distilbert_sa_GLUE_Experiment_logit_kd_sst2_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7397
- Accuracy: 0.8108
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 |
|---|---|---|---|---|
| 1.1137 | 1.0 | 264 | 0.7619 | 0.8016 |
| 0.5525 | 2.0 | 528 | 0.7758 | 0.8050 |
| 0.4209 | 3.0 | 792 | 0.7397 | 0.8108 |
| 0.3585 | 4.0 | 1056 | 0.8179 | 0.8085 |
| 0.3153 | 5.0 | 1320 | 0.8172 | 0.7982 |
| 0.2824 | 6.0 | 1584 | 0.8974 | 0.8096 |
| 0.2512 | 7.0 | 1848 | 0.9205 | 0.7924 |
| 0.2315 | 8.0 | 2112 | 0.9320 | 0.8016 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2