metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_20_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_rand_20_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7132352941176471
- name: F1
type: f1
value: 0.7958115183246073
bert_base_rand_20_v1_mrpc
This model is a fine-tuned version of Hartunka/bert_base_rand_20_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5873
- Accuracy: 0.7132
- F1: 0.7958
- Combined Score: 0.7545
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 |
|---|---|---|---|---|---|---|
| 0.6376 | 1.0 | 15 | 0.5900 | 0.6912 | 0.8006 | 0.7459 |
| 0.5782 | 2.0 | 30 | 0.5873 | 0.7132 | 0.7958 | 0.7545 |
| 0.5004 | 3.0 | 45 | 0.5992 | 0.7157 | 0.7986 | 0.7571 |
| 0.3709 | 4.0 | 60 | 0.7209 | 0.6936 | 0.7723 | 0.7330 |
| 0.2326 | 5.0 | 75 | 0.9645 | 0.6814 | 0.7610 | 0.7212 |
| 0.1352 | 6.0 | 90 | 1.1715 | 0.6789 | 0.7690 | 0.7239 |
| 0.0961 | 7.0 | 105 | 1.2892 | 0.6618 | 0.7579 | 0.7098 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1