|
--- |
|
license: mit |
|
base_model: openai-community/gpt2 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- stanfordnlp/snli |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: gpt2-snli-model3 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: snli |
|
type: stanfordnlp/snli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8768542979069295 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# gpt2-snli-model3 |
|
|
|
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the snli dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3346 |
|
- Accuracy: 0.8769 |
|
|
|
## 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: 256 |
|
- eval_batch_size: 128 |
|
- seed: 9 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.4552 | 1.0 | 2146 | 0.3673 | 0.8595 | |
|
| 0.4043 | 2.0 | 4292 | 0.3391 | 0.8722 | |
|
| 0.3795 | 3.0 | 6438 | 0.3346 | 0.8769 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
