metadata
library_name: transformers
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_distillation
results: []
bert_distillation
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: 1.0805
- Model Preparation Time: 0.0009
- Accuracy: 0.8360
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 2023
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy |
|---|---|---|---|---|---|
| 1.2724 | 1.0 | 527 | 1.0482 | 0.0009 | 0.8108 |
| 0.6783 | 2.0 | 1054 | 1.0651 | 0.0009 | 0.8280 |
| 0.5164 | 3.0 | 1581 | 1.0805 | 0.0009 | 0.8360 |
| 0.4397 | 4.0 | 2108 | 1.1196 | 0.0009 | 0.8280 |
| 0.3887 | 5.0 | 2635 | 1.1339 | 0.0009 | 0.8314 |
| 0.3558 | 6.0 | 3162 | 1.1385 | 0.0009 | 0.8326 |
| 0.3397 | 7.0 | 3689 | 1.1512 | 0.0009 | 0.8268 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2