Downloads · 30 days
40
62% of all-time downloads
gpt2_mini_baby_100M_32768_42
xiulinyang/gpt2_mini_baby_100M_32768_42
gpt2_mini_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
65
Public
Repo size
8.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin119 MB · 98%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Oct 20, 2025
- Updated
- Oct 20, 2025
- SHA
- cda70f03
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_mini_baby_100M_32768_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3746
- Accuracy: 0.3776
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 |
|---|---|---|---|---|
| 6.9128 | 0.23 | 2000 | 6.5061 | 0.1697 |
| 5.1709 | 0.45 | 4000 | 5.4740 | 0.2120 |
| 4.7278 | 0.68 | 6000 | 5.1105 | 0.2252 |
| 4.4583 | 0.91 | 8000 | 4.8617 | 0.2418 |
| 4.2379 | 1.13 | 10000 | 4.6517 | 0.2596 |
| 4.0511 | 1.36 | 12000 | 4.4771 | 0.2730 |
| 3.8999 | 1.59 | 14000 | 4.3265 | 0.2843 |
| 3.7702 | 1.81 | 16000 | 4.2006 | 0.2942 |
| 3.6572 | 2.04 | 18000 | 4.1037 | 0.3021 |
| 3.5709 | 2.27 | 20000 | 4.0113 | 0.3093 |
| 3.4851 | 2.49 | 22000 | 3.9402 | 0.3169 |
| 3.4192 | 2.72 | 24000 | 3.8823 | 0.3224 |
| 3.3567 | 2.94 | 26000 | 3.8327 | 0.3280 |
| 3.3007 | 3.17 | 28000 | 3.7816 | 0.3335 |
| 3.2461 | 3.4 | 30000 | 3.7452 | 0.3359 |
| 3.2279 | 3.62 | 32000 | 3.7070 | 0.3403 |
| 3.1961 | 3.85 | 34000 | 3.6820 | 0.3419 |
| 3.1559 | 4.08 | 36000 | 3.6598 | 0.3450 |
| 3.1309 | 4.3 | 38000 | 3.6376 | 0.3463 |
| 3.1134 | 4.53 | 40000 | 3.6097 | 0.3494 |
| 3.0978 | 4.76 | 42000 | 3.5894 | 0.3519 |
| 3.0766 | 4.98 | 44000 | 3.5693 | 0.3540 |
| 3.0365 | 5.21 | 46000 | 3.5576 | 0.3560 |
| 3.0251 | 5.44 | 48000 | 3.5331 | 0.3583 |
| 3.0213 | 5.66 | 50000 | 3.5233 | 0.3598 |
| 3.0048 | 5.89 | 52000 | 3.5028 | 0.3610 |
| 2.968 | 6.12 | 54000 | 3.5017 | 0.3623 |
| 2.9805 | 6.34 | 56000 | 3.4903 | 0.3629 |
| 2.9665 | 6.57 | 58000 | 3.4774 | 0.3644 |
| 2.9559 | 6.8 | 60000 | 3.4683 | 0.3653 |
| 2.9473 | 7.02 | 62000 | 3.4626 | 0.3665 |
| 2.9228 | 7.25 | 64000 | 3.4542 | 0.3677 |
| 2.9243 | 7.47 | 66000 | 3.4510 | 0.3682 |
| 2.9108 | 7.7 | 68000 | 3.4418 | 0.3695 |
| 2.9209 | 7.93 | 70000 | 3.4349 | 0.3697 |
| 2.889 | 8.15 | 72000 | 3.4317 | 0.3703 |
| 2.8862 | 8.38 | 74000 | 3.4279 | 0.3709 |
| 2.8889 | 8.61 | 76000 | 3.4189 | 0.3719 |
| 2.8835 | 8.83 | 78000 | 3.4159 | 0.3723 |
| 2.8685 | 9.06 | 80000 | 3.4122 | 0.3736 |
| 2.8568 | 9.29 | 82000 | 3.4062 | 0.3735 |
| 2.8599 | 9.51 | 84000 | 3.3998 | 0.3744 |
| 2.8664 | 9.74 | 86000 | 3.3955 | 0.3749 |
| 2.852 | 9.97 | 88000 | 3.3891 | 0.3755 |
| 2.8309 | 10.19 | 90000 | 3.3878 | 0.3760 |
| 2.8354 | 10.42 | 92000 | 3.3860 | 0.3762 |
| 2.84 | 10.65 | 94000 | 3.3796 | 0.3768 |
| 2.8291 | 10.87 | 96000 | 3.3772 | 0.3773 |
| 2.817 | 11.1 | 98000 | 3.3767 | 0.3774 |
| 2.825 | 11.33 | 100000 | 3.3746 | 0.3776 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3
- Type
- gpt2
- Created
- Oct 20, 2025
- Updated
- Oct 20, 2025