<!-- 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. -->
hBERTv2_new_pretrain_w_init_48_ver2_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.6098
- Accuracy: 0.6814
- F1: 0.7876
- Combined Score: 0.7345
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 |
|---|---|---|---|---|---|---|
| 0.6536 | 1.0 | 58 | 0.6201 | 0.6667 | 0.7785 | 0.7226 |
| 0.6165 | 2.0 | 116 | 0.6098 | 0.6814 | 0.7876 | 0.7345 |
| 0.5699 | 3.0 | 174 | 0.6265 | 0.6593 | 0.7352 | 0.6973 |
| 0.4763 | 4.0 | 232 | 0.6630 | 0.6887 | 0.7873 | 0.7380 |
| 0.3676 | 5.0 | 290 | 0.8272 | 0.7083 | 0.8114 | 0.7599 |
| 0.2392 | 6.0 | 348 | 1.0790 | 0.6495 | 0.7597 | 0.7046 |
| 0.1663 | 7.0 | 406 | 1.5179 | 0.6225 | 0.7169 | 0.6697 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
