metadata
base_model: huawei-noah/TinyBERT_General_6L_768D
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: tinybert
results: []
tinybert
This model is a fine-tuned version of huawei-noah/TinyBERT_General_6L_768D on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4997
- Accuracy: 0.8235
- Precision: 0.8261
- Recall: 0.8235
- F1: 0.8241
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.6638 | 1.0 | 2000 | 0.6264 | 0.7678 | 0.8006 | 0.7678 | 0.7728 |
| 0.5171 | 2.0 | 4000 | 0.4984 | 0.8139 | 0.8149 | 0.8139 | 0.8140 |
| 0.369 | 3.0 | 6000 | 0.4997 | 0.8235 | 0.8261 | 0.8235 | 0.8241 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 3.6.0
- Tokenizers 0.19.1