<!-- 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_48_ver2_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5902
- Accuracy: 0.6838
- F1: 0.7969
- Combined Score: 0.7403
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 |
|---|---|---|---|---|---|---|
| 0.6435 | 1.0 | 58 | 0.6367 | 0.6544 | 0.7531 | 0.7037 |
| 0.6154 | 2.0 | 116 | 0.5902 | 0.6838 | 0.7969 | 0.7403 |
| 0.5494 | 3.0 | 174 | 0.6056 | 0.6985 | 0.7953 | 0.7469 |
| 0.4115 | 4.0 | 232 | 0.7328 | 0.625 | 0.7119 | 0.6684 |
| 0.2774 | 5.0 | 290 | 0.9700 | 0.6740 | 0.7654 | 0.7197 |
| 0.1932 | 6.0 | 348 | 1.1100 | 0.6667 | 0.7563 | 0.7115 |
| 0.1464 | 7.0 | 406 | 1.1999 | 0.6642 | 0.7540 | 0.7091 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
