<!-- 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. -->
mobilebert_sa_GLUE_Experiment_logit_kd_stsb_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.1337
- Pearson: 0.0151
- Spearmanr: 0.0166
- Combined Score: 0.0159
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: 128
- eval_batch_size: 128
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
---|---|---|---|---|---|---|
2.075 | 1.0 | 45 | 1.1337 | 0.0151 | 0.0166 | 0.0159 |
1.0752 | 2.0 | 90 | 1.1691 | 0.0603 | 0.0648 | 0.0626 |
1.0435 | 3.0 | 135 | 1.2035 | 0.0659 | 0.0746 | 0.0703 |
1.0472 | 4.0 | 180 | 1.1488 | 0.0764 | 0.0817 | 0.0790 |
0.9687 | 5.0 | 225 | 1.5234 | 0.0979 | 0.0959 | 0.0969 |
0.9016 | 6.0 | 270 | 1.2243 | 0.1434 | 0.1381 | 0.1408 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2