|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: openai-community/gpt2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: finetuned_gpt2_model2 |
|
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. --> |
|
|
|
# finetuned_gpt2_model2 |
|
|
|
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1285 |
|
- Precision: 0.3701 |
|
- Recall: 0.4221 |
|
- F1: 0.3944 |
|
- Accuracy: 0.9579 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 250 | 0.1313 | 0.3755 | 0.4334 | 0.4024 | 0.9570 | |
|
| 0.1287 | 2.0 | 500 | 0.1298 | 0.3706 | 0.4266 | 0.3967 | 0.9577 | |
|
| 0.1287 | 3.0 | 750 | 0.1298 | 0.3746 | 0.4242 | 0.3979 | 0.9573 | |
|
| 0.1269 | 4.0 | 1000 | 0.1285 | 0.3701 | 0.4221 | 0.3944 | 0.9579 | |
|
| 0.1269 | 5.0 | 1250 | 0.1287 | 0.3771 | 0.4300 | 0.4018 | 0.9576 | |
|
| 0.127 | 6.0 | 1500 | 0.1288 | 0.3774 | 0.4300 | 0.4020 | 0.9575 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
