distilbert_sa_GLUE_Experiment_data_aug_mnli_384
This model is a fine-tuned version of distilbert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.9264
- Accuracy: 0.6353
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 |
|---|---|---|---|---|
| 0.799 | 1.0 | 31440 | 0.9061 | 0.6341 |
| 0.5094 | 2.0 | 62880 | 1.0978 | 0.6270 |
| 0.3276 | 3.0 | 94320 | 1.3038 | 0.6245 |
| 0.2273 | 4.0 | 125760 | 1.4093 | 0.6210 |
| 0.1682 | 5.0 | 157200 | 1.5859 | 0.6122 |
| 0.1302 | 6.0 | 188640 | 1.7206 | 0.6197 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2