distilbert_sa_GLUE_Experiment_mrpc_192
This model is a fine-tuned version of distilbert-base-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5927
- Accuracy: 0.6887
- F1: 0.7784
- Combined Score: 0.7335
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6412 | 1.0 | 15 | 0.6239 | 0.6838 | 0.8122 | 0.7480 |
| 0.6281 | 2.0 | 30 | 0.6238 | 0.6838 | 0.8122 | 0.7480 |
| 0.629 | 3.0 | 45 | 0.6239 | 0.6838 | 0.8122 | 0.7480 |
| 0.6296 | 4.0 | 60 | 0.6236 | 0.6838 | 0.8122 | 0.7480 |
| 0.6323 | 5.0 | 75 | 0.6228 | 0.6838 | 0.8122 | 0.7480 |
| 0.6272 | 6.0 | 90 | 0.6209 | 0.6838 | 0.8122 | 0.7480 |
| 0.6175 | 7.0 | 105 | 0.6000 | 0.6838 | 0.8122 | 0.7480 |
| 0.5733 | 8.0 | 120 | 0.5927 | 0.6887 | 0.7784 | 0.7335 |
| 0.5199 | 9.0 | 135 | 0.5969 | 0.6936 | 0.7818 | 0.7377 |
| 0.4423 | 10.0 | 150 | 0.6369 | 0.6765 | 0.7700 | 0.7233 |
| 0.3645 | 11.0 | 165 | 0.6708 | 0.6838 | 0.7832 | 0.7335 |
| 0.3203 | 12.0 | 180 | 0.7179 | 0.6446 | 0.7249 | 0.6847 |
| 0.2778 | 13.0 | 195 | 0.7517 | 0.6740 | 0.7726 | 0.7233 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2