<!-- 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_stsb_192
This model is a fine-tuned version of distilbert-base-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.8747
- Pearson: 0.1794
- Spearmanr: 0.1839
- Combined Score: 0.1816
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 | Pearson | Spearmanr | Combined Score |
---|---|---|---|---|---|---|
1.2844 | 1.0 | 1259 | 2.8897 | 0.1809 | 0.1879 | 0.1844 |
0.4862 | 2.0 | 2518 | 2.9860 | 0.1713 | 0.1773 | 0.1743 |
0.3063 | 3.0 | 3777 | 2.8747 | 0.1794 | 0.1839 | 0.1816 |
0.2133 | 4.0 | 5036 | 2.9659 | 0.1611 | 0.1665 | 0.1638 |
0.1614 | 5.0 | 6295 | 3.0123 | 0.1717 | 0.1793 | 0.1755 |
0.1289 | 6.0 | 7554 | 3.0058 | 0.1798 | 0.1900 | 0.1849 |
0.1077 | 7.0 | 8813 | 3.0575 | 0.1648 | 0.1786 | 0.1717 |
0.0921 | 8.0 | 10072 | 3.0590 | 0.1687 | 0.1758 | 0.1723 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2