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_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.7617982099267697
tinybert_base_train_kd_mnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_kd on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.5858
- Accuracy: 0.7618
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 |
|---|---|---|---|---|
| 0.8098 | 1.0 | 1534 | 0.7137 | 0.6905 |
| 0.6666 | 2.0 | 3068 | 0.6576 | 0.7277 |
| 0.5873 | 3.0 | 4602 | 0.6274 | 0.7377 |
| 0.522 | 4.0 | 6136 | 0.6076 | 0.7493 |
| 0.4623 | 5.0 | 7670 | 0.6133 | 0.7570 |
| 0.4069 | 6.0 | 9204 | 0.6448 | 0.7575 |
| 0.3547 | 7.0 | 10738 | 0.6818 | 0.7606 |
| 0.3073 | 8.0 | 12272 | 0.7034 | 0.7603 |
| 0.2658 | 9.0 | 13806 | 0.8077 | 0.7490 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1