<!-- 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_add_GLUE_Experiment_logit_kd_pretrain_qqp
This model is a fine-tuned version of gokuls/distilbert_add_pre-training-complete on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.6175
- Accuracy: 0.6518
- F1: 0.1118
- Combined Score: 0.3818
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 | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.7332 | 1.0 | 1422 | 0.6640 | 0.6318 | 0.0 | 0.3159 |
| 0.6295 | 2.0 | 2844 | 0.6362 | 0.6446 | 0.0739 | 0.3593 |
| 0.5849 | 3.0 | 4266 | 0.6227 | 0.6401 | 0.0478 | 0.3439 |
| 0.5561 | 4.0 | 5688 | 0.6212 | 0.6517 | 0.1097 | 0.3807 |
| 0.5343 | 5.0 | 7110 | 0.6175 | 0.6518 | 0.1118 | 0.3818 |
| 0.52 | 6.0 | 8532 | 0.6184 | 0.6487 | 0.0949 | 0.3718 |
| 0.5093 | 7.0 | 9954 | 0.6239 | 0.6588 | 0.1472 | 0.4030 |
| 0.501 | 8.0 | 11376 | 0.6235 | 0.6649 | 0.1783 | 0.4216 |
| 0.4947 | 9.0 | 12798 | 0.6211 | 0.6622 | 0.1632 | 0.4127 |
| 0.4895 | 10.0 | 14220 | 0.6256 | 0.6688 | 0.1970 | 0.4329 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
