metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_km_5_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6936274509803921
- name: F1
type: f1
value: 0.8079877112135176
tiny_bert_km_5_v1_mrpc
This model is a fine-tuned version of Hartunka/tiny_bert_km_5_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5968
- Accuracy: 0.6936
- F1: 0.8080
- Combined Score: 0.7508
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 |
|---|---|---|---|---|---|---|
| 0.6303 | 1.0 | 15 | 0.6029 | 0.6961 | 0.8098 | 0.7529 |
| 0.5897 | 2.0 | 30 | 0.5968 | 0.6936 | 0.8080 | 0.7508 |
| 0.5512 | 3.0 | 45 | 0.6064 | 0.6936 | 0.8109 | 0.7523 |
| 0.5077 | 4.0 | 60 | 0.6256 | 0.6912 | 0.7850 | 0.7381 |
| 0.4312 | 5.0 | 75 | 0.6735 | 0.6789 | 0.7776 | 0.7283 |
| 0.3364 | 6.0 | 90 | 0.7617 | 0.6814 | 0.7751 | 0.7282 |
| 0.2516 | 7.0 | 105 | 0.8654 | 0.6373 | 0.7404 | 0.6888 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1