|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilgpt2 |
|
tags: |
|
- generated_from_trainer |
|
library_name: peft |
|
model-index: |
|
- name: distilgpt2-lora-text-classification |
|
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. --> |
|
|
|
# distilgpt2-lora-text-classification |
|
|
|
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 6.5596 |
|
- Rougel F1: 0.0 |
|
|
|
## 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-06 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rougel F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:| |
|
| No log | 1.0 | 83 | 7.1013 | 0.0 | |
|
| No log | 2.0 | 166 | 6.9855 | 0.0 | |
|
| No log | 3.0 | 249 | 6.8850 | 0.0 | |
|
| No log | 4.0 | 332 | 6.7975 | 0.0 | |
|
| No log | 5.0 | 415 | 6.7247 | 0.0 | |
|
| No log | 6.0 | 498 | 6.6657 | 0.0 | |
|
| 7.0748 | 7.0 | 581 | 6.6194 | 0.0 | |
|
| 7.0748 | 8.0 | 664 | 6.5859 | 0.0 | |
|
| 7.0748 | 9.0 | 747 | 6.5662 | 0.0 | |
|
| 7.0748 | 10.0 | 830 | 6.5596 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.14.0 |
|
- Transformers 4.43.4 |
|
- Pytorch 2.6.0 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
