.6918 | 0.5162 |
| 0.6835 | 2.0 | 20 | 0.6920 | 0.5596 |
| 0.6616 | 3.0 | 30 | 0.7088 | 0.5740 |
| 0.6219 | 4.0 | 40 | 0.7803 | 0.5523 |
| 0.5651 | 5.0 | 50 | 0.8309 | 0.5379 |
| 0.4986 | 6.0 | 60 | 0.9334 | 0.5126 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1