mobilebert_add_GLUE_Experiment_logit_kd_qnli_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 1.0610
- Accuracy: 0.5054
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 |
|---|---|---|---|---|
| 1.1396 | 1.0 | 819 | 1.0612 | 0.5054 |
| 1.1393 | 2.0 | 1638 | 1.0611 | 0.5054 |
| 1.1393 | 3.0 | 2457 | 1.0617 | 0.5054 |
| 1.1393 | 4.0 | 3276 | 1.0610 | 0.5054 |
| 1.1394 | 5.0 | 4095 | 1.0612 | 0.5054 |
| 1.1393 | 6.0 | 4914 | 1.0613 | 0.5054 |
| 1.1393 | 7.0 | 5733 | 1.0614 | 0.5054 |
| 1.1393 | 8.0 | 6552 | 1.0615 | 0.5054 |
| 1.1392 | 9.0 | 7371 | 1.0611 | 0.5054 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2