metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: gokulsrinivasagan/tinybert_train_book_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tinybert_train_book_v2_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7254901960784313
- name: F1
type: f1
value: 0.819935691318328
tinybert_train_book_v2_mrpc
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5565
- Accuracy: 0.7255
- F1: 0.8199
- Combined Score: 0.7727
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6258 | 1.0 | 15 | 0.6008 | 0.6936 | 0.8092 | 0.7514 |
| 0.5875 | 2.0 | 30 | 0.5684 | 0.7157 | 0.8159 | 0.7658 |
| 0.5354 | 3.0 | 45 | 0.5565 | 0.7255 | 0.8199 | 0.7727 |
| 0.463 | 4.0 | 60 | 0.5646 | 0.7059 | 0.7770 | 0.7414 |
| 0.3584 | 5.0 | 75 | 0.5854 | 0.7721 | 0.8463 | 0.8092 |
| 0.2647 | 6.0 | 90 | 0.6195 | 0.7647 | 0.8378 | 0.8013 |
| 0.1931 | 7.0 | 105 | 0.7031 | 0.7647 | 0.8356 | 0.8002 |
| 0.1698 | 8.0 | 120 | 0.7911 | 0.7647 | 0.8442 | 0.8044 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3