<!-- 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_mnli
This model is a fine-tuned version of gokuls/distilbert_add_pre-training-complete on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4768
- Accuracy: 0.6843
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 |
|---|---|---|---|---|
| 0.5762 | 1.0 | 1534 | 0.5291 | 0.5904 |
| 0.5131 | 2.0 | 3068 | 0.4986 | 0.6470 |
| 0.4806 | 3.0 | 4602 | 0.4832 | 0.6713 |
| 0.4563 | 4.0 | 6136 | 0.4803 | 0.6770 |
| 0.4352 | 5.0 | 7670 | 0.4790 | 0.6832 |
| 0.4157 | 6.0 | 9204 | 0.4866 | 0.6809 |
| 0.3984 | 7.0 | 10738 | 0.4938 | 0.6836 |
| 0.3835 | 8.0 | 12272 | 0.4940 | 0.6841 |
| 0.3703 | 9.0 | 13806 | 0.4972 | 0.6823 |
| 0.3592 | 10.0 | 15340 | 0.4992 | 0.6854 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
