<!-- 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. -->
distilbert_sa_GLUE_Experiment_data_aug_wnli
This model is a fine-tuned version of distilbert-base-uncased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 2.4231
- Accuracy: 0.0845
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 |
---|---|---|---|---|
0.6166 | 1.0 | 218 | 2.4231 | 0.0845 |
0.4183 | 2.0 | 436 | 4.2000 | 0.0986 |
0.3033 | 3.0 | 654 | 5.7862 | 0.0704 |
0.2294 | 4.0 | 872 | 7.2969 | 0.0704 |
0.1768 | 5.0 | 1090 | 7.5620 | 0.0986 |
0.1365 | 6.0 | 1308 | 7.3554 | 0.0845 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2