distilbert_add_GLUE_Experiment_logit_kd_stsb
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: 1.1735
- Pearson: 0.0712
- Spearmanr: 0.0650
- Combined Score: 0.0681
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 |
---|---|---|---|---|---|---|
1.8584 | 1.0 | 23 | 1.2094 | 0.0666 | 0.0636 | 0.0651 |
1.0947 | 2.0 | 46 | 1.2681 | 0.0776 | 0.0622 | 0.0699 |
1.0743 | 3.0 | 69 | 1.1735 | 0.0712 | 0.0650 | 0.0681 |
1.0098 | 4.0 | 92 | 1.3340 | 0.0809 | 0.0800 | 0.0804 |
0.9112 | 5.0 | 115 | 1.2858 | 0.1005 | 0.0958 | 0.0981 |
0.8385 | 6.0 | 138 | 1.3734 | 0.1165 | 0.1114 | 0.1140 |
0.7601 | 7.0 | 161 | 1.3383 | 0.1358 | 0.1338 | 0.1348 |
0.693 | 8.0 | 184 | 1.4171 | 0.1371 | 0.1358 | 0.1365 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 13
Dataset used to train gokuls/distilbert_add_GLUE_Experiment_logit_kd_stsb
Evaluation results
- Spearmanr on GLUE STSBvalidation set self-reported0.065