<!-- 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_sst2_384
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: 0.5433
- Accuracy: 0.7878
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 |
---|---|---|---|---|
0.3436 | 1.0 | 4374 | 0.5433 | 0.7878 |
0.2417 | 2.0 | 8748 | 0.6281 | 0.7890 |
0.1823 | 3.0 | 13122 | 0.7529 | 0.7775 |
0.1432 | 4.0 | 17496 | 0.8767 | 0.7741 |
0.117 | 5.0 | 21870 | 0.9864 | 0.7638 |
0.0986 | 6.0 | 26244 | 1.1162 | 0.7649 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2