Downloads · 30 days
9
4% of all-time downloads
gpt2_small_wiki_100M_32768_76
xiulinyang/gpt2_small_wiki_100M_32768_76
gpt2_small_wiki_100M_32768_76 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
250
Public
Repo size
35.4 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
- Nov 4, 2025
- Updated
- Nov 4, 2025
- SHA
- 73df7233
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_wiki_100M_32768_76
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.9867
- Accuracy: 0.3384
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: 76
- 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 |
|---|---|---|---|---|
| 7.1994 | 0.22 | 2000 | 7.1382 | 0.1369 |
| 6.3019 | 0.43 | 4000 | 6.4729 | 0.1662 |
| 5.7738 | 0.65 | 6000 | 6.0315 | 0.1837 |
| 5.3557 | 0.87 | 8000 | 5.7015 | 0.1985 |
| 5.0098 | 1.08 | 10000 | 5.4541 | 0.2116 |
| 4.7038 | 1.3 | 12000 | 5.2236 | 0.2303 |
| 4.4117 | 1.52 | 14000 | 5.0253 | 0.2463 |
| 4.1978 | 1.73 | 16000 | 4.8662 | 0.2579 |
| 4.0353 | 1.95 | 18000 | 4.7521 | 0.2666 |
| 3.8948 | 2.17 | 20000 | 4.6681 | 0.2730 |
| 3.8041 | 2.38 | 22000 | 4.5821 | 0.2796 |
| 3.7361 | 2.6 | 24000 | 4.5307 | 0.2841 |
| 3.6731 | 2.82 | 26000 | 4.4703 | 0.2889 |
| 3.6033 | 3.03 | 28000 | 4.4253 | 0.2923 |
| 3.5406 | 3.25 | 30000 | 4.3861 | 0.2967 |
| 3.5068 | 3.47 | 32000 | 4.3553 | 0.2987 |
| 3.4718 | 3.68 | 34000 | 4.3285 | 0.3019 |
| 3.4479 | 3.9 | 36000 | 4.2997 | 0.3042 |
| 3.3698 | 4.12 | 38000 | 4.2818 | 0.3064 |
| 3.3623 | 4.33 | 40000 | 4.2655 | 0.3080 |
| 3.3413 | 4.55 | 42000 | 4.2401 | 0.3105 |
| 3.3265 | 4.77 | 44000 | 4.2078 | 0.3129 |
| 3.301 | 4.98 | 46000 | 4.1884 | 0.3144 |
| 3.2195 | 5.2 | 48000 | 4.1815 | 0.3163 |
| 3.2155 | 5.42 | 50000 | 4.1620 | 0.3183 |
| 3.2068 | 5.63 | 52000 | 4.1481 | 0.3195 |
| 3.1956 | 5.85 | 54000 | 4.1243 | 0.3214 |
| 3.1364 | 6.07 | 56000 | 4.1191 | 0.3228 |
| 3.113 | 6.28 | 58000 | 4.1108 | 0.3240 |
| 3.1142 | 6.5 | 60000 | 4.0983 | 0.3248 |
| 3.107 | 6.72 | 62000 | 4.0894 | 0.3261 |
| 3.1038 | 6.93 | 64000 | 4.0761 | 0.3268 |
| 3.031 | 7.15 | 66000 | 4.0725 | 0.3278 |
| 3.0355 | 7.36 | 68000 | 4.0642 | 0.3287 |
| 3.0379 | 7.58 | 70000 | 4.0519 | 0.3292 |
| 3.0367 | 7.8 | 72000 | 4.0377 | 0.3312 |
| 3.0259 | 8.01 | 74000 | 4.0370 | 0.3322 |
| 2.9667 | 8.23 | 76000 | 4.0366 | 0.3322 |
| 2.9684 | 8.45 | 78000 | 4.0337 | 0.3325 |
| 2.9693 | 8.66 | 80000 | 4.0196 | 0.3335 |
| 2.9701 | 8.88 | 82000 | 4.0072 | 0.3348 |
| 2.9116 | 9.1 | 84000 | 4.0167 | 0.3349 |
| 2.9155 | 9.31 | 86000 | 4.0114 | 0.3352 |
| 2.9104 | 9.53 | 88000 | 4.0061 | 0.3357 |
| 2.9138 | 9.75 | 90000 | 3.9983 | 0.3368 |
| 2.91 | 9.96 | 92000 | 3.9942 | 0.3371 |
| 2.8689 | 10.18 | 94000 | 3.9946 | 0.3373 |
| 2.8666 | 10.4 | 96000 | 3.9934 | 0.3379 |
| 2.8607 | 10.61 | 98000 | 3.9867 | 0.3383 |
| 2.863 | 10.83 | 100000 | 3.9867 | 0.3384 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3
- Type
- gpt2
- Created
- Nov 4, 2025
- Updated
- Nov 4, 2025