|
--- |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-ds |
|
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-ds |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 6.5115 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 7.9456 | 0.08 | 10 | 7.6166 | |
|
| 7.4919 | 0.16 | 20 | 7.3649 | |
|
| 7.3086 | 0.24 | 30 | 7.1963 | |
|
| 7.1312 | 0.32 | 40 | 7.0145 | |
|
| 6.9745 | 0.4 | 50 | 6.8656 | |
|
| 6.8648 | 0.48 | 60 | 6.7427 | |
|
| 6.7591 | 0.56 | 70 | 6.6575 | |
|
| 6.6745 | 0.64 | 80 | 6.5982 | |
|
| 6.6597 | 0.72 | 90 | 6.5550 | |
|
| 6.6284 | 0.8 | 100 | 6.5302 | |
|
| 6.5895 | 0.88 | 110 | 6.5159 | |
|
| 6.5568 | 0.96 | 120 | 6.5115 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
