mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_mnli
This model is a fine-tuned version of gokuls/mobilebert_sa_pre-training-complete on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3782
- Accuracy: 0.8390
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: 128
- eval_batch_size: 128
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6657 | 1.0 | 3068 | 0.4271 | 0.8153 |
0.4271 | 2.0 | 6136 | 0.4219 | 0.8248 |
0.3376 | 3.0 | 9204 | 0.3896 | 0.8356 |
0.2799 | 4.0 | 12272 | 0.3866 | 0.8380 |
0.2397 | 5.0 | 15340 | 0.3847 | 0.8397 |
0.21 | 6.0 | 18408 | 0.3990 | 0.8403 |
0.1885 | 7.0 | 21476 | 0.3940 | 0.8380 |
0.1723 | 8.0 | 24544 | 0.4066 | 0.8373 |
0.1588 | 9.0 | 27612 | 0.3966 | 0.8388 |
0.149 | 10.0 | 30680 | 0.3883 | 0.8422 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 6
Inference API (serverless) is not available, repository is disabled.