metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_rand_50_v2_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6985294117647058
- name: F1
type: f1
value: 0.8098918083462133
tiny_bert_rand_50_v2_mrpc
This model is a fine-tuned version of Hartunka/tiny_bert_rand_50_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5925
- Accuracy: 0.6985
- F1: 0.8099
- Combined Score: 0.7542
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 |
|---|---|---|---|---|---|---|
| 0.6271 | 1.0 | 15 | 0.6033 | 0.6961 | 0.8092 | 0.7527 |
| 0.5912 | 2.0 | 30 | 0.5925 | 0.6985 | 0.8099 | 0.7542 |
| 0.5551 | 3.0 | 45 | 0.6019 | 0.6863 | 0.7994 | 0.7428 |
| 0.5148 | 4.0 | 60 | 0.6426 | 0.6422 | 0.7214 | 0.6818 |
| 0.43 | 5.0 | 75 | 0.6741 | 0.6225 | 0.7105 | 0.6665 |
| 0.3406 | 6.0 | 90 | 0.8508 | 0.6373 | 0.7422 | 0.6897 |
| 0.2595 | 7.0 | 105 | 0.9303 | 0.6740 | 0.7734 | 0.7237 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1