|
|
--- |
|
|
license: mit |
|
|
base_model: gpt2-large |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: gpt2-large-agnews-classifier |
|
|
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. --> |
|
|
|
|
|
# gpt2-large-agnews-classifier |
|
|
|
|
|
This model is a fine-tuned version of [gpt2-large](https://huggingface.co/gpt2-large) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1733 |
|
|
- Accuracy: 0.9514 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 16 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- num_epochs: 2 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 0.1796 | 1.0 | 7500 | 0.1746 | 0.9436 | |
|
|
| 0.0928 | 2.0 | 15000 | 0.1733 | 0.9514 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.40.0 |
|
|
- Pytorch 2.6.0+cu118 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
