|
--- |
|
license: apache-2.0 |
|
base_model: bert-large-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert-large-cased-bn-adapter-3.17M-snli-model3 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# bert-large-cased-bn-adapter-3.17M-snli-model3 |
|
|
|
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co./bert-large-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7627 |
|
- Accuracy: 0.7315 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 61 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.4101 | 1.0 | 8584 | 0.3392 | 0.8718 | |
|
| 0.3707 | 2.0 | 17168 | 0.3116 | 0.8842 | |
|
| 0.3628 | 3.0 | 25752 | 0.3035 | 0.8879 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
