<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
add_BERT_48_qqp
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new_48 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.5350
- Accuracy: 0.7352
- F1: 0.5825
- Combined Score: 0.6589
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 |
---|---|---|---|---|---|---|
0.5553 | 1.0 | 2843 | 0.5350 | 0.7352 | 0.5825 | 0.6589 |
0.5508 | 2.0 | 5686 | 0.5437 | 0.7274 | 0.5239 | 0.6257 |
0.5741 | 3.0 | 8529 | 0.5982 | 0.6716 | 0.4706 | 0.5711 |
0.6098 | 4.0 | 11372 | 0.6233 | 0.6660 | 0.3837 | 0.5249 |
0.6415 | 5.0 | 14215 | 0.6580 | 0.6318 | 0.0 | 0.3159 |
0.6244 | 6.0 | 17058 | 0.6158 | 0.6520 | 0.4099 | 0.5309 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3