<!-- 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_rte
This model is a fine-tuned version of distilbert-base-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.4234
- Accuracy: 0.4729
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 |
---|---|---|---|---|
0.4797 | 1.0 | 10 | 0.4265 | 0.4729 |
0.4185 | 2.0 | 20 | 0.4243 | 0.4729 |
0.4177 | 3.0 | 30 | 0.4247 | 0.4729 |
0.4158 | 4.0 | 40 | 0.4234 | 0.4729 |
0.4139 | 5.0 | 50 | 0.4357 | 0.4729 |
0.4052 | 6.0 | 60 | 0.4433 | 0.4729 |
0.3792 | 7.0 | 70 | 0.4748 | 0.4874 |
0.3413 | 8.0 | 80 | 0.4962 | 0.4946 |
0.3104 | 9.0 | 90 | 0.5339 | 0.4838 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2