|
|
--- |
|
|
library_name: peft |
|
|
license: mit |
|
|
base_model: gpt2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Se124M10KInfPrompt |
|
|
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. --> |
|
|
|
|
|
# Se124M10KInfPrompt |
|
|
|
|
|
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: 0.7128 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 50 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 0.4014 | 1.0 | 267 | 1.0141 | |
|
|
| 0.2422 | 2.0 | 534 | 0.8523 | |
|
|
| 0.2202 | 3.0 | 801 | 0.8168 | |
|
|
| 0.2129 | 4.0 | 1068 | 0.7993 | |
|
|
| 0.2059 | 5.0 | 1335 | 0.7837 | |
|
|
| 0.2041 | 6.0 | 1602 | 0.7695 | |
|
|
| 0.2031 | 7.0 | 1869 | 0.7635 | |
|
|
| 0.1982 | 8.0 | 2136 | 0.7586 | |
|
|
| 0.1975 | 9.0 | 2403 | 0.7532 | |
|
|
| 0.1974 | 10.0 | 2670 | 0.7483 | |
|
|
| 0.1978 | 11.0 | 2937 | 0.7467 | |
|
|
| 0.1939 | 12.0 | 3204 | 0.7445 | |
|
|
| 0.1953 | 13.0 | 3471 | 0.7439 | |
|
|
| 0.1929 | 14.0 | 3738 | 0.7362 | |
|
|
| 0.1937 | 15.0 | 4005 | 0.7328 | |
|
|
| 0.1934 | 16.0 | 4272 | 0.7329 | |
|
|
| 0.1927 | 17.0 | 4539 | 0.7323 | |
|
|
| 0.1927 | 18.0 | 4806 | 0.7257 | |
|
|
| 0.1909 | 19.0 | 5073 | 0.7276 | |
|
|
| 0.1919 | 20.0 | 5340 | 0.7251 | |
|
|
| 0.1919 | 21.0 | 5607 | 0.7239 | |
|
|
| 0.1912 | 22.0 | 5874 | 0.7260 | |
|
|
| 0.1897 | 23.0 | 6141 | 0.7241 | |
|
|
| 0.1916 | 24.0 | 6408 | 0.7235 | |
|
|
| 0.1905 | 25.0 | 6675 | 0.7225 | |
|
|
| 0.1919 | 26.0 | 6942 | 0.7188 | |
|
|
| 0.1883 | 27.0 | 7209 | 0.7207 | |
|
|
| 0.1898 | 28.0 | 7476 | 0.7198 | |
|
|
| 0.1874 | 29.0 | 7743 | 0.7195 | |
|
|
| 0.188 | 30.0 | 8010 | 0.7194 | |
|
|
| 0.1873 | 31.0 | 8277 | 0.7182 | |
|
|
| 0.1878 | 32.0 | 8544 | 0.7212 | |
|
|
| 0.1866 | 33.0 | 8811 | 0.7171 | |
|
|
| 0.1883 | 34.0 | 9078 | 0.7151 | |
|
|
| 0.1881 | 35.0 | 9345 | 0.7176 | |
|
|
| 0.1868 | 36.0 | 9612 | 0.7149 | |
|
|
| 0.1871 | 37.0 | 9879 | 0.7157 | |
|
|
| 0.1876 | 38.0 | 10146 | 0.7162 | |
|
|
| 0.188 | 39.0 | 10413 | 0.7142 | |
|
|
| 0.1861 | 40.0 | 10680 | 0.7149 | |
|
|
| 0.1862 | 41.0 | 10947 | 0.7144 | |
|
|
| 0.1862 | 42.0 | 11214 | 0.7128 | |
|
|
| 0.186 | 43.0 | 11481 | 0.7136 | |
|
|
| 0.1868 | 44.0 | 11748 | 0.7137 | |
|
|
| 0.1837 | 45.0 | 12015 | 0.7138 | |
|
|
| 0.1868 | 46.0 | 12282 | 0.7141 | |
|
|
| 0.187 | 47.0 | 12549 | 0.7133 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.15.1 |
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.6.0+cu118 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.1 |
