Downloads · 30 days
21
47% of all-time downloads
gpt2_tiny_baby_100M_32768_42
xiulinyang/gpt2_tiny_baby_100M_32768_42
gpt2_tiny_baby_100M_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
45
Public
Repo size
3.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin46.7 MB · 95%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Oct 12, 2025
- Updated
- Oct 12, 2025
- SHA
- 98aaae15
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_tiny_baby_100M_32768_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6074
- Accuracy: 0.3498
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 |
|---|---|---|---|---|
| 8.548 | 0.23 | 2000 | 8.1195 | 0.1336 |
| 6.112 | 0.45 | 4000 | 6.1441 | 0.1863 |
| 5.1469 | 0.68 | 6000 | 5.4803 | 0.2105 |
| 4.8151 | 0.91 | 8000 | 5.2002 | 0.2213 |
| 4.6071 | 1.13 | 10000 | 4.9978 | 0.2326 |
| 4.4279 | 1.36 | 12000 | 4.8260 | 0.2461 |
| 4.2792 | 1.59 | 14000 | 4.6859 | 0.2564 |
| 4.1445 | 1.81 | 16000 | 4.5612 | 0.2651 |
| 4.021 | 2.04 | 18000 | 4.4521 | 0.2723 |
| 3.9258 | 2.27 | 20000 | 4.3515 | 0.2798 |
| 3.834 | 2.49 | 22000 | 4.2739 | 0.2849 |
| 3.7631 | 2.72 | 24000 | 4.1986 | 0.2906 |
| 3.6951 | 2.94 | 26000 | 4.1383 | 0.2955 |
| 3.6384 | 3.17 | 28000 | 4.0808 | 0.3011 |
| 3.5713 | 3.4 | 30000 | 4.0299 | 0.3050 |
| 3.5425 | 3.62 | 32000 | 3.9783 | 0.3103 |
| 3.4977 | 3.85 | 34000 | 3.9439 | 0.3132 |
| 3.4527 | 4.08 | 36000 | 3.9134 | 0.3177 |
| 3.4187 | 4.3 | 38000 | 3.8761 | 0.3202 |
| 3.3921 | 4.53 | 40000 | 3.8478 | 0.3238 |
| 3.3712 | 4.76 | 42000 | 3.8208 | 0.3259 |
| 3.3458 | 4.98 | 44000 | 3.8012 | 0.3279 |
| 3.3128 | 5.21 | 46000 | 3.7859 | 0.3308 |
| 3.297 | 5.44 | 48000 | 3.7629 | 0.3324 |
| 3.2921 | 5.66 | 50000 | 3.7514 | 0.3339 |
| 3.2735 | 5.89 | 52000 | 3.7329 | 0.3358 |
| 3.2473 | 6.12 | 54000 | 3.7231 | 0.3369 |
| 3.257 | 6.34 | 56000 | 3.7148 | 0.3375 |
| 3.2399 | 6.57 | 58000 | 3.7080 | 0.3384 |
| 3.2282 | 6.8 | 60000 | 3.6976 | 0.3392 |
| 3.2212 | 7.02 | 62000 | 3.6880 | 0.3403 |
| 3.2042 | 7.25 | 64000 | 3.6813 | 0.3411 |
| 3.2031 | 7.47 | 66000 | 3.6789 | 0.3419 |
| 3.1887 | 7.7 | 68000 | 3.6704 | 0.3427 |
| 3.1983 | 7.93 | 70000 | 3.6622 | 0.3433 |
| 3.1769 | 8.15 | 72000 | 3.6565 | 0.3441 |
| 3.1714 | 8.38 | 74000 | 3.6567 | 0.3443 |
| 3.1742 | 8.61 | 76000 | 3.6471 | 0.3451 |
| 3.1667 | 8.83 | 78000 | 3.6431 | 0.3455 |
| 3.1572 | 9.06 | 80000 | 3.6388 | 0.3463 |
| 3.1481 | 9.29 | 82000 | 3.6365 | 0.3465 |
| 3.1513 | 9.51 | 84000 | 3.6305 | 0.3473 |
| 3.1571 | 9.74 | 86000 | 3.6263 | 0.3477 |
| 3.1428 | 9.97 | 88000 | 3.6234 | 0.3482 |
| 3.1285 | 10.19 | 90000 | 3.6197 | 0.3484 |
| 3.133 | 10.42 | 92000 | 3.6161 | 0.3488 |
| 3.1375 | 10.65 | 94000 | 3.6123 | 0.3492 |
| 3.1253 | 10.87 | 96000 | 3.6102 | 0.3495 |
| 3.1188 | 11.1 | 98000 | 3.6095 | 0.3495 |
| 3.1279 | 11.33 | 100000 | 3.6074 | 0.3498 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu117
- Datasets 4.1.1
- Tokenizers 0.13.3
- Type
- gpt2
- Created
- Oct 12, 2025
- Updated
- Oct 12, 2025