hBERTv2_new_pretrain_48_KD_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48_KD on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5941
- Accuracy: 0.6961
- F1: 0.8075
- Combined Score: 0.7518
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 |
---|---|---|---|---|---|---|
0.6497 | 1.0 | 29 | 0.5941 | 0.6961 | 0.8075 | 0.7518 |
0.6083 | 2.0 | 58 | 0.6215 | 0.6544 | 0.7197 | 0.6870 |
0.5781 | 3.0 | 87 | 0.6071 | 0.6838 | 0.8122 | 0.7480 |
0.5073 | 4.0 | 116 | 0.6257 | 0.7132 | 0.8047 | 0.7590 |
0.4077 | 5.0 | 145 | 0.7379 | 0.6373 | 0.7329 | 0.6851 |
0.2908 | 6.0 | 174 | 0.9998 | 0.6422 | 0.7286 | 0.6854 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train gokuls/hBERTv2_new_pretrain_48_KD_mrpc
Evaluation results
- Accuracy on GLUE MRPCvalidation set self-reported0.696
- F1 on GLUE MRPCvalidation set self-reported0.807