<!-- 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_logit_kd_stsb_96
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: 1.1255
- Pearson: nan
- Spearmanr: nan
- Combined Score: nan
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 |
|---|---|---|---|---|---|---|
| 4.2655 | 1.0 | 23 | 3.2719 | 0.0074 | 0.0048 | 0.0061 |
| 3.8876 | 2.0 | 46 | 3.0839 | -0.0416 | -0.0423 | -0.0420 |
| 3.6577 | 3.0 | 69 | 2.8849 | nan | nan | nan |
| 3.4237 | 4.0 | 92 | 2.6822 | 0.0011 | 0.0035 | 0.0023 |
| 3.1879 | 5.0 | 115 | 2.4766 | nan | nan | nan |
| 2.9317 | 6.0 | 138 | 2.2745 | 0.0091 | 0.0098 | 0.0094 |
| 2.6928 | 7.0 | 161 | 2.0801 | 0.0173 | 0.0165 | 0.0169 |
| 2.4619 | 8.0 | 184 | 1.8985 | -0.0019 | -0.0026 | -0.0023 |
| 2.2395 | 9.0 | 207 | 1.7302 | nan | nan | nan |
| 2.0254 | 10.0 | 230 | 1.5798 | nan | nan | nan |
| 1.8258 | 11.0 | 253 | 1.4485 | nan | nan | nan |
| 1.6552 | 12.0 | 276 | 1.3382 | -0.0040 | -0.0043 | -0.0041 |
| 1.511 | 13.0 | 299 | 1.2493 | -0.0376 | -0.0378 | -0.0377 |
| 1.3781 | 14.0 | 322 | 1.1843 | nan | nan | nan |
| 1.2754 | 15.0 | 345 | 1.1427 | nan | nan | nan |
| 1.193 | 16.0 | 368 | 1.1255 | nan | nan | nan |
| 1.1427 | 17.0 | 391 | 1.1320 | 0.0123 | 0.0102 | 0.0113 |
| 1.1061 | 18.0 | 414 | 1.1565 | 0.0412 | 0.0370 | 0.0391 |
| 1.0979 | 19.0 | 437 | 1.1724 | nan | nan | nan |
| 1.0972 | 20.0 | 460 | 1.1748 | 0.0246 | 0.0255 | 0.0251 |
| 1.0882 | 21.0 | 483 | 1.1792 | nan | nan | nan |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
