|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: EleutherAI/gpt-neo-125M |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt-neo-125M_menuitemexp |
|
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. --> |
|
|
|
# gpt-neo-125M_menuitemexp |
|
|
|
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8843 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 25 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 9.1319 | 0.4918 | 30 | 7.7822 | |
|
| 7.0116 | 0.9836 | 60 | 6.2200 | |
|
| 5.5238 | 1.4754 | 90 | 4.9230 | |
|
| 4.2988 | 1.9672 | 120 | 3.8166 | |
|
| 3.296 | 2.4590 | 150 | 2.9837 | |
|
| 2.5326 | 2.9508 | 180 | 2.2714 | |
|
| 1.8979 | 3.4426 | 210 | 1.8421 | |
|
| 1.6111 | 3.9344 | 240 | 1.5914 | |
|
| 1.3322 | 4.4262 | 270 | 1.4063 | |
|
| 1.1786 | 4.9180 | 300 | 1.2800 | |
|
| 1.0535 | 5.4098 | 330 | 1.1787 | |
|
| 0.9352 | 5.9016 | 360 | 1.1194 | |
|
| 0.8669 | 6.3934 | 390 | 1.0640 | |
|
| 0.8312 | 6.8852 | 420 | 1.0327 | |
|
| 0.7797 | 7.3770 | 450 | 1.0137 | |
|
| 0.7653 | 7.8689 | 480 | 0.9842 | |
|
| 0.7149 | 8.3607 | 510 | 0.9717 | |
|
| 0.7059 | 8.8525 | 540 | 0.9627 | |
|
| 0.6857 | 9.3443 | 570 | 0.9478 | |
|
| 0.6648 | 9.8361 | 600 | 0.9424 | |
|
| 0.654 | 10.3279 | 630 | 0.9343 | |
|
| 0.6452 | 10.8197 | 660 | 0.9258 | |
|
| 0.6032 | 11.3115 | 690 | 0.9343 | |
|
| 0.6174 | 11.8033 | 720 | 0.9123 | |
|
| 0.5936 | 12.2951 | 750 | 0.9071 | |
|
| 0.5865 | 12.7869 | 780 | 0.9011 | |
|
| 0.5975 | 13.2787 | 810 | 0.8992 | |
|
| 0.5714 | 13.7705 | 840 | 0.8958 | |
|
| 0.5533 | 14.2623 | 870 | 0.8996 | |
|
| 0.5508 | 14.7541 | 900 | 0.8985 | |
|
| 0.5496 | 15.2459 | 930 | 0.8930 | |
|
| 0.5389 | 15.7377 | 960 | 0.8943 | |
|
| 0.5453 | 16.2295 | 990 | 0.8915 | |
|
| 0.5355 | 16.7213 | 1020 | 0.8863 | |
|
| 0.5271 | 17.2131 | 1050 | 0.8894 | |
|
| 0.5276 | 17.7049 | 1080 | 0.8884 | |
|
| 0.5131 | 18.1967 | 1110 | 0.8891 | |
|
| 0.513 | 18.6885 | 1140 | 0.8860 | |
|
| 0.5075 | 19.1803 | 1170 | 0.8866 | |
|
| 0.5131 | 19.6721 | 1200 | 0.8848 | |
|
| 0.5022 | 20.1639 | 1230 | 0.8851 | |
|
| 0.5116 | 20.6557 | 1260 | 0.8854 | |
|
| 0.5015 | 21.1475 | 1290 | 0.8851 | |
|
| 0.5063 | 21.6393 | 1320 | 0.8844 | |
|
| 0.5064 | 22.1311 | 1350 | 0.8844 | |
|
| 0.4869 | 22.6230 | 1380 | 0.8845 | |
|
| 0.5047 | 23.1148 | 1410 | 0.8849 | |
|
| 0.5027 | 23.6066 | 1440 | 0.8846 | |
|
| 0.4911 | 24.0984 | 1470 | 0.8845 | |
|
| 0.5007 | 24.5902 | 1500 | 0.8844 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
