add_BERT_24_rte
This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6936
- Accuracy: 0.5271
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 |
|---|---|---|---|---|
| 0.7559 | 1.0 | 20 | 0.6977 | 0.5271 |
| 0.704 | 2.0 | 40 | 0.6936 | 0.5271 |
| 0.701 | 3.0 | 60 | 0.6969 | 0.5126 |
| 0.6801 | 4.0 | 80 | 0.7166 | 0.4729 |
| 0.6792 | 5.0 | 100 | 0.7125 | 0.5307 |
| 0.6577 | 6.0 | 120 | 0.7617 | 0.4874 |
| 0.5614 | 7.0 | 140 | 0.9793 | 0.4765 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3