mobilebert_add_GLUE_Experiment_logit_kd_rte
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.3914
- Accuracy: 0.5271
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 |
|---|---|---|---|---|
| 0.4089 | 1.0 | 20 | 0.3934 | 0.5271 |
| 0.4084 | 2.0 | 40 | 0.3922 | 0.5271 |
| 0.4078 | 3.0 | 60 | 0.3914 | 0.5271 |
| 0.4073 | 4.0 | 80 | 0.3941 | 0.5271 |
| 0.4076 | 5.0 | 100 | 0.3927 | 0.5271 |
| 0.4065 | 6.0 | 120 | 0.3926 | 0.5271 |
| 0.4013 | 7.0 | 140 | 0.4076 | 0.4765 |
| 0.3911 | 8.0 | 160 | 0.4073 | 0.4838 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2