metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_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: 0.7058823529411765
- name: F1
type: f1
value: 0.7931034482758621
bert_base_rand_50_v2_mrpc
This model is a fine-tuned version of Hartunka/bert_base_rand_50_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5897
- Accuracy: 0.7059
- F1: 0.7931
- Combined Score: 0.7495
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 | 0.5932 | 0.6912 | 0.8006 | 0.7459 |
| 0.5729 | 2.0 | 30 | 0.5897 | 0.7059 | 0.7931 | 0.7495 |
| 0.4928 | 3.0 | 45 | 0.6287 | 0.6863 | 0.7681 | 0.7272 |
| 0.3613 | 4.0 | 60 | 0.7397 | 0.6789 | 0.7631 | 0.7210 |
| 0.2399 | 5.0 | 75 | 0.9838 | 0.6593 | 0.7421 | 0.7007 |
| 0.1438 | 6.0 | 90 | 1.2018 | 0.6225 | 0.6932 | 0.6579 |
| 0.099 | 7.0 | 105 | 1.4125 | 0.6299 | 0.7091 | 0.6695 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1