<!-- 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_256
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: 1.1268
- 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 |
---|---|---|---|---|---|---|
3.1622 | 1.0 | 23 | 1.7502 | -0.0248 | -0.0193 | -0.0221 |
1.8579 | 2.0 | 46 | 1.3087 | -0.0465 | -0.0476 | -0.0470 |
1.3508 | 3.0 | 69 | 1.1268 | nan | nan | nan |
1.1078 | 4.0 | 92 | 1.1974 | 0.0294 | 0.0287 | 0.0290 |
1.0747 | 5.0 | 115 | 1.1797 | 0.0509 | 0.0597 | 0.0553 |
1.024 | 6.0 | 138 | 1.2292 | 0.0554 | 0.0782 | 0.0668 |
0.944 | 7.0 | 161 | 1.2819 | 0.1274 | 0.1441 | 0.1358 |
0.795 | 8.0 | 184 | 1.2143 | 0.1987 | 0.2082 | 0.2035 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2