<!-- 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_48_KD_w_init_qqp
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.5377
- Accuracy: 0.7336
- F1: 0.6479
- Combined Score: 0.6907
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 |
---|---|---|---|---|---|---|
0.5751 | 1.0 | 2843 | 0.5381 | 0.7260 | 0.6367 | 0.6813 |
0.522 | 2.0 | 5686 | 0.5377 | 0.7336 | 0.6479 | 0.6907 |
0.5274 | 3.0 | 8529 | 0.5656 | 0.7333 | 0.6147 | 0.6740 |
0.5435 | 4.0 | 11372 | 0.5561 | 0.7424 | 0.6314 | 0.6869 |
0.5405 | 5.0 | 14215 | 0.5772 | 0.7359 | 0.5543 | 0.6451 |
0.5468 | 6.0 | 17058 | 0.5563 | 0.7355 | 0.5944 | 0.6649 |
0.5732 | 7.0 | 19901 | 0.5929 | 0.7148 | 0.5017 | 0.6082 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3