distilbert_sa_GLUE_Experiment_logit_kd_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: 1.1279
- 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 |
|---|---|---|---|---|---|---|
| 3.3853 | 1.0 | 23 | 1.9990 | -0.0411 | -0.0438 | -0.0425 |
| 2.183 | 2.0 | 46 | 1.5416 | -0.0346 | -0.0339 | -0.0343 |
| 1.6692 | 3.0 | 69 | 1.2526 | -0.1157 | -0.1181 | -0.1169 |
| 1.3094 | 4.0 | 92 | 1.1279 | nan | nan | nan |
| 1.1238 | 5.0 | 115 | 1.1817 | 0.0181 | 0.0180 | 0.0181 |
| 1.0934 | 6.0 | 138 | 1.1718 | 0.0580 | 0.0536 | 0.0558 |
| 1.0784 | 7.0 | 161 | 1.1594 | 0.0592 | 0.0625 | 0.0609 |
| 1.0191 | 8.0 | 184 | 1.2390 | 0.0613 | 0.0770 | 0.0692 |
| 0.9587 | 9.0 | 207 | 1.2917 | 0.0993 | 0.1113 | 0.1053 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2