<!-- 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. -->
add_BERT_48_mrpc
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new_48 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5979
- Accuracy: 0.6471
- F1: 0.7353
- Combined Score: 0.6912
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 |
---|---|---|---|---|---|---|
0.6617 | 1.0 | 29 | 0.6153 | 0.6838 | 0.7975 | 0.7407 |
0.628 | 2.0 | 58 | 0.5979 | 0.6471 | 0.7353 | 0.6912 |
0.5741 | 3.0 | 87 | 0.6442 | 0.6985 | 0.8189 | 0.7587 |
0.5094 | 4.0 | 116 | 0.6365 | 0.6912 | 0.7850 | 0.7381 |
0.4123 | 5.0 | 145 | 0.7135 | 0.6740 | 0.7577 | 0.7159 |
0.2939 | 6.0 | 174 | 0.8433 | 0.6740 | 0.7734 | 0.7237 |
0.2194 | 7.0 | 203 | 1.1034 | 0.6471 | 0.7429 | 0.6950 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3