hBERTv1_new_pretrain_48_emb_com_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5831
- Accuracy: 0.7083
- F1: 0.8172
- Combined Score: 0.7628
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 |
---|---|---|---|---|---|---|
0.6776 | 1.0 | 29 | 0.6052 | 0.7010 | 0.8146 | 0.7578 |
0.6271 | 2.0 | 58 | 0.6112 | 0.6961 | 0.8025 | 0.7493 |
0.58 | 3.0 | 87 | 0.5831 | 0.7083 | 0.8172 | 0.7628 |
0.5494 | 4.0 | 116 | 0.6458 | 0.7010 | 0.8094 | 0.7552 |
0.5148 | 5.0 | 145 | 0.6067 | 0.6838 | 0.7882 | 0.7360 |
0.4573 | 6.0 | 174 | 0.6267 | 0.6863 | 0.7935 | 0.7399 |
0.395 | 7.0 | 203 | 0.7897 | 0.6275 | 0.7295 | 0.6785 |
0.3102 | 8.0 | 232 | 0.9040 | 0.6593 | 0.7599 | 0.7096 |
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/hBERTv1_new_pretrain_48_emb_com_mrpc
Evaluation results
- Accuracy on GLUE MRPCvalidation set self-reported0.708
- F1 on GLUE MRPCvalidation set self-reported0.817