bert_uncased_L-4_H-512_A-8_qqp
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2574
- Accuracy: 0.8914
- F1: 0.8539
- Combined Score: 0.8727
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 |
|---|---|---|---|---|---|---|
| 0.3551 | 1.0 | 1422 | 0.2993 | 0.8693 | 0.8179 | 0.8436 |
| 0.2662 | 2.0 | 2844 | 0.2663 | 0.8842 | 0.8492 | 0.8667 |
| 0.217 | 3.0 | 4266 | 0.2574 | 0.8914 | 0.8539 | 0.8727 |
| 0.179 | 4.0 | 5688 | 0.2646 | 0.8937 | 0.8550 | 0.8744 |
| 0.1487 | 5.0 | 7110 | 0.2920 | 0.8938 | 0.8582 | 0.8760 |
| 0.1228 | 6.0 | 8532 | 0.2971 | 0.8936 | 0.8587 | 0.8762 |
| 0.1042 | 7.0 | 9954 | 0.3390 | 0.8916 | 0.8577 | 0.8746 |
| 0.0882 | 8.0 | 11376 | 0.3568 | 0.8931 | 0.8604 | 0.8768 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 104
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for gokulsrinivasagan/bert_uncased_L-4_H-512_A-8_qqp
Base model
google/bert_uncased_L-4_H-512_A-8Dataset used to train gokulsrinivasagan/bert_uncased_L-4_H-512_A-8_qqp
Evaluation results
- Accuracy on GLUE QQPself-reported0.891
- F1 on GLUE QQPself-reported0.854