metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert-base-uncased_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7867647058823529
- name: F1
type: f1
value: 0.8481675392670157
bert-base-uncased_mrpc
This model is a fine-tuned version of google-bert/bert-base-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.4455
- Accuracy: 0.7868
- F1: 0.8482
- Combined Score: 0.8175
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 |
|---|---|---|---|---|---|---|
| 0.5933 | 1.0 | 15 | 0.5066 | 0.7745 | 0.8351 | 0.8048 |
| 0.4605 | 2.0 | 30 | 0.4455 | 0.7868 | 0.8482 | 0.8175 |
| 0.31 | 3.0 | 45 | 0.5169 | 0.8162 | 0.8777 | 0.8469 |
| 0.1871 | 4.0 | 60 | 0.4473 | 0.8407 | 0.8862 | 0.8634 |
| 0.1453 | 5.0 | 75 | 0.5061 | 0.8235 | 0.8672 | 0.8453 |
| 0.0963 | 6.0 | 90 | 0.5724 | 0.8284 | 0.8797 | 0.8541 |
| 0.0515 | 7.0 | 105 | 0.7238 | 0.8333 | 0.8863 | 0.8598 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3