Downloads · 30 days
10
6% of all-time downloads
gpt2_small_babyLM_100_bigbatch_20e_2
devika-tiwari/gpt2_small_babyLM_100_bigbatch_20e_2
gpt2_small_babyLM_100_bigbatch_20e_2 is a machine learning model from devika-tiwari. 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
171
Public
Repo size
10.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin498 MB · 99%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Dec 13, 2025
- Updated
- Dec 13, 2025
- SHA
- 3c3d44f6
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_babyLM_100_bigbatch_20e_2
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8590
- Accuracy: 0.4695
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: 1024
- eval_batch_size: 1024
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.8866 | 1.0 | 1382 | 3.7949 | 0.3955 |
| 3.3093 | 2.0 | 2764 | 3.3630 | 0.4229 |
| 3.0821 | 3.0 | 4146 | 3.1716 | 0.4375 |
| 2.9496 | 4.0 | 5528 | 3.0676 | 0.4466 |
| 2.8765 | 5.0 | 6910 | 3.0083 | 0.4523 |
| 2.8228 | 6.0 | 8292 | 2.9676 | 0.4564 |
| 2.7814 | 7.0 | 9674 | 2.9410 | 0.4592 |
| 2.7498 | 8.0 | 11056 | 2.9223 | 0.4613 |
| 2.7217 | 9.0 | 12438 | 2.9077 | 0.4629 |
| 2.6977 | 10.0 | 13820 | 2.8946 | 0.4644 |
| 2.6802 | 11.0 | 15202 | 2.8866 | 0.4655 |
| 2.6623 | 12.0 | 16584 | 2.8814 | 0.4660 |
| 2.6467 | 13.0 | 17966 | 2.8744 | 0.4669 |
| 2.6319 | 14.0 | 19348 | 2.8718 | 0.4673 |
| 2.6175 | 15.0 | 20730 | 2.8688 | 0.4680 |
| 2.6061 | 16.0 | 22112 | 2.8644 | 0.4684 |
| 2.5962 | 17.0 | 23494 | 2.8624 | 0.4689 |
| 2.5849 | 18.0 | 24876 | 2.8603 | 0.4692 |
| 2.5774 | 19.0 | 26258 | 2.8592 | 0.4694 |
| 2.5708 | 20.0 | 27640 | 2.8590 | 0.4695 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3
- Type
- gpt2
- Created
- Dec 13, 2025
- Updated
- Dec 13, 2025