<!-- 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_qnli_192
This model is a fine-tuned version of distilbert-base-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3981
- Accuracy: 0.5830
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 |
---|---|---|---|---|
0.4154 | 1.0 | 410 | 0.4115 | 0.5054 |
0.4103 | 2.0 | 820 | 0.4001 | 0.5826 |
0.3967 | 3.0 | 1230 | 0.3981 | 0.5830 |
0.3897 | 4.0 | 1640 | 0.3995 | 0.5942 |
0.3849 | 5.0 | 2050 | 0.4017 | 0.5885 |
0.3804 | 6.0 | 2460 | 0.4072 | 0.5836 |
0.3763 | 7.0 | 2870 | 0.4096 | 0.5751 |
0.3717 | 8.0 | 3280 | 0.4092 | 0.5773 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2