metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: gokulsrinivasagan/tinybert_base_train_kd
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tinybert_base_train_kd_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5848375451263538
tinybert_base_train_kd_rte
This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_kd on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6791
- Accuracy: 0.5848
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 |
|---|---|---|---|---|
| 0.705 | 1.0 | 10 | 0.6918 | 0.5271 |
| 0.695 | 2.0 | 20 | 0.7236 | 0.4801 |
| 0.6831 | 3.0 | 30 | 0.6791 | 0.5848 |
| 0.6248 | 4.0 | 40 | 0.6916 | 0.5884 |
| 0.5451 | 5.0 | 50 | 0.7247 | 0.6245 |
| 0.4932 | 6.0 | 60 | 0.7858 | 0.5884 |
| 0.3597 | 7.0 | 70 | 0.9330 | 0.6029 |
| 0.268 | 8.0 | 80 | 0.9831 | 0.6209 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1