<!-- 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. -->
hBERTv1_new_pretrain_w_init_48_ver2_qqp
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.4918
- Accuracy: 0.7601
- F1: 0.6952
- Combined Score: 0.7277
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: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.5279 | 1.0 | 5686 | 0.4918 | 0.7601 | 0.6952 | 0.7277 |
| 0.4826 | 2.0 | 11372 | 0.5367 | 0.7644 | 0.6556 | 0.7100 |
| 0.4943 | 3.0 | 17058 | 0.5223 | 0.7594 | 0.6440 | 0.7017 |
| 0.492 | 4.0 | 22744 | 0.5379 | 0.7600 | 0.6465 | 0.7032 |
| 0.505 | 5.0 | 28430 | 0.5431 | 0.7423 | 0.6507 | 0.6965 |
| 0.5428 | 6.0 | 34116 | 0.5789 | 0.7089 | 0.6289 | 0.6689 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
