<!-- 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_24_mrpc
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5847
- Accuracy: 0.7010
- F1: 0.8135
- Combined Score: 0.7572
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 |
---|---|---|---|---|---|---|
0.6554 | 1.0 | 29 | 0.5847 | 0.7010 | 0.8135 | 0.7572 |
0.6027 | 2.0 | 58 | 0.5925 | 0.6985 | 0.8150 | 0.7568 |
0.5423 | 3.0 | 87 | 0.6010 | 0.6887 | 0.8049 | 0.7468 |
0.4401 | 4.0 | 116 | 0.6617 | 0.6961 | 0.8050 | 0.7506 |
0.2731 | 5.0 | 145 | 0.9531 | 0.6348 | 0.7151 | 0.6750 |
0.16 | 6.0 | 174 | 1.0283 | 0.6985 | 0.8045 | 0.7515 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3