metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: add_BERT_no_pretrain_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
config: qqp
split: validation
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.6823893148651992
- name: F1
type: f1
value: 0.4704523897892697
add_BERT_no_pretrain_qqp
This model is a fine-tuned version of on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.5939
- Accuracy: 0.6824
- F1: 0.4705
- Combined Score: 0.5764
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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- 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 |
|---|---|---|---|---|---|---|
| 0.657 | 1.0 | 2843 | 0.6438 | 0.6490 | 0.1608 | 0.4049 |
| 0.6273 | 2.0 | 5686 | 0.6302 | 0.6443 | 0.1919 | 0.4181 |
| 0.6273 | 3.0 | 8529 | 0.6265 | 0.6527 | 0.3602 | 0.5064 |
| 0.6093 | 4.0 | 11372 | 0.5939 | 0.6824 | 0.4705 | 0.5764 |
| 0.5932 | 5.0 | 14215 | 0.5962 | 0.6802 | 0.4170 | 0.5486 |
| 0.599 | 6.0 | 17058 | 0.5981 | 0.6757 | 0.4795 | 0.5776 |
| 0.6063 | 7.0 | 19901 | 0.6511 | 0.6318 | 0.0 | 0.3159 |
| 0.6264 | 8.0 | 22744 | 0.6261 | 0.6532 | 0.2074 | 0.4303 |
| 0.6348 | 9.0 | 25587 | 0.6774 | 0.6318 | 0.0 | 0.3159 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3