metadata
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny-bert-sst2-distilled
results: []
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: 1.1018
- Accuracy: 0.8211
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: 6e-05
- 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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4646 | 1.0 | 527 | 1.1825 | 0.7867 |
| 0.8559 | 2.0 | 1054 | 1.0389 | 0.8085 |
| 0.6569 | 3.0 | 1581 | 1.0545 | 0.8222 |
| 0.5672 | 4.0 | 2108 | 1.0577 | 0.8188 |
| 0.5094 | 5.0 | 2635 | 1.0876 | 0.8211 |
| 0.4717 | 6.0 | 3162 | 1.0979 | 0.8200 |
| 0.4513 | 7.0 | 3689 | 1.1018 | 0.8211 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1