metadata
language:
- en
base_model: Hartunka/tiny_bert_rand_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_rand_50_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6813725490196079
- name: F1
type: f1
value: 0.7936507936507936
tiny_bert_rand_50_v1_mrpc
This model is a fine-tuned version of Hartunka/tiny_bert_rand_50_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5949
- Accuracy: 0.6814
- F1: 0.7937
- Combined Score: 0.7375
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6286 | 1.0 | 15 | 0.6045 | 0.6863 | 0.8019 | 0.7441 |
| 0.5948 | 2.0 | 30 | 0.5950 | 0.6985 | 0.8087 | 0.7536 |
| 0.556 | 3.0 | 45 | 0.5949 | 0.6814 | 0.7937 | 0.7375 |
| 0.5107 | 4.0 | 60 | 0.6383 | 0.7108 | 0.7958 | 0.7533 |
| 0.4193 | 5.0 | 75 | 0.6820 | 0.6495 | 0.7366 | 0.6931 |
| 0.3479 | 6.0 | 90 | 0.8077 | 0.7034 | 0.8 | 0.7517 |
| 0.2647 | 7.0 | 105 | 0.8842 | 0.6838 | 0.7795 | 0.7317 |
| 0.1929 | 8.0 | 120 | 1.0427 | 0.6814 | 0.7833 | 0.7324 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1