tiny-bert-sst2-distilled
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9648
- Accuracy: 0.8245
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: 0.0002628217875157273
- train_batch_size: 128
- eval_batch_size: 128
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.5717 | 1.0 | 527 | 2.0086 | 0.8073 |
| 1.2017 | 2.0 | 1054 | 1.8121 | 0.8222 |
| 0.9081 | 3.0 | 1581 | 1.8837 | 0.8177 |
| 0.7559 | 4.0 | 2108 | 1.9089 | 0.8234 |
| 0.6694 | 5.0 | 2635 | 1.9749 | 0.8177 |
| 0.6147 | 6.0 | 3162 | 1.9445 | 0.8257 |
| 0.5729 | 7.0 | 3689 | 1.9648 | 0.8245 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Slava/tiny-bert-sst2-distilled
Base model
google/bert_uncased_L-2_H-128_A-2