Downloads · 30 days
4
1% of all-time downloads
gpt2_small_baby_30M_32768_42
xiulinyang/gpt2_small_baby_30M_32768_42
gpt2_small_baby_30M_32768_42 is a machine learning model from xiulinyang. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
353
Public
Repo size
16.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin443 MB · 100%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Oct 19, 2025
- Updated
- Oct 19, 2025
- SHA
- 043e4887
Model card
From the Hugging Face model README
<!-- 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_small_baby_30M_32768_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0415
- Accuracy: 0.3344
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.2951 | 0.71 | 2000 | 6.0728 | 0.2002 |
| 4.3315 | 1.43 | 4000 | 5.4415 | 0.2167 |
| 4.0551 | 2.14 | 6000 | 5.1222 | 0.2421 |
| 3.8032 | 2.86 | 8000 | 4.8666 | 0.2644 |
| 3.641 | 3.57 | 10000 | 4.6957 | 0.2766 |
| 3.5313 | 4.29 | 12000 | 4.5410 | 0.2880 |
| 3.4533 | 5.0 | 14000 | 4.4303 | 0.2968 |
| 3.3798 | 5.72 | 16000 | 4.3632 | 0.3032 |
| 3.3109 | 6.43 | 18000 | 4.3000 | 0.3080 |
| 3.2608 | 7.15 | 20000 | 4.2392 | 0.3135 |
| 3.2282 | 7.86 | 22000 | 4.1918 | 0.3165 |
| 3.1827 | 8.57 | 24000 | 4.1812 | 0.3191 |
| 3.1392 | 9.29 | 26000 | 4.1280 | 0.3221 |
| 3.1321 | 10.0 | 28000 | 4.1064 | 0.3239 |
| 3.0934 | 10.72 | 30000 | 4.0898 | 0.3252 |
| 3.0465 | 11.43 | 32000 | 4.0817 | 0.3258 |
| 3.0284 | 12.15 | 34000 | 4.0602 | 0.3288 |
| 3.0238 | 12.86 | 36000 | 4.0888 | 0.3309 |
| 2.9797 | 13.58 | 38000 | 4.0737 | 0.3316 |
| 2.9414 | 14.29 | 40000 | 4.0827 | 0.3324 |
| 2.9645 | 15.01 | 42000 | 4.0548 | 0.3327 |
| 2.9164 | 15.72 | 44000 | 4.0415 | 0.3344 |
| 2.8547 | 16.43 | 46000 | 4.0695 | 0.3345 |
| 2.8496 | 17.15 | 48000 | 4.0746 | 0.3353 |
| 2.8444 | 17.86 | 50000 | 4.0647 | 0.3359 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 4.1.1
- Tokenizers 0.13.3
- Type
- gpt2
- Created
- Oct 19, 2025
- Updated
- Oct 19, 2025