<!-- 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_stsb_384
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: 2.3296
- Pearson: 0.0643
- Spearmanr: 0.0635
- Combined Score: 0.0639
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 |
---|---|---|---|---|---|---|
4.1667 | 1.0 | 23 | 2.3937 | 0.0211 | 0.0215 | 0.0213 |
2.1645 | 2.0 | 46 | 2.3296 | 0.0643 | 0.0635 | 0.0639 |
2.0445 | 3.0 | 69 | 2.5873 | 0.0574 | 0.0760 | 0.0667 |
1.9177 | 4.0 | 92 | 2.5104 | 0.1360 | 0.1374 | 0.1367 |
1.6933 | 5.0 | 115 | 2.4024 | 0.1910 | 0.2072 | 0.1991 |
1.4482 | 6.0 | 138 | 2.5412 | 0.2007 | 0.2127 | 0.2067 |
1.2485 | 7.0 | 161 | 2.5616 | 0.1943 | 0.2005 | 0.1974 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2