<!-- 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. -->
tiny-bert-sst2-1_mobilebert_and_bert-multi-teacher-distillation
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 2.5545
- Accuracy: 0.8280
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: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6309 | 1.0 | 4210 | 2.5545 | 0.8280 |
0.6148 | 2.0 | 8420 | 2.4299 | 0.8245 |
0.595 | 3.0 | 12630 | 2.3525 | 0.8211 |
0.5388 | 4.0 | 16840 | 2.5075 | 0.8234 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1